# Layer — Full Site Content > Layer is the AI platform for creative teams in the entertainment industry. Generate and edit images, video, 3D models, and audio assets with leading AI models in one workspace. Built for game studios with enterprise security, workflow automation, and team collaboration. Layer provides 247+ AI models across four modalities (image, video, 3D, audio), custom style training, node-based workflow automation, and enterprise features like SOC 2 Type II compliance, SSO/SCIM, and role-based access controls. Used by 300+ game studios worldwide. ## Core Pages - [Home](https://www.layer.ai/): AI platform overview for creative teams - [Features](https://www.layer.ai/features): Platform capabilities and creative automation features - [Pricing](https://www.layer.ai/pricing): Usage-based pricing with Creative Units, no seat fees - [Pricing (machine-readable)](https://www.layer.ai/pricing.md): Full pricing table in Markdown format > All content pages are also available as Markdown by appending .md to the URL (e.g., /blog/post-slug.md, /models/model-slug.md). - [Pricing Calculator](https://www.layer.ai/pricing/calculator): Configure models and estimate costs - [Enterprise](https://www.layer.ai/enterprise): Enterprise features, security, and compliance - [Solutions](https://www.layer.ai/solutions): Use cases for characters, UI, environments, and marketing assets - [Contact Sales](https://www.layer.ai/contact-sales): Talk to the Layer sales team ## AI Models - [All Models](https://www.layer.ai/models): Browse 247+ AI models - [Image Models](https://www.layer.ai/models/image): 82 models - [Video Models](https://www.layer.ai/models/video): 98 models - [3D Models](https://www.layer.ai/models/3d): 34 models - [Audio Models](https://www.layer.ai/models/audio): 33 models ### Image Models #### [GPT Image 2](https://www.layer.ai/models/openai-gpt-image-2) ([md](https://www.layer.ai/models/openai-gpt-image-2.md)) Provider: OpenAI | Category: Image OpenAI's latest image model with stronger text rendering, UI generation, and photorealism. Native output up to 4K with three quality tiers. Capabilities: Aspect ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9 #### [Reve 2.1](https://www.layer.ai/models/reve-reve-2-1) ([md](https://www.layer.ai/models/reve-reve-2-1.md)) Provider: Reve | Category: Image Reve's next-generation image model with strong prompt adherence and text rendering, plus native editing. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Reve 2.1 Remix](https://www.layer.ai/models/reve-reve-2-1-remix) ([md](https://www.layer.ai/models/reve-reve-2-1-remix.md)) Provider: Reve | Category: Image Reve's remix model - blends one to eight reference images into a single new image, guided by a prompt. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Gemini 3.1 Flash Image](https://www.layer.ai/models/google-gemini-3-1-flash-image) ([md](https://www.layer.ai/models/google-gemini-3-1-flash-image.md)) Provider: Google | Category: Image Google's fast, high-quality image generation model with multimodal reasoning. Capabilities: Aspect ratios: 8:1, 4:1, 21:9, 16:9, 3:2, 5:4, 4:3, 1:1, 4:5, 3:4, 2:3, 9:16, 1:4, 1:8 #### [GPT Image 1.5](https://www.layer.ai/models/openai-gpt-image-1-5) ([md](https://www.layer.ai/models/openai-gpt-image-1-5.md)) Provider: OpenAI | Category: Image GPT Image 1.5 is the latest image generation model from OpenAI, with better instruction following and adherence to prompts. Capabilities: Aspect ratios: 1:1, 2:3, 3:2 #### [MAI Image 2.5](https://www.layer.ai/models/microsoft-mai-image-2-5) ([md](https://www.layer.ai/models/microsoft-mai-image-2-5.md)) Provider: Microsoft | Category: Image Microsoft's photorealistic image model with strong typography and native editing. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Gemini 3 Pro Image](https://www.layer.ai/models/google-gemini-3-pro-image) ([md](https://www.layer.ai/models/google-gemini-3-pro-image.md)) Provider: Google | Category: Image Google's state-of-the-art image generation and editing model. Capabilities: Aspect ratios: 21:9, 16:9, 3:2, 5:4, 4:3, 1:1, 4:5, 3:4, 2:3, 9:16 #### [Gemini 3.1 Flash-Lite Image](https://www.layer.ai/models/google-gemini-3-1-flash-lite-image) ([md](https://www.layer.ai/models/google-gemini-3-1-flash-lite-image.md)) Provider: Google | Category: Image Google's fastest, most cost-efficient Gemini image generation model. Capabilities: Aspect ratios: 8:1, 4:1, 21:9, 16:9, 3:2, 5:4, 4:3, 1:1, 4:5, 3:4, 2:3, 9:16, 1:4, 1:8 #### [Grok Imagine Image](https://www.layer.ai/models/xai-grok-imagine-image) ([md](https://www.layer.ai/models/xai-grok-imagine-image.md)) Provider: xAI | Category: Image xAI's image generation model capable of creating high-quality images from text prompts. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3 #### [Qwen Image 2 Pro](https://www.layer.ai/models/qwen-qwen-image-2-pro) ([md](https://www.layer.ai/models/qwen-qwen-image-2-pro.md)) Provider: Qwen | Category: Image Qwen Image 2 Pro tier with higher quality text-to-image generation and enhanced detail. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [FLUX.2 [max]](https://www.layer.ai/models/bfl-flux-2-max) ([md](https://www.layer.ai/models/bfl-flux-2-max.md)) Provider: Black Forest Labs | Category: Image Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Krea 2 Turbo](https://www.layer.ai/models/krea-krea-2-turbo) ([md](https://www.layer.ai/models/krea-krea-2-turbo.md)) Provider: Krea | Category: Image Speed-optimized open-source version of Krea 2 — high-fidelity images in seconds, with the full Krea aesthetic range. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Luma UNI-1 Max](https://www.layer.ai/models/lumalabs-uni-1-max) ([md](https://www.layer.ai/models/lumalabs-uni-1-max.md)) Provider: Luma AI | Category: Image The highest-fidelity tier of Luma UNI-1, for hero-quality stills and premium edits. Capabilities: Aspect ratios: 1:1, 3:2, 16:9, 2:3, 9:16 #### [Seedream 4.0](https://www.layer.ai/models/bytedance-seedream-4-0) ([md](https://www.layer.ai/models/bytedance-seedream-4-0.md)) Provider: ByteDance | Category: Image Unified architecture for image generation and editing. Allows fluid movement from concept to refinement. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Krea 2 Large](https://www.layer.ai/models/krea-krea-2-large) ([md](https://www.layer.ai/models/krea-krea-2-large.md)) Provider: Krea | Category: Image Krea's flagship text-to-image model for high-fidelity generations with distinctive aesthetic range. Capabilities: Aspect ratios: 1:1, 4:3, 3:2, 16:9, 2:3, 9:16 #### [FLUX.2 [flex]](https://www.layer.ai/models/bfl-flux-2-flex) ([md](https://www.layer.ai/models/bfl-flux-2-flex.md)) Provider: Black Forest Labs | Category: Image Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Ideogram V4](https://www.layer.ai/models/ideogram-v4) ([md](https://www.layer.ai/models/ideogram-v4.md)) Provider: Ideogram | Category: Image Ideogram's latest text-to-image model with crisp visuals, accurate text, and image-to-image support. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [FLUX.2 [pro]](https://www.layer.ai/models/bfl-flux-2-pro) ([md](https://www.layer.ai/models/bfl-flux-2-pro.md)) Provider: Black Forest Labs | Category: Image Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Kling Image V3](https://www.layer.ai/models/kling-image-v3) ([md](https://www.layer.ai/models/kling-image-v3.md)) Provider: Kling | Category: Image Kling V3 image model. High-quality images with negative prompts, supports up to 2K resolution. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9 #### [Seedream 4.5](https://www.layer.ai/models/bytedance-seedream-4-5) ([md](https://www.layer.ai/models/bytedance-seedream-4-5.md)) Provider: ByteDance | Category: Image A new-generation image creation model from ByteDance, for both generation and editing. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [GPT Image 1](https://www.layer.ai/models/openai-gpt-image-1) ([md](https://www.layer.ai/models/openai-gpt-image-1.md)) Provider: OpenAI | Category: Image Powerful, versatile OpenAI image model for creative and professional apps. Capabilities: Aspect ratios: 1:1, 2:3, 3:2 #### [Seedream 5.0 Lite](https://www.layer.ai/models/bytedance-seedream-5-lite) ([md](https://www.layer.ai/models/bytedance-seedream-5-lite.md)) Provider: ByteDance | Category: Image Fast, high-quality image generation from ByteDance, optimized for creative advertising. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Luma UNI-1](https://www.layer.ai/models/lumalabs-uni-1) ([md](https://www.layer.ai/models/lumalabs-uni-1.md)) Provider: Luma AI | Category: Image Luma's unified image model for high-fidelity generation and prompt-based editing. Capabilities: Aspect ratios: 1:1, 3:2, 16:9, 2:3, 9:16 #### [FLUX.2 [dev]](https://www.layer.ai/models/bfl-flux-2-dev) ([md](https://www.layer.ai/models/bfl-flux-2-dev.md)) Provider: Black Forest Labs | Category: Image Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [FLUX.2 [dev] Edit](https://www.layer.ai/models/bfl-flux-2-dev-edit) ([md](https://www.layer.ai/models/bfl-flux-2-dev-edit.md)) Provider: Black Forest Labs | Category: Image Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [HiDream O1 Image Dev](https://www.layer.ai/models/hidream-hidream-o1-image-dev) ([md](https://www.layer.ai/models/hidream-hidream-o1-image-dev.md)) Provider: Hidream | Category: Image HiDream's distilled O1 Image Dev model — create, edit, and personalize images up to 2K in one native model. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Kling Image O3](https://www.layer.ai/models/kling-image-o3) ([md](https://www.layer.ai/models/kling-image-o3.md)) Provider: Kling | Category: Image Kling Omni 3 image model. High-quality images with text rendering capabilities up to 4K resolution. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9 #### [HiDream O1 Image 1.0](https://www.layer.ai/models/hidream-hidream-o1-image) ([md](https://www.layer.ai/models/hidream-hidream-o1-image.md)) Provider: Hidream | Category: Image HiDream's full O1 Image model — create, edit, and personalize images up to 2K in one native model. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Imagen 4 Ultra](https://www.layer.ai/models/google-imagen-4-ultra) ([md](https://www.layer.ai/models/google-imagen-4-ultra.md)) Provider: Google | Category: Image Google's highest quality image generation model. Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Recraft V4.1](https://www.layer.ai/models/recraft-v4-1) ([md](https://www.layer.ai/models/recraft-v4-1.md)) Provider: Recraft | Category: Image Professional design model with extended prompt support (10,000 characters) and advanced style customization. Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Gemini 2.5 Flash Image](https://www.layer.ai/models/google-gemini-2-5-flash-image) ([md](https://www.layer.ai/models/google-gemini-2-5-flash-image.md)) Provider: Google | Category: Image Google's image generation and editing model capable of multimodal reasoning. Capabilities: Aspect ratios: 1:1, 5:4, 4:5, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9 #### [Recraft V4.1 Pro](https://www.layer.ai/models/recraft-v4-1-pro) ([md](https://www.layer.ai/models/recraft-v4-1-pro.md)) Provider: Recraft | Category: Image Professional design model with extended prompt support (10,000 characters) and advanced style customization. Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Recraft V4](https://www.layer.ai/models/recraft-v4) ([md](https://www.layer.ai/models/recraft-v4.md)) Provider: Recraft | Category: Image Professional design model with extended prompt support (10,000 characters) and advanced style customization. Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Qwen-Image 2512](https://www.layer.ai/models/qwen-qwen-image-2512) ([md](https://www.layer.ai/models/qwen-qwen-image-2512.md)) Provider: Qwen | Category: Image Latest Qwen text-to-image model with enhanced quality, detail, and prompt adherence. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [FLUX.2 [klein] 9B](https://www.layer.ai/models/bfl-flux-2-klein-9b) ([md](https://www.layer.ai/models/bfl-flux-2-klein-9b.md)) Provider: Black Forest Labs | Category: Image Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [FLUX.2 [klein] 9B Edit](https://www.layer.ai/models/bfl-flux-2-klein-9b-edit) ([md](https://www.layer.ai/models/bfl-flux-2-klein-9b-edit.md)) Provider: Black Forest Labs | Category: Image Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Qwen-Image Edit 2511](https://www.layer.ai/models/qwen-qwen-image-edit-2511) ([md](https://www.layer.ai/models/qwen-qwen-image-edit-2511.md)) Provider: Qwen | Category: Image Latest Qwen image editing model. Supports prompt-guided transformations with enhanced quality. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [FLUX.1 Kontext [max]](https://www.layer.ai/models/bfl-flux-1-kontext-max) ([md](https://www.layer.ai/models/bfl-flux-1-kontext-max.md)) Provider: Black Forest Labs | Category: Image Premium model for max editing performance, superior typography, and visual narrative consistency. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Qwen-Image Edit 2509](https://www.layer.ai/models/qwen-qwen-image-edit-2509) ([md](https://www.layer.ai/models/qwen-qwen-image-edit-2509.md)) Provider: Qwen | Category: Image Advanced image editing model. Enhanced performance for fine-grained manipulation. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Qwen Image 2](https://www.layer.ai/models/qwen-qwen-image-2) ([md](https://www.layer.ai/models/qwen-qwen-image-2.md)) Provider: Qwen | Category: Image Qwen Image 2 standard text-to-image model with strong prompt adherence and diverse style support. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Z-Image Turbo](https://www.layer.ai/models/qwen-z-image-turbo) ([md](https://www.layer.ai/models/qwen-z-image-turbo.md)) Provider: Qwen | Category: Image Ultra-fast 6B parameter image model from Tongyi-MAI, optimized for near real-time generation. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Imagen 3](https://www.layer.ai/models/google-imagen-3) ([md](https://www.layer.ai/models/google-imagen-3.md)) Provider: Google | Category: Image Cutting-edge T2I model. Exceptional detail, photorealism, and accurate text rendering. Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Imagen 4](https://www.layer.ai/models/google-imagen-4) ([md](https://www.layer.ai/models/google-imagen-4.md)) Provider: Google | Category: Image Next-gen image model for professionals. Unparalleled prompt adherence and high-resolution output. Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [FLUX.2 [klein] 4B](https://www.layer.ai/models/bfl-flux-2-klein-4b) ([md](https://www.layer.ai/models/bfl-flux-2-klein-4b.md)) Provider: Black Forest Labs | Category: Image Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [FLUX.2 [klein] 4B Edit](https://www.layer.ai/models/bfl-flux-2-klein-4b-edit) ([md](https://www.layer.ai/models/bfl-flux-2-klein-4b-edit.md)) Provider: Black Forest Labs | Category: Image Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [FLUX.1 Kontext [pro]](https://www.layer.ai/models/bfl-flux-1-kontext-pro) ([md](https://www.layer.ai/models/bfl-flux-1-kontext-pro.md)) Provider: Black Forest Labs | Category: Image Pro-grade multimodal model for fast, iterative editing, style transfer, and consistency. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [FLUX 1.1 [pro] Ultra](https://www.layer.ai/models/bfl-flux-1-1-pro-ultra) ([md](https://www.layer.ai/models/bfl-flux-1-1-pro-ultra.md)) Provider: Black Forest Labs | Category: Image Delivers ultra-high-res (up to 4MP) images with superior photorealism, detail, and speed. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Imagen 4 Fast](https://www.layer.ai/models/google-imagen-4-fast) ([md](https://www.layer.ai/models/google-imagen-4-fast.md)) Provider: Google | Category: Image High-velocity Imagen 4 model, optimized for speed. Essential for quick iteration and interactive creative tools. Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [FLUX 1.1 [pro]](https://www.layer.ai/models/bfl-flux-1-1-pro) ([md](https://www.layer.ai/models/bfl-flux-1-1-pro.md)) Provider: Black Forest Labs | Category: Image Next-gen FLUX model. 6x faster with enhanced prompt adherence and top-tier quality for production. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [FLUX.1 [pro]](https://www.layer.ai/models/bfl-flux-1-pro) ([md](https://www.layer.ai/models/bfl-flux-1-pro.md)) Provider: Black Forest Labs | Category: Image Flagship commercial T2I model offering superior prompt adherence, quality, and stylistic outputs. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Qwen-Image](https://www.layer.ai/models/qwen-qwen-image) ([md](https://www.layer.ai/models/qwen-qwen-image.md)) Provider: Qwen | Category: Image Open-source T2I model. Excels at high-res images from complex text, notable for clear, stylized text. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [FLUX.1 SRPO [dev]](https://www.layer.ai/models/bfl-flux-1-dev-srpo) ([md](https://www.layer.ai/models/bfl-flux-1-dev-srpo.md)) Provider: Black Forest Labs | Category: Image 12B flow transformer fine-tuned with SRPO for exceptional photorealism and polished composition. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Recraft V3](https://www.layer.ai/models/recraft-v3) ([md](https://www.layer.ai/models/recraft-v3.md)) Provider: Recraft | Category: Image Versatile image model for graphic design. Generates legible, stylized text and scalable vector art (SVG). Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Stable Diffusion 3](https://www.layer.ai/models/stabilityai-sd3) ([md](https://www.layer.ai/models/stabilityai-sd3.md)) Provider: Stability AI | Category: Image Latest open-weight MM-DiT model. Major improvements in quality, prompt following, and text rendering. Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [FLUX.1 [dev]](https://www.layer.ai/models/bfl-flux-1-dev) ([md](https://www.layer.ai/models/bfl-flux-1-dev.md)) Provider: Black Forest Labs | Category: Image Powerful, open-weight 12B image model. Excels in image quality, prompt adherence, and commercial use. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 | Outpainting | Tileable textures #### [FLUX.1 Krea [dev]](https://www.layer.ai/models/bfl-flux-1-dev-krea) ([md](https://www.layer.ai/models/bfl-flux-1-dev-krea.md)) Provider: Black Forest Labs | Category: Image Open-weight model co-developed with Krea AI. Excels in photorealism and aesthetics. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 | Outpainting | Tileable textures #### [FLUX.1 Kontext [dev]](https://www.layer.ai/models/bfl-flux-1-kontext-dev) ([md](https://www.layer.ai/models/bfl-flux-1-kontext-dev.md)) Provider: Black Forest Labs | Category: Image Open-weight, multimodal model for context-aware image editing. Excels at iterative edits via text. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [FLUX.1 [schnell]](https://www.layer.ai/models/bfl-flux-1-schnell) ([md](https://www.layer.ai/models/bfl-flux-1-schnell.md)) Provider: Black Forest Labs | Category: Image Ultra-fast, open-source model. Generates high-quality images in 1-4 steps for rapid prototyping. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [BiRefNet v2](https://www.layer.ai/models/nankai-birefnet-v2) ([md](https://www.layer.ai/models/nankai-birefnet-v2.md)) Provider: Nankai | Category: Image High-quality image background removal. #### [SeedVR2 Image Upscaler](https://www.layer.ai/models/bytedance-seedvr-upscale-image) ([md](https://www.layer.ai/models/bytedance-seedvr-upscale-image.md)) Provider: ByteDance | Category: Image ByteDance's SeedVR2 model for high-quality image upscaling. #### [Topaz Enhance](https://www.layer.ai/models/topaz-enhance) ([md](https://www.layer.ai/models/topaz-enhance.md)) Provider: Topaz | Category: Image Enhance image quality with advanced upscaling. #### [Pixelcut Background Removal](https://www.layer.ai/models/pixelcut-background-removal) ([md](https://www.layer.ai/models/pixelcut-background-removal.md)) Provider: Pixelcut | Category: Image High-quality image background removal from Pixelcut. #### [Ideogram Remove Background](https://www.layer.ai/models/ideogram-remove-background) ([md](https://www.layer.ai/models/ideogram-remove-background.md)) Provider: Ideogram | Category: Image Fast, clean background removal from Ideogram. #### [Qwen-Image Edit 2511 Multiple Angles](https://www.layer.ai/models/qwen-qwen-image-edit-2511-multiple-angles) ([md](https://www.layer.ai/models/qwen-qwen-image-edit-2511-multiple-angles.md)) Provider: Qwen | Category: Image Qwen Image Edit 2511 with the Multiple Angles LoRA. Re-renders the input image from a chosen camera angle. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Recraft Vectorize Image](https://www.layer.ai/models/recraft-recraft-vectorize-image) ([md](https://www.layer.ai/models/recraft-recraft-vectorize-image.md)) Provider: Recraft | Category: Image Convert raster images to vector graphics using Recraft. #### [ESRGAN Upscaler](https://www.layer.ai/models/esrgan-upscaler) ([md](https://www.layer.ai/models/esrgan-upscaler.md)) Provider: ESRGAN | Category: Image Very fast upscaling with good quality. #### [Seedream 5.0 Pro Layerize](https://www.layer.ai/models/bytedance-seedream-5-pro-layerize) ([md](https://www.layer.ai/models/bytedance-seedream-5-pro-layerize.md)) Provider: ByteDance | Category: Image Split a finished image into independently editable layers with Seedream 5.0 Pro Layerize. #### [Clarity Creative Upscaler](https://www.layer.ai/models/clarity-creative) ([md](https://www.layer.ai/models/clarity-creative.md)) Provider: Clarity AI | Category: Image Upscale images with high fidelity or creativity. #### [Qwen-Image Layered](https://www.layer.ai/models/qwen-qwen-image-layered) ([md](https://www.layer.ai/models/qwen-qwen-image-layered.md)) Provider: Qwen | Category: Image Split an image into layers using Qwen-Image Layered. #### [Topaz Generative Enhance](https://www.layer.ai/models/topaz-enhance-generative) ([md](https://www.layer.ai/models/topaz-enhance-generative.md)) Provider: Topaz | Category: Image Topaz Generative Enhance for enhanced details. #### [Recraft Crisp Upscale](https://www.layer.ai/models/recraft-upscale-crisp) ([md](https://www.layer.ai/models/recraft-upscale-crisp.md)) Provider: Recraft | Category: Image Boost resolution while refining small details and faces. #### [Image to SVG](https://www.layer.ai/models/fal-image-to-svg) ([md](https://www.layer.ai/models/fal-image-to-svg.md)) Provider: fal | Category: Image Convert raster images to clean, scalable SVG vector graphics with fine-grained control over detail. #### [Recraft Creative Upscale](https://www.layer.ai/models/recraft-upscale-creative) ([md](https://www.layer.ai/models/recraft-upscale-creative.md)) Provider: Recraft | Category: Image Upscale for a sharper, cleaner, higher-resolution result. #### [Grok Imagine Image 2.0](https://www.layer.ai/models/xai-grok-imagine-image-2.0) ([md](https://www.layer.ai/models/xai-grok-imagine-image-2.0.md)) Provider: xAI | Category: Image xAI's Grok Imagine Image 2.0 model for high-quality text-to-image generation and editing. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3 #### [Wan 2.7 Pro](https://www.layer.ai/models/alibaba-wan-2-7-pro) ([md](https://www.layer.ai/models/alibaba-wan-2-7-pro.md)) Provider: Alibaba | Category: Image Alibaba WAN 2.7 Pro image model for high-quality text-to-image generation and multi-image editing. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [FLUX Pro VTO](https://www.layer.ai/models/bfl-flux-pro-vto) ([md](https://www.layer.ai/models/bfl-flux-pro-vto.md)) Provider: Black Forest Labs | Category: Image Virtual try-on from Black Forest Labs: dress a person photo with a garment reference. #### [SAM 3.1 Image](https://www.layer.ai/models/sam-3-1-image) ([md](https://www.layer.ai/models/sam-3-1-image.md)) Provider: Meta | Category: Image Meta's SAM 3.1 for fast multi-object image segmentation. #### [Reve 2.0 Remix](https://www.layer.ai/models/reve-reve-2-remix) ([md](https://www.layer.ai/models/reve-reve-2-remix.md)) Provider: Reve | Category: Image Reve's remix model - blends one to eight reference images into a single new image, guided by a prompt. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Recraft V4.1 Vector](https://www.layer.ai/models/recraft-v4-1-vector) ([md](https://www.layer.ai/models/recraft-v4-1-vector.md)) Provider: Recraft | Category: Image Recraft's V4.1 text-to-vector model. Generates scalable vector art (SVG) directly from a prompt. Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Reve 2.0](https://www.layer.ai/models/reve-reve-2) ([md](https://www.layer.ai/models/reve-reve-2.md)) Provider: Reve | Category: Image Reve's flagship image model with best-in-class prompt adherence and text rendering, plus native editing. Capabilities: Aspect ratios: 1:1, 2:3, 3:4, 9:16, 3:2, 4:3, 16:9 #### [Recraft V4.1 Pro Vector](https://www.layer.ai/models/recraft-v4-1-pro-vector) ([md](https://www.layer.ai/models/recraft-v4-1-pro-vector.md)) Provider: Recraft | Category: Image Recraft's V4.1 Pro text-to-vector model. Generates scalable vector art (SVG) directly from a prompt. Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 #### [Imagen 3 Fast](https://www.layer.ai/models/google-imagen-3-fast) ([md](https://www.layer.ai/models/google-imagen-3-fast.md)) Provider: Google | Category: Image Speed-optimized Imagen 3. Delivers high-quality images fast, ideal for real-time previews. Capabilities: Aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9 ### Video Models #### [Gemini Omni Flash](https://www.layer.ai/models/google-gemini-omni-flash) ([md](https://www.layer.ai/models/google-gemini-omni-flash.md)) Provider: Google | Category: Video Google's fast multimodal video model — 720p clips with synchronized native audio from text or a still image. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s #### [Gemini Omni Flash Reference](https://www.layer.ai/models/google-gemini-omni-flash-reference) ([md](https://www.layer.ai/models/google-gemini-omni-flash-reference.md)) Provider: Google | Category: Video Reference-guided video generation with up to 5 reference images for consistent characters and style. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s #### [MiniMax H3](https://www.layer.ai/models/minimax-h3) ([md](https://www.layer.ai/models/minimax-h3.md)) Provider: MiniMax | Category: Video MiniMax H3 (Hailuo-03) next-gen open-weight video with native stereo audio at 2K and 24 FPS. Capabilities: Aspect ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | Durations: 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [MiniMax H3 Reference](https://www.layer.ai/models/minimax-h3-reference) ([md](https://www.layer.ai/models/minimax-h3-reference.md)) Provider: MiniMax | Category: Video Reference-guided MiniMax H3 video with multimodal image, video, and audio inputs at 2K. Capabilities: Aspect ratios: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | Durations: 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Seedance 2 Reference](https://www.layer.ai/models/bytedance-seedance-v2-reference) ([md](https://www.layer.ai/models/bytedance-seedance-v2-reference.md)) Provider: ByteDance | Category: Video Generate videos guided by reference images, videos, and audio with precise style and character control. Capabilities: Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9 | Durations: 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Seedance 2](https://www.layer.ai/models/bytedance-seedance-v2) ([md](https://www.layer.ai/models/bytedance-seedance-v2.md)) Provider: ByteDance | Category: Video Professional-grade video model with cinematic quality, up to 4K output, and synchronized audio generation. Capabilities: Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9 | Durations: 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Seedance 2.5 Reference](https://www.layer.ai/models/bytedance-seedance-v2-5-reference) ([md](https://www.layer.ai/models/bytedance-seedance-v2-5-reference.md)) Provider: ByteDance | Category: Video Reference-guided Seedance 2.5 video with up to 30 images, 10 videos, and 10 audio files. Capabilities: Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9 | Durations: 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s, 16s, 17s, 18s, 19s, 20s, 21s, 22s, 23s, 24s, 25s, 26s, 27s, 28s, 29s, 30s #### [Seedance 2.5](https://www.layer.ai/models/bytedance-seedance-v2-5) ([md](https://www.layer.ai/models/bytedance-seedance-v2-5.md)) Provider: ByteDance | Category: Video ByteDance's Seedance 2.5 video model with up to 30s clips, 480p/720p output, and native audio. Capabilities: Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9 | Durations: 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s, 16s, 17s, 18s, 19s, 20s, 21s, 22s, 23s, 24s, 25s, 26s, 27s, 28s, 29s, 30s #### [Seedance 2 Fast Reference](https://www.layer.ai/models/bytedance-seedance-v2-fast-reference) ([md](https://www.layer.ai/models/bytedance-seedance-v2-fast-reference.md)) Provider: ByteDance | Category: Video Fast reference-guided video generation with multi-modal inputs and synchronized audio. Capabilities: Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9 | Durations: 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Seedance 2 Fast](https://www.layer.ai/models/bytedance-seedance-v2-fast) ([md](https://www.layer.ai/models/bytedance-seedance-v2-fast.md)) Provider: ByteDance | Category: Video Fast, cost-effective variant of Seedance 2 with 720p output and synchronized audio generation. Capabilities: Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9 | Durations: 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Grok Imagine Video 1.5](https://www.layer.ai/models/xai-grok-imagine-video-1.5) ([md](https://www.layer.ai/models/xai-grok-imagine-video-1.5.md)) Provider: xAI | Category: Video xAI's Grok Imagine 1.5 image-to-video model, animating images into 480p or 720p clips. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4 | Durations: 1s, 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Grok Imagine Video](https://www.layer.ai/models/xai-grok-imagine-video) ([md](https://www.layer.ai/models/xai-grok-imagine-video.md)) Provider: xAI | Category: Video xAI's video generation model capable of creating high-quality 720p video from text and images. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3 | Durations: 1s, 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [PixVerse v6](https://www.layer.ai/models/pixverse-v6) ([md](https://www.layer.ai/models/pixverse-v6.md)) Provider: PixVerse | Category: Video Latest PixVerse video model with improved quality and audio generation, supporting up to 1080p resolution. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 3:2, 2:3, 4:3, 3:4, 21:9 | Durations: 1s, 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Grok Imagine Video Extend](https://www.layer.ai/models/xai-grok-imagine-video-extend) ([md](https://www.layer.ai/models/xai-grok-imagine-video-extend.md)) Provider: xAI | Category: Video Extend an existing video with xAI's Grok Imagine, continuing motion from the source ending. Capabilities: Durations: 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s #### [Happy Horse 1.1](https://www.layer.ai/models/alibaba-happy-horse-1-1) ([md](https://www.layer.ai/models/alibaba-happy-horse-1-1.md)) Provider: Alibaba | Category: Video Alibaba's text-to-video and image-to-video model generating 720p or 1080p clips with native audio and multilingual lip-sync. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Happy Horse 1.0](https://www.layer.ai/models/alibaba-happy-horse) ([md](https://www.layer.ai/models/alibaba-happy-horse.md)) Provider: Alibaba | Category: Video Alibaba's text-to-video and image-to-video model generating 720p or 1080p clips with native audio and multilingual lip-sync. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Happy Horse 1.0 Reference](https://www.layer.ai/models/alibaba-happy-horse-reference) ([md](https://www.layer.ai/models/alibaba-happy-horse-reference.md)) Provider: Alibaba | Category: Video Reference-guided video generation with up to 9 reference images for consistent characters and style. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Kling v2.5 Turbo Pro](https://www.layer.ai/models/kling-v2-5-turbo-pro) ([md](https://www.layer.ai/models/kling-v2-5-turbo-pro.md)) Provider: Kling | Category: Video High-speed video model. Produces rapid, professional-quality 1080p video for fast-paced content. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s, 10s #### [Kling V3 Pro](https://www.layer.ai/models/kling-v3-pro) ([md](https://www.layer.ai/models/kling-v3-pro.md)) Provider: Kling | Category: Video Generate high-quality videos with advanced control. Pro tier with negative prompts. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Kling V3 4K](https://www.layer.ai/models/kling-v3-4k) ([md](https://www.layer.ai/models/kling-v3-4k.md)) Provider: Kling | Category: Video Generate native 4K videos directly from prompts or images. Cinema-grade output in one step. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Vidu Q3 Pro](https://www.layer.ai/models/vidu-q3-pro) ([md](https://www.layer.ai/models/vidu-q3-pro.md)) Provider: Vidu | Category: Video Vidu's Q3 Pro video model with up to 16s clips, 720p/1080p output, and native audio. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4 | Durations: 1s, 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s, 16s #### [PixVerse v5.5](https://www.layer.ai/models/pixverse-v5-5) ([md](https://www.layer.ai/models/pixverse-v5-5.md)) Provider: PixVerse | Category: Video Latest PixVerse video model with enhanced quality and audio generation, supporting up to 1080p resolution. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4 | Durations: 5s, 8s, 10s #### [PixVerse v5.5 Fast](https://www.layer.ai/models/pixverse-v5-5-fast) ([md](https://www.layer.ai/models/pixverse-v5-5-fast.md)) Provider: PixVerse | Category: Video Speed-optimized PixVerse v5.5 variant for rapid video generation at up to 720p resolution. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4 #### [Kling O3 Pro](https://www.layer.ai/models/kling-o3-pro) ([md](https://www.layer.ai/models/kling-o3-pro.md)) Provider: Kling | Category: Video Generate high-quality videos with prompts, images, or reference elements. Pro tier for premium quality. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Kling O3 4K](https://www.layer.ai/models/kling-o3-4k) ([md](https://www.layer.ai/models/kling-o3-4k.md)) Provider: Kling | Category: Video Generate native 4K videos with Kling's Omni 3 model. Cinema-grade output in one step. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Kling O3 4K Reference](https://www.layer.ai/models/kling-o3-4k-reference) ([md](https://www.layer.ai/models/kling-o3-4k-reference.md)) Provider: Kling | Category: Video Generate native 4K videos guided by reference images and elements. Cinema-grade output. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Kling O3 Standard](https://www.layer.ai/models/kling-o3-standard) ([md](https://www.layer.ai/models/kling-o3-standard.md)) Provider: Kling | Category: Video Generate videos with prompts, images, or reference elements. Standard tier for balanced quality and speed. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [Kling V3 Standard](https://www.layer.ai/models/kling-v3-standard) ([md](https://www.layer.ai/models/kling-v3-standard.md)) Provider: Kling | Category: Video Generate videos with prompts and images. Standard tier with negative prompts. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s #### [PixVerse v5](https://www.layer.ai/models/pixverse-v5) ([md](https://www.layer.ai/models/pixverse-v5.md)) Provider: PixVerse | Category: Video Powerful, user-friendly video model producing high-quality, stylized 1080p video with consistent motion. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4 | Durations: 5s, 8s #### [Runway Gen-4.5](https://www.layer.ai/models/runway-gen4-5) ([md](https://www.layer.ai/models/runway-gen4-5.md)) Provider: Runway | Category: Video Runway's high-fidelity image-to-video model with improved prompt adherence and motion quality. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s, 10s #### [Veo 3.1 Fast](https://www.layer.ai/models/google-veo-3-1-fast) ([md](https://www.layer.ai/models/google-veo-3-1-fast.md)) Provider: Google | Category: Video Speed-optimized Veo 3.1 model. Delivers high-quality video rapidly for dynamic workflows. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 4s, 6s, 8s #### [Veo 3.1 Fast Reference to Video](https://www.layer.ai/models/google-veo-3-1-fast-reference) ([md](https://www.layer.ai/models/google-veo-3-1-fast-reference.md)) Provider: Google | Category: Video Speed-optimized reference-guided Veo 3.1: character-consistent video from up to three reference images. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 8s #### [Kling v2.6 Pro](https://www.layer.ai/models/kling-v2-6-pro) ([md](https://www.layer.ai/models/kling-v2-6-pro.md)) Provider: Kling | Category: Video Generate videos from images with native audio generation and fluid motion. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s, 10s #### [Veo 3.1](https://www.layer.ai/models/google-veo-3-1) ([md](https://www.layer.ai/models/google-veo-3-1.md)) Provider: Google | Category: Video Flagship video update: refined control, enhanced visual fidelity, and improved subtle motion details. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 4s, 6s, 8s #### [Veo 3.1 Reference to Video](https://www.layer.ai/models/google-veo-3-1-reference) ([md](https://www.layer.ai/models/google-veo-3-1-reference.md)) Provider: Google | Category: Video Reference-guided Veo 3.1: lock characters and objects across shots using up to three reference images. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 8s #### [Seedance 1.5 Pro](https://www.layer.ai/models/bytedance-seedance-v1-5-pro) ([md](https://www.layer.ai/models/bytedance-seedance-v1-5-pro.md)) Provider: ByteDance | Category: Video Next-generation Seedance video model with improved quality, 1080p output, and integrated audio generation. Capabilities: Aspect ratios: 1:1, 16:9, 9:16, 21:9, 4:3, 3:4 | Durations: 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s #### [Veo 3.1 Lite](https://www.layer.ai/models/google-veo-3-1-lite) ([md](https://www.layer.ai/models/google-veo-3-1-lite.md)) Provider: Google | Category: Video Cost-effective Veo 3.1 variant. Balances quality and affordability for high-volume video creation. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 4s, 6s, 8s #### [Minimax Hailuo-2.3 Pro](https://www.layer.ai/models/minimax-hailuo-2-3-pro) ([md](https://www.layer.ai/models/minimax-hailuo-2-3-pro.md)) Provider: MiniMax | Category: Video Pinnacle of Hailuo T2V series. Cinematic quality with superior coherence, detail, and artistic control. #### [Minimax Hailuo-02 Pro](https://www.layer.ai/models/minimax-hailuo-2-pro) ([md](https://www.layer.ai/models/minimax-hailuo-2-pro.md)) Provider: MiniMax | Category: Video Premium video model engineered for professional-grade 1080p output, superior fidelity, and smoother motion. Capabilities: Aspect ratios: 16:9 | Durations: 5s #### [Minimax Hailuo-2.3 Standard](https://www.layer.ai/models/minimax-hailuo-2-3-standard) ([md](https://www.layer.ai/models/minimax-hailuo-2-3-standard.md)) Provider: MiniMax | Category: Video Latest standard video model. Improved prompt understanding and visual consistency for daily creation. Capabilities: Durations: 6s, 10s #### [Wan 2.5](https://www.layer.ai/models/alibaba-wan-2-5) ([md](https://www.layer.ai/models/alibaba-wan-2-5.md)) Provider: Alibaba | Category: Video Powerful video model. Optimized for top-tier 1080p cinematic quality and consistency. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s, 10s #### [Minimax Hailuo-02 Standard](https://www.layer.ai/models/minimax-hailuo-2-standard) ([md](https://www.layer.ai/models/minimax-hailuo-2-standard.md)) Provider: MiniMax | Category: Video Robust video model producing crisp 768p video. Offers a solid balance of quality and reliable performance. Capabilities: Aspect ratios: 16:9 | Durations: 6s, 10s #### [Seedance Pro](https://www.layer.ai/models/bytedance-seedance-v1-pro) ([md](https://www.layer.ai/models/bytedance-seedance-v1-pro.md)) Provider: ByteDance | Category: Video High-quality video model. Tuned for maximum visual fidelity and broadcast-quality 1080p output. Capabilities: Aspect ratios: 1:1, 16:9, 9:16, 21:9, 4:3, 3:4 | Durations: 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s #### [Veo 3](https://www.layer.ai/models/google-veo-3) ([md](https://www.layer.ai/models/google-veo-3.md)) Provider: Google | Category: Video Next-gen video model with enhanced control over narrative, tone, and shot composition. Includes audio. Capabilities: Aspect ratios: 1:1, 16:9, 9:16 | Durations: 4s, 6s, 8s #### [Wan 2.6](https://www.layer.ai/models/alibaba-wan-2-6) ([md](https://www.layer.ai/models/alibaba-wan-2-6.md)) Provider: Alibaba | Category: Video State-of-the-art multimodal video generation model from Alibaba, with native audio support Capabilities: Aspect ratios: 16:9, 9:16, 4:3, 3:4, 1:1 | Durations: 5s, 10s, 15s #### [Kling v2.1 Master](https://www.layer.ai/models/kling-v21-master) ([md](https://www.layer.ai/models/kling-v21-master.md)) Provider: Kling | Category: Video Premium 1080p video model. Maximum visual fidelity, capturing intricate details and lifelike expressions. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s, 10s #### [Pika 2.5](https://www.layer.ai/models/pika-2.5) ([md](https://www.layer.ai/models/pika-2.5.md)) Provider: Pika | Category: Video Pika's highest-quality image-to-video model, generating 480p, 720p, or 1080p clips from a still frame. Capabilities: Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4 | Durations: 5s, 10s #### [Kling O1](https://www.layer.ai/models/kling-o1) ([md](https://www.layer.ai/models/kling-o1.md)) Provider: Kling | Category: Video Generate new videos from first and last frame images. Capabilities: Aspect ratios: 16:9, 9:16, 4:3, 3:4, 1:1 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s #### [Kling O1 Reference](https://www.layer.ai/models/kling-o1-reference) ([md](https://www.layer.ai/models/kling-o1-reference.md)) Provider: Kling | Category: Video Generate new videos guided by prompts, images or videos. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s #### [Minimax Hailuo-2.3 Fast](https://www.layer.ai/models/minimax-hailuo-2-3-fast) ([md](https://www.layer.ai/models/minimax-hailuo-2-3-fast.md)) Provider: MiniMax | Category: Video High-speed T2V variant. Optimized for rapid creation, iteration, and social media content workflows. Capabilities: Durations: 6s, 10s #### [LTX Video 2.0 Pro](https://www.layer.ai/models/lightricks-ltx-v2-pro) ([md](https://www.layer.ai/models/lightricks-ltx-v2-pro.md)) Provider: Lightricks | Category: Video High-fidelity video model designed for professional-quality results, offering superior detail and nuanced audio. Capabilities: Aspect ratios: 16:9 | Durations: 6s, 8s, 10s #### [Kling v2.1 Pro](https://www.layer.ai/models/kling-v21-pro) ([md](https://www.layer.ai/models/kling-v21-pro.md)) Provider: Kling | Category: Video Refined Kling model delivering professional-grade 1080p video with improved clarity and motion. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s, 10s #### [LTX Video 2.0 Fast](https://www.layer.ai/models/lightricks-ltx-v2-fast) ([md](https://www.layer.ai/models/lightricks-ltx-v2-fast.md)) Provider: Lightricks | Category: Video Versatile video model integrating video and audio creation in one seamless, speed-optimized workflow. Capabilities: Aspect ratios: 16:9 | Durations: 6s, 8s, 10s, 12s, 14s, 16s, 18s, 20s #### [Kling v2.0 Master](https://www.layer.ai/models/kling-v2-master) ([md](https://www.layer.ai/models/kling-v2-master.md)) Provider: Kling | Category: Video Master-grade video model. Enhanced realism and physics simulation for cinematic, high-impact clips. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s, 10s #### [Veo 3 Fast](https://www.layer.ai/models/google-veo-3-fast) ([md](https://www.layer.ai/models/google-veo-3-fast.md)) Provider: Google | Category: Video Speed-optimized Veo 3 variant for rapid video creation and iteration, ideal for short-form content. Capabilities: Aspect ratios: 1:1, 16:9, 9:16 | Durations: 4s, 6s, 8s #### [LTX Video 2.3 Fast](https://www.layer.ai/models/lightricks-ltx-v2-3-fast) ([md](https://www.layer.ai/models/lightricks-ltx-v2-3-fast.md)) Provider: Lightricks | Category: Video Speed-optimized LTX video model with extended duration support up to 20 seconds and portrait mode. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 6s, 8s, 10s, 12s, 14s, 16s, 18s, 20s #### [LTX Video 2.5 Fast](https://www.layer.ai/models/lightricks-ltx-v2-5-fast) ([md](https://www.layer.ai/models/lightricks-ltx-v2-5-fast.md)) Provider: Lightricks | Category: Video Speed-optimized LTX 2.5 audio-video model with 720p–4K output and clips up to 20 seconds. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 6s, 8s, 10s, 12s, 14s, 16s, 18s, 20s #### [LTX Video 2.5 Fast Audio-to-Video](https://www.layer.ai/models/lightricks-ltx-v2-5-fast-audio) ([md](https://www.layer.ai/models/lightricks-ltx-v2-5-fast-audio.md)) Provider: Lightricks | Category: Video Speed-optimized LTX 2.5 mode that generates video timed to a supplied audio clip. Capabilities: Aspect ratios: 16:9, 9:16 #### [LTX Video 2.3](https://www.layer.ai/models/lightricks-ltx-v2-3) ([md](https://www.layer.ai/models/lightricks-ltx-v2-3.md)) Provider: Lightricks | Category: Video Latest LTX video model with sharper details, cleaner audio, and portrait support for professional content creation. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 6s, 8s, 10s #### [LTX Video 2.5 Pro](https://www.layer.ai/models/lightricks-ltx-v2-5-pro) ([md](https://www.layer.ai/models/lightricks-ltx-v2-5-pro.md)) Provider: Lightricks | Category: Video Quality-optimized LTX 2.5 audio-video model for high-fidelity 720p and 1080p output. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 6s, 8s, 10s #### [LTX Video 2.5 Pro Audio-to-Video](https://www.layer.ai/models/lightricks-ltx-v2-5-pro-audio) ([md](https://www.layer.ai/models/lightricks-ltx-v2-5-pro-audio.md)) Provider: Lightricks | Category: Video Quality-optimized LTX 2.5 mode for final visuals synchronized to music, dialogue, or soundtrack. Capabilities: Aspect ratios: 16:9, 9:16 #### [Seedance Lite](https://www.layer.ai/models/bytedance-seedance-v1-lite) ([md](https://www.layer.ai/models/bytedance-seedance-v1-lite.md)) Provider: ByteDance | Category: Video Versatile and efficient video model. Optimized for speed and ideal for short clips and rapid prototypes. Capabilities: Aspect ratios: 1:1, 16:9, 9:16, 21:9, 4:3, 3:4, 9:21 | Durations: 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s #### [Kling v1.6 Pro](https://www.layer.ai/models/kling-v1-6-pro) ([md](https://www.layer.ai/models/kling-v1-6-pro.md)) Provider: Kling | Category: Video Powerful video model for high-fidelity, imaginative content with complex character motion. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s, 10s #### [Hunyuan Video 1.5](https://www.layer.ai/models/tencent-hunyuan-video-1-5) ([md](https://www.layer.ai/models/tencent-hunyuan-video-1-5.md)) Provider: Tencent | Category: Video High quality open-source video model from Tencent Hunyuan. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 5s #### [Veo 2](https://www.layer.ai/models/google-veo-2) ([md](https://www.layer.ai/models/google-veo-2.md)) Provider: Google | Category: Video Legacy video model generating high-definition, long-form cinematic video content. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s, 6s, 7s, 8s #### [Wan 2.2](https://www.layer.ai/models/alibaba-wan-2-2) ([md](https://www.layer.ai/models/alibaba-wan-2-2.md)) Provider: Alibaba | Category: Video Advanced video model. Enhanced visual consistency and detail for high-resolution 1080p content. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s #### [Runway Aleph 2](https://www.layer.ai/models/runway-aleph2) ([md](https://www.layer.ai/models/runway-aleph2.md)) Provider: Runway | Category: Video Runway's next-generation video-to-video model for restyling and transforming existing footage from a prompt. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 #### [Runway Gen-4 Aleph](https://www.layer.ai/models/runway-gen4-aleph) ([md](https://www.layer.ai/models/runway-gen4-aleph.md)) Provider: Runway | Category: Video Runway's video-to-video model for restyling and transforming existing footage from a prompt. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 #### [Runway Gen-4 Turbo](https://www.layer.ai/models/runway-gen4-turbo) ([md](https://www.layer.ai/models/runway-gen4-turbo.md)) Provider: Runway | Category: Video Runway's speed-optimized image-to-video model for rapid, high-quality clip generation. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s, 10s #### [Minimax Video 01](https://www.layer.ai/models/minimax-video-01) ([md](https://www.layer.ai/models/minimax-video-01.md)) Provider: MiniMax | Category: Video Accessible video model. Generates engaging 720p clips from text with good visual consistency. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s #### [Wan 2.1](https://www.layer.ai/models/alibaba-wan-2-1) ([md](https://www.layer.ai/models/alibaba-wan-2-1.md)) Provider: Alibaba | Category: Video State-of-the-art video model. Generates detailed, stylistically diverse clips with fluid motion. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s #### [Hunyuan Video](https://www.layer.ai/models/tencent-hunyuan-video) ([md](https://www.layer.ai/models/tencent-hunyuan-video.md)) Provider: Tencent | Category: Video Impressive open-source video model. Excels at stable, coherent sequences with high visual quality. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 5s #### [Ray 2 Flash](https://www.layer.ai/models/lumalabs-ray-2-flash) ([md](https://www.layer.ai/models/lumalabs-ray-2-flash.md)) Provider: Luma AI | Category: Video High-speed variant of Ray 2, optimized for rapid video creation. Perfect blend of speed and quality. Capabilities: Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, 9:21 | Durations: 5s, 9s #### [Ray 2](https://www.layer.ai/models/lumalabs-ray-2) ([md](https://www.layer.ai/models/lumalabs-ray-2.md)) Provider: Luma AI | Category: Video Large-scale, state-of-the-art video model for stunning realistic and coherent 1080p motion. Capabilities: Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, 9:21 | Durations: 5s, 9s #### [Bria Video Background Removal](https://www.layer.ai/models/bria-video-background-removal) ([md](https://www.layer.ai/models/bria-video-background-removal.md)) Provider: Bria | Category: Video Remove video backgrounds for advanced video editing. #### [Topaz Video Upscaler](https://www.layer.ai/models/topaz-upscale-video) ([md](https://www.layer.ai/models/topaz-upscale-video.md)) Provider: Topaz | Category: Video Professional-grade video upscaling solution utilizing Topaz AI technology for high-quality enhancement. #### [SeedVR2 Video Upscaler](https://www.layer.ai/models/bytedance-seedvr-upscale-video) ([md](https://www.layer.ai/models/bytedance-seedvr-upscale-video.md)) Provider: ByteDance | Category: Video Powerful video upscaling model from ByteDance, optimized for high-quality resolution and fidelity improvement. #### [Video Subtitles](https://www.layer.ai/models/auto-subtitle) ([md](https://www.layer.ai/models/auto-subtitle.md)) Provider: fal | Category: Video #### [FLUX.3](https://www.layer.ai/models/bfl-flux-3) ([md](https://www.layer.ai/models/bfl-flux-3.md)) Provider: Black Forest Labs | Category: Video Frontier video model from Black Forest Labs with native audio, lipsync, and first/last frame control. Capabilities: Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, 9:21 | Durations: 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s, 16s, 17s, 18s, 19s, 20s | Lip sync #### [ESRGAN Video Upscaler](https://www.layer.ai/models/esrgan-video-upscaler) ([md](https://www.layer.ai/models/esrgan-video-upscaler.md)) Provider: ESRGAN | Category: Video ESRGAN model for video upscaling, enhancing resolution and detail. #### [Pixelcut Video Background Removal](https://www.layer.ai/models/pixelcut-video-background-removal) ([md](https://www.layer.ai/models/pixelcut-video-background-removal.md)) Provider: Pixelcut | Category: Video Remove video backgrounds with Pixelcut for clean cutouts. #### [Bria Video Background Removal v3](https://www.layer.ai/models/bria-video-background-removal-v3) ([md](https://www.layer.ai/models/bria-video-background-removal-v3.md)) Provider: Bria | Category: Video Bria's v3 video background removal for advanced video editing. #### [Sora 2 Pro](https://www.layer.ai/models/openai-sora-2-pro) ([md](https://www.layer.ai/models/openai-sora-2-pro.md)) Provider: OpenAI | Category: Video Premium video version offering higher resolution (up to 1024p) and enhanced controls for pro projects. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 4s, 8s, 12s, 16s, 20s #### [FLUX.3 Extend](https://www.layer.ai/models/bfl-flux-3-extend) ([md](https://www.layer.ai/models/bfl-flux-3-extend.md)) Provider: Black Forest Labs | Category: Video Extend an existing video clip with FLUX.3, continuing motion and native audio from the source ending. Capabilities: Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, 9:21 | Durations: 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s, 16s, 17s, 18s, 19s, 20s | Lip sync #### [Hunyuan Video Foley](https://www.layer.ai/models/tencent-hunyuan-video-foley) ([md](https://www.layer.ai/models/tencent-hunyuan-video-foley.md)) Provider: Tencent | Category: Video Specialized model to automatically create and sync sound effects (foley) for video content. #### [Sora 2](https://www.layer.ai/models/openai-sora-2) ([md](https://www.layer.ai/models/openai-sora-2.md)) Provider: OpenAI | Category: Video Next-gen video model generating long, high-fidelity 720p video with unparalleled narrative understanding. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 4s, 8s, 12s, 16s, 20s #### [Bria Video Increase Resolution](https://www.layer.ai/models/bria-video-increase-resolution) ([md](https://www.layer.ai/models/bria-video-increase-resolution.md)) Provider: Bria | Category: Video Bria's advanced AI technology designed to increase the resolution of video content efficiently. #### [Magi Distilled](https://www.layer.ai/models/sandai-magi-distilled) ([md](https://www.layer.ai/models/sandai-magi-distilled.md)) Provider: SandAI | Category: Video Fast, efficient open-source I2V model. Animates still images using an autoregressive approach. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 4s, 5s, 6s, 7s, 8s #### [Wan 3.0](https://www.layer.ai/models/alibaba-wan-3-0) ([md](https://www.layer.ai/models/alibaba-wan-3-0.md)) Provider: Alibaba | Category: Video Alibaba's Wan 3.0 video model with up to 30s clips, 480p/720p/1080p output, and native audio. Capabilities: Aspect ratios: 16:9, 9:16, 4:3, 3:4, 1:1 | Durations: 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s, 16s, 17s, 18s, 19s, 20s, 21s, 22s, 23s, 24s, 25s, 26s, 27s, 28s, 29s, 30s #### [Wan 3.0 Reference](https://www.layer.ai/models/alibaba-wan-3-0-reference) ([md](https://www.layer.ai/models/alibaba-wan-3-0-reference.md)) Provider: Alibaba | Category: Video Reference-guided Wan 3.0 video with up to 10 images, 5 videos, and 5 audio files. Capabilities: Aspect ratios: 16:9, 9:16, 4:3, 3:4, 1:1 | Durations: 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s, 16s, 17s, 18s, 19s, 20s, 21s, 22s, 23s, 24s, 25s, 26s, 27s, 28s, 29s, 30s #### [SAM 3.1 Video](https://www.layer.ai/models/sam-3-1-video) ([md](https://www.layer.ai/models/sam-3-1-video.md)) Provider: Meta | Category: Video Meta's SAM 3.1 for multi-object video segmentation and tracking. #### [Sonilo Video Music 1.1](https://www.layer.ai/models/sonilo-v1-1-video-to-video-music) ([md](https://www.layer.ai/models/sonilo-v1-1-video-to-video-music.md)) Provider: Sonilo | Category: Video Mux frame-synced, licensed music onto any video; optionally keep original speech. #### [Sonilo Video Sound Effects 1.1](https://www.layer.ai/models/sonilo-v1-1-video-to-video-sound-effects) ([md](https://www.layer.ai/models/sonilo-v1-1-video-to-video-sound-effects.md)) Provider: Sonilo | Category: Video Add synchronized, royalty-free sound effects mixed into the finished video. #### [FLUX.3 Keyframes](https://www.layer.ai/models/bfl-flux-3-keyframes) ([md](https://www.layer.ai/models/bfl-flux-3-keyframes.md)) Provider: Black Forest Labs | Category: Video Guide FLUX.3 video generation with up to 10 keyframe images pinned across the clip. Capabilities: Aspect ratios: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, 9:21 | Durations: 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s, 16s, 17s, 18s, 19s, 20s | Lip sync #### [OmniHuman](https://www.layer.ai/models/bytedance-omnihuman) ([md](https://www.layer.ai/models/bytedance-omnihuman.md)) Provider: ByteDance | Category: Video Advanced video model bringing a still image of a person to life using audio, producing expressive videos. Capabilities: Lip sync #### [AI Avatar](https://www.layer.ai/models/multitalk-ai-avatar) ([md](https://www.layer.ai/models/multitalk-ai-avatar.md)) Provider: Multitalk | Category: Video Specialized model for creating realistic, audio-driven talking avatars with accurate lip-sync and expressions. Capabilities: Durations: 2s, 3s, 4s, 5s, 6s, 7s, 8s | Lip sync #### [Framepack](https://www.layer.ai/models/layer-framepack) ([md](https://www.layer.ai/models/layer-framepack.md)) Provider: Layer | Category: Video Highly efficient, open-source I2V model that generates video by predicting the next frame. Capabilities: Aspect ratios: 16:9, 9:16 | Durations: 5s, 10s, 15s, 20s, 25s, 30s, 35s, 40s, 45s, 50s, 55s, 60s #### [Minimax Video 01 Live](https://www.layer.ai/models/minimax-video-01-live) ([md](https://www.layer.ai/models/minimax-video-01-live.md)) Provider: MiniMax | Category: Video Specialized video model. Optimized for a dynamic, live-action feel with naturalistic camera work. Capabilities: Aspect ratios: 16:9, 9:16, 1:1 | Durations: 5s ### 3D Models #### [Meshy V6](https://www.layer.ai/models/meshy-v6) ([md](https://www.layer.ai/models/meshy-v6.md)) Provider: Meshy | Category: 3D Meshy V6. High-fidelity 3D asset creation focusing on PBR, quad mesh, and face rigging. Capabilities: PBR materials #### [Hunyuan 3D v3.1 Pro](https://www.layer.ai/models/tencent-hunyuan3d-v3-1-pro) ([md](https://www.layer.ai/models/tencent-hunyuan3d-v3-1-pro.md)) Provider: Tencent | Category: 3D Latest Hunyuan 3D model with enhanced quality, multi-view input, and PBR material support. Capabilities: PBR materials #### [Tripo v3.0](https://www.layer.ai/models/tripo3d-v3-0) ([md](https://www.layer.ai/models/tripo3d-v3-0.md)) Provider: Tripo | Category: 3D Latest 3D model for production-quality assets with superior textures and clean geometry. Capabilities: PBR materials #### [Meshy V7](https://www.layer.ai/models/meshy-v7) ([md](https://www.layer.ai/models/meshy-v7.md)) Provider: Meshy | Category: 3D Meshy V7. Image and multi-image to 3D with PBR, quad mesh, and optional rigging. Capabilities: PBR materials #### [Meshy V5 Remesh](https://www.layer.ai/models/meshy-v5-remesh) ([md](https://www.layer.ai/models/meshy-v5-remesh.md)) Provider: Meshy | Category: 3D Dedicated Meshy 3D tool for remeshing models to optimize topology and reduce polygon count. #### [Hunyuan 3D 3.0](https://www.layer.ai/models/tencent-hunyuan3d-3-0) ([md](https://www.layer.ai/models/tencent-hunyuan3d-3-0.md)) Provider: Tencent | Category: 3D Professional-grade 3D model optimized for high-quality, detailed assets with advanced features. Capabilities: PBR materials #### [Meshy Rigging](https://www.layer.ai/models/meshy-rigging) ([md](https://www.layer.ai/models/meshy-rigging.md)) Provider: Meshy | Category: 3D Auto-rigs humanoid 3D models and optionally applies a preset animation, returning rigged GLB/FBX. #### [Tripo Remesh](https://www.layer.ai/models/tripo3d-remesh) ([md](https://www.layer.ai/models/tripo3d-remesh.md)) Provider: Tripo | Category: 3D Rebuilds a high-poly 3D mesh as a low-poly model at a target face count, baking the original textures onto the result. #### [Rodin Gen-1.5](https://www.layer.ai/models/hyper3d-rodin) ([md](https://www.layer.ai/models/hyper3d-rodin.md)) Provider: Hyper3D | Category: 3D Advanced 3D generation model creating high-quality, textured T-pose avatars from a single image. #### [Tripo Retexture](https://www.layer.ai/models/tripo3d-retexture) ([md](https://www.layer.ai/models/tripo3d-retexture.md)) Provider: Tripo | Category: 3D Retextures an existing mesh from a text prompt or reference image, keeping geometry intact. Capabilities: PBR materials #### [Tripo Rig](https://www.layer.ai/models/tripo3d-rig) ([md](https://www.layer.ai/models/tripo3d-rig.md)) Provider: Tripo | Category: 3D Auto-rigs a 3D mesh, returning a rigged GLB. Humanoid meshes come back with a Mixamo-named skeleton for direct use in game engines; other body plans use Tripo's own naming, which Mixamo cannot describe. #### [Tripo Segment](https://www.layer.ai/models/tripo3d-segment) ([md](https://www.layer.ai/models/tripo3d-segment.md)) Provider: Tripo | Category: 3D Segments a 3D mesh into parts, returning a part-grouped model for further editing. #### [Tripo P1](https://www.layer.ai/models/tripo3d-p1) ([md](https://www.layer.ai/models/tripo3d-p1.md)) Provider: Tripo | Category: 3D Game-ready Tripo model: a single image to clean low-poly 3D with PBR textures. Capabilities: PBR materials #### [Tripo Animate](https://www.layer.ai/models/tripo3d-animate) ([md](https://www.layer.ai/models/tripo3d-animate.md)) Provider: Tripo | Category: 3D Rigs a 3D mesh and applies a preset animation from the animation library, returning an animated GLB. #### [Meshy V5 Retexture](https://www.layer.ai/models/meshy-v5-retexture) ([md](https://www.layer.ai/models/meshy-v5-retexture.md)) Provider: Meshy | Category: 3D Specialized Meshy 3D tool for quickly retexturing imported meshes using text prompts. #### [Hi3D Parts](https://www.layer.ai/models/hitem3d-hi3d-parts) ([md](https://www.layer.ai/models/hitem3d-hi3d-parts.md)) Provider: Hitem3d | Category: 3D Splits a 3D model into parts for editing, printing, or modular asset workflows. #### [Tripo v3.1](https://www.layer.ai/models/tripo3d-v3-1) ([md](https://www.layer.ai/models/tripo3d-v3-1.md)) Provider: Tripo | Category: 3D High-detail Tripo model for production assets with dense geometry and refined textures. Capabilities: PBR materials #### [Trellis 2](https://www.layer.ai/models/microsoft-trellis-2) ([md](https://www.layer.ai/models/microsoft-trellis-2.md)) Provider: Microsoft | Category: 3D Open-source, high-quality 3D model from Microsoft, leveraging a novel field-free sparse voxel structure. #### [Hunyuan 3D v2 Mini](https://www.layer.ai/models/tencent-hunyuan3d-v2-mini) ([md](https://www.layer.ai/models/tencent-hunyuan3d-v2-mini.md)) Provider: Tencent | Category: 3D Lightweight, efficient 3D version optimized for less powerful hardware. Delivers good quality assets. #### [Rodin Bang](https://www.layer.ai/models/hyper3d-bang) ([md](https://www.layer.ai/models/hyper3d-bang.md)) Provider: Hyper3D | Category: 3D Segments a 3D mesh into parts with Hyper3D Bang! #### [Rodin Gen-2](https://www.layer.ai/models/hyper3d-rodin-gen-2) ([md](https://www.layer.ai/models/hyper3d-rodin-gen-2.md)) Provider: Hyper3D | Category: 3D Hyper3D Rodin Gen-2 delivers sharper geometry and cleaner textures from a single image or prompt. Capabilities: PBR materials #### [Rodin Gen-2.5](https://www.layer.ai/models/hyper3d-rodin-gen-2-5) ([md](https://www.layer.ai/models/hyper3d-rodin-gen-2-5.md)) Provider: Hyper3D | Category: 3D Hyper3D Rodin Gen-2.5 pushes structural detail and surface quality further, with selectable quality. Capabilities: PBR materials #### [Hi3D](https://www.layer.ai/models/hitem3d-hi3d) ([md](https://www.layer.ai/models/hitem3d-hi3d.md)) Provider: Hitem3d | Category: 3D Hi3D image-to-3D with multi-view support, PBR materials, and configurable face counts. Capabilities: PBR materials #### [Hi3D Texture](https://www.layer.ai/models/hitem3d-hi3d-texture) ([md](https://www.layer.ai/models/hitem3d-hi3d-texture.md)) Provider: Hitem3d | Category: 3D Textures an existing Hi3D-compatible geometry mesh from a reference image. #### [Hunyuan 3D v3.1 Fast](https://www.layer.ai/models/tencent-hunyuan3d-v3-1-fast) ([md](https://www.layer.ai/models/tencent-hunyuan3d-v3-1-fast.md)) Provider: Tencent | Category: 3D Fast Hunyuan 3D model for rapid 3D generation with PBR material support. Capabilities: PBR materials #### [Bytedance Seed 3D](https://www.layer.ai/models/bytedance-seed3d) ([md](https://www.layer.ai/models/bytedance-seed3d.md)) Provider: ByteDance | Category: 3D Powerful 3D model focusing on high-quality objects from a single image. Adept at geometry & texture. #### [SAM 3D Align 1.0](https://www.layer.ai/models/meta-sam-3-3d-align) ([md](https://www.layer.ai/models/meta-sam-3-3d-align.md)) Provider: Meta | Category: 3D Meta SAM 3D Align places body and object meshes into a spatially coherent scene from one image. #### [SAM 3D Body 1.0](https://www.layer.ai/models/meta-sam-3-3d-body) ([md](https://www.layer.ai/models/meta-sam-3-3d-body.md)) Provider: Meta | Category: 3D Meta SAM 3D Body reconstructs accurate human body shape and pose from a single image. #### [SAM 3D Objects 1.0](https://www.layer.ai/models/meta-sam-3-3d-objects) ([md](https://www.layer.ai/models/meta-sam-3-3d-objects.md)) Provider: Meta | Category: 3D Meta SAM 3D Objects reconstructs textured 3D geometry from a single real-world image. #### [Anything World Animate](https://www.layer.ai/models/anything-world-anything-world-animate) ([md](https://www.layer.ai/models/anything-world-anything-world-animate.md)) Provider: Anything World | Category: 3D Specialized mesh rigging model that automatically prepares 3D models with skeletons for animation. #### [Tripo Turbo v1.0](https://www.layer.ai/models/tripo3d-turbo-v1-0) ([md](https://www.layer.ai/models/tripo3d-turbo-v1-0.md)) Provider: Tripo | Category: 3D Speed-optimized 3D generation model designed for rapid prototyping and fast generation times. Capabilities: PBR materials #### [Tripo v2.5](https://www.layer.ai/models/tripo3d-v2-5) ([md](https://www.layer.ai/models/tripo3d-v2-5.md)) Provider: Tripo | Category: 3D Incremental 3D update. Refined performance, improved mesh topology, and texture fidelity. Capabilities: PBR materials #### [Hunyuan 3D v2](https://www.layer.ai/models/tencent-hunyuan3d-v2) ([md](https://www.layer.ai/models/tencent-hunyuan3d-v2.md)) Provider: Tencent | Category: 3D Powerful, open-source 3D model producing high-res, textured 3D objects from text or image inputs. #### [Trellis](https://www.layer.ai/models/microsoft-trellis) ([md](https://www.layer.ai/models/microsoft-trellis.md)) Provider: Microsoft | Category: 3D Open-source 3D model creating high-quality objects with realistic materials and geometry from text. ### Audio Models #### [Qwen 3 TTS](https://www.layer.ai/models/qwen-3-tts) ([md](https://www.layer.ai/models/qwen-3-tts.md)) Provider: Qwen 3 Tts | Category: Audio Multilingual TTS with zero-shot voice cloning and prompt-based voice design. #### [Gemini 3.1 Flash TTS](https://www.layer.ai/models/gemini-3.1-flash-tts) ([md](https://www.layer.ai/models/gemini-3.1-flash-tts.md)) Provider: Google | Category: Audio Google's most controllable TTS model with 200+ audio tags for vocal style and delivery. #### [ElevenLabs TTS V3](https://www.layer.ai/models/elevenlabs-tts-v3) ([md](https://www.layer.ai/models/elevenlabs-tts-v3.md)) Provider: ElevenLabs | Category: Audio ElevenLabs' most expressive TTS model with inline audio tags for emotion and delivery. #### [xAI TTS V1](https://www.layer.ai/models/xai-tts-v1) ([md](https://www.layer.ai/models/xai-tts-v1.md)) Provider: xAI | Category: Audio xAI's text-to-speech model with speech tags for expressive delivery in 20+ languages. #### [ElevenLabs Multilingual V2](https://www.layer.ai/models/elevenlabs-multilingual-v2) ([md](https://www.layer.ai/models/elevenlabs-multilingual-v2.md)) Provider: ElevenLabs | Category: Audio Multilingual text-to-speech with natural voice selection and stability controls. #### [ElevenLabs Sound Effects](https://www.layer.ai/models/elevenlabs-sound-effects) ([md](https://www.layer.ai/models/elevenlabs-sound-effects.md)) Provider: ElevenLabs | Category: Audio Generate custom sound effects from text descriptions with duration and prompt control. #### [Seed Audio 1.0](https://www.layer.ai/models/seed-audio-1) ([md](https://www.layer.ai/models/seed-audio-1.md)) Provider: ByteDance | Category: Audio Bytedance Seed Audio TTS with preset voices and zero-shot voice cloning. #### [Sonilo Sound Effects 1.1](https://www.layer.ai/models/sonilo-v1-1-text-to-sound-effects) ([md](https://www.layer.ai/models/sonilo-v1-1-text-to-sound-effects.md)) Provider: Sonilo | Category: Audio High-quality, commercial-use-safe sound effects from text with exact duration control. #### [ElevenLabs Music](https://www.layer.ai/models/elevenlabs-music) ([md](https://www.layer.ai/models/elevenlabs-music.md)) Provider: ElevenLabs | Category: Audio Premium AI music generation from ElevenLabs with composition planning and section control. #### [Lyria 3 Pro](https://www.layer.ai/models/lyria-3-pro) ([md](https://www.layer.ai/models/lyria-3-pro.md)) Provider: Google | Category: Audio Premium tier of Google's Lyria 3 with highest fidelity and compositional complexity. #### [ACE-Step](https://www.layer.ai/models/ace-step) ([md](https://www.layer.ai/models/ace-step.md)) Provider: ACE-Step | Category: Audio Fast open-source music generation with lyrics alignment, remixing, and audio editing. #### [Stable Audio 2.5](https://www.layer.ai/models/stable-audio-25) ([md](https://www.layer.ai/models/stable-audio-25.md)) Provider: Stability AI | Category: Audio Enterprise-grade audio generation with multi-part compositions and audio inpainting. #### [Stable Audio](https://www.layer.ai/models/stable-audio) ([md](https://www.layer.ai/models/stable-audio.md)) Provider: Stability AI | Category: Audio Open-source text-to-audio model for sound effects, field recordings, and instrument samples. #### [Lyria 3](https://www.layer.ai/models/lyria-3) ([md](https://www.layer.ai/models/lyria-3.md)) Provider: Google | Category: Audio Google DeepMind's next-generation music model with enhanced composition and vocal quality. #### [MiniMax Music 3](https://www.layer.ai/models/minimax-music-3) ([md](https://www.layer.ai/models/minimax-music-3.md)) Provider: MiniMax | Category: Audio High-performance MiniMax music model for complete songs up to five minutes with structure tags and seed control. #### [Sonilo Video to Music 1.1](https://www.layer.ai/models/sonilo-v1-1-video-to-music) ([md](https://www.layer.ai/models/sonilo-v1-1-video-to-music.md)) Provider: Sonilo | Category: Audio Frame-synced, licensed music scored from video pacing, mood, and timing. #### [Sonilo Video to Sound Effects 1.1](https://www.layer.ai/models/sonilo-v1-1-video-to-sound-effects) ([md](https://www.layer.ai/models/sonilo-v1-1-video-to-sound-effects.md)) Provider: Sonilo | Category: Audio Synchronized, royalty-free sound effects timed to actions visible in a video. #### [Sonilo Music 1.1](https://www.layer.ai/models/sonilo-v1-1-text-to-music) ([md](https://www.layer.ai/models/sonilo-v1-1-text-to-music.md)) Provider: Sonilo | Category: Audio Licensed, commercial-use-safe music from a text prompt with exact duration control. #### [Minimax Music V2.6](https://www.layer.ai/models/minimax-music-v26) ([md](https://www.layer.ai/models/minimax-music-v26.md)) Provider: MiniMax | Category: Audio Latest MiniMax music model with native audio-visual generation capabilities. #### [Minimax Music V2.5](https://www.layer.ai/models/minimax-music-v25) ([md](https://www.layer.ai/models/minimax-music-v25.md)) Provider: MiniMax | Category: Audio Updated MiniMax music model with improved vocal quality and arrangement control. #### [CassetteAI Sound Effects](https://www.layer.ai/models/cassetteai-sfx) ([md](https://www.layer.ai/models/cassetteai-sfx.md)) Provider: CassetteAI | Category: Audio Real-time sound effects generation in under 1 second, up to 30 seconds long. #### [SAM Audio Separate](https://www.layer.ai/models/sam-audio-separate) ([md](https://www.layer.ai/models/sam-audio-separate.md)) Provider: Meta | Category: Audio Foundation model for audio source separation using text, visual, or temporal prompts. #### [Inworld TTS 1.5 Max](https://www.layer.ai/models/inworld-tts-1.5-max) ([md](https://www.layer.ai/models/inworld-tts-1.5-max.md)) Provider: Inworld | Category: Audio Inworld's premium TTS model optimized for expressive game character voices. #### [ElevenLabs Text to Dialogue](https://www.layer.ai/models/elevenlabs-text-to-dialogue) ([md](https://www.layer.ai/models/elevenlabs-text-to-dialogue.md)) Provider: ElevenLabs | Category: Audio Generate multi-speaker dialogue audio from structured text with per-speaker voice control. #### [ElevenLabs Voice Changer](https://www.layer.ai/models/elevenlabs-voice-changer) ([md](https://www.layer.ai/models/elevenlabs-voice-changer.md)) Provider: ElevenLabs | Category: Audio Transform the voice in an audio recording to a different target voice. #### [CassetteAI Music](https://www.layer.ai/models/cassetteai-music) ([md](https://www.layer.ai/models/cassetteai-music.md)) Provider: CassetteAI | Category: Audio Ultra-fast music generation producing 3-minute tracks in under 10 seconds at 44.1 kHz. #### [Lyria 2](https://www.layer.ai/models/lyria-2) ([md](https://www.layer.ai/models/lyria-2.md)) Provider: Google | Category: Audio Google DeepMind's high-fidelity 48 kHz music model with fine-grained creative control. #### [Minimax Music V2](https://www.layer.ai/models/minimax-music-v2) ([md](https://www.layer.ai/models/minimax-music-v2.md)) Provider: MiniMax | Category: Audio AI music generator producing complete songs with vocals, lyrics, and full instrumentation. #### [DeepFilterNet3](https://www.layer.ai/models/deepfilternet3) ([md](https://www.layer.ai/models/deepfilternet3.md)) Provider: Rikorose | Category: Audio Real-time speech enhancement and noise suppression at 48 kHz full-band audio. #### [Kling Video to Audio](https://www.layer.ai/models/kling-video-to-audio) ([md](https://www.layer.ai/models/kling-video-to-audio.md)) Provider: Kling | Category: Audio Generate synchronized sound effects, dialogue, and ambient audio from video content. #### [ElevenLabs Audio Isolation](https://www.layer.ai/models/elevenlabs-audio-isolation) ([md](https://www.layer.ai/models/elevenlabs-audio-isolation.md)) Provider: ElevenLabs | Category: Audio Isolate clean voice from noisy recordings by removing background noise and music. #### [Mirelo SFX 1.6](https://www.layer.ai/models/mirelo-sfx) ([md](https://www.layer.ai/models/mirelo-sfx.md)) Provider: Mirelo | Category: Audio Sound effects generation and editing with text-to-audio and audio inpainting. #### [Gemini TTS](https://www.layer.ai/models/gemini-tts) ([md](https://www.layer.ai/models/gemini-tts.md)) Provider: Google | Category: Audio Google's text-to-speech model with multi-speaker support and natural expressiveness. ## Tools & Workflows - [All Tools](https://www.layer.ai/tools): 32 workflow templates #### [Outpainting a Scene](https://www.layer.ai/tools/layer--outpainting-a-scene) ([md](https://www.layer.ai/tools/layer--outpainting-a-scene.md)) Expand transparent areas in images to create complete, seamless compositions Labels: Gemini 3, Popular #### [Place Characters Into a Scene](https://www.layer.ai/tools/layer--place-characters-into-a-scene) ([md](https://www.layer.ai/tools/layer--place-characters-into-a-scene.md)) Create style consistent scenes with your characters. Labels: Gemini 3, Popular #### [Animate A Character](https://www.layer.ai/tools/layer--animate-a-character) ([md](https://www.layer.ai/tools/layer--animate-a-character.md)) Create a natural feeling animation from an image. #### [Try Out New Hairstyles](https://www.layer.ai/tools/layer--try-out-new-hairstyles) ([md](https://www.layer.ai/tools/layer--try-out-new-hairstyles.md)) Easily change your character's hairstyles with the click of a button Labels: Gemini 3 #### [Outfit Change](https://www.layer.ai/tools/layer--outfit-change) ([md](https://www.layer.ai/tools/layer--outfit-change.md)) Apply a new outfit while keeping your character consistent. Labels: Popular #### [Item Evolution Chain](https://www.layer.ai/tools/layer--item-evolution-chain) ([md](https://www.layer.ai/tools/layer--item-evolution-chain.md)) Create a 4-stage evolution chain of an object. Labels: Popular #### [Batch Theme Items](https://www.layer.ai/tools/layer--batch-theme-items) ([md](https://www.layer.ai/tools/layer--batch-theme-items.md)) Apply a theme to multiple assets at once. Labels: Popular #### [In-Game Currency Upgrade Chain](https://www.layer.ai/tools/layer--in-game-currency-upgrade-chain) ([md](https://www.layer.ai/tools/layer--in-game-currency-upgrade-chain.md)) Want to create a chain of upgrade for your in-game currency? Try out this workflow. Labels: Workflow #### [Consistent Character Placement](https://www.layer.ai/tools/layer--consistent-character-placement) ([md](https://www.layer.ai/tools/layer--consistent-character-placement.md)) Place a character within any scene while keeping their style consistent #### [Style Transfer to Scene (Beta)](https://www.layer.ai/tools/layer--style-transfer-to-scene-beta) ([md](https://www.layer.ai/tools/layer--style-transfer-to-scene-beta.md)) Apply the style from reference images to an entire scene Labels: Gemini 3 #### [Style Transfer to Item (Beta)](https://www.layer.ai/tools/layer--style-transfer-to-item-beta) ([md](https://www.layer.ai/tools/layer--style-transfer-to-item-beta.md)) Turn one item into the reference image's art style Labels: Gemini 3 #### [Change a Scene's Lighting](https://www.layer.ai/tools/layer--change-a-scenes-lighting) ([md](https://www.layer.ai/tools/layer--change-a-scenes-lighting.md)) Transform the mood and atmosphere of your scenes Labels: Gemini 3 #### [Create Spine Components](https://www.layer.ai/tools/layer--create-spine-components) ([md](https://www.layer.ai/tools/layer--create-spine-components.md)) Turn an image into animatable 2D spine components Labels: Gemini 3 #### [Tileable Texture](https://www.layer.ai/tools/layer--tileable-texture) ([md](https://www.layer.ai/tools/layer--tileable-texture.md)) Create a seamless tileable texture with just a prompt. #### [Batch Remove Background](https://www.layer.ai/tools/layer--batch-remove-background) ([md](https://www.layer.ai/tools/layer--batch-remove-background.md)) Remove the background from multiple images at once. #### [Character Level Up](https://www.layer.ai/tools/layer--character-level-up) ([md](https://www.layer.ai/tools/layer--character-level-up.md)) Generate a level-up video for animation inspo. #### [Idle Animation Loop](https://www.layer.ai/tools/layer--idle-animation-loop) ([md](https://www.layer.ai/tools/layer--idle-animation-loop.md)) Create a looping idle animation of a character’s subtle motion. #### [Image To Sprite](https://www.layer.ai/tools/layer--image-to-sprite) ([md](https://www.layer.ai/tools/layer--image-to-sprite.md)) Turn the subject of an image into a retro 2D sprite. #### [Generate a Sprite Sheet](https://www.layer.ai/tools/layer--generate-a-sprite-sheet) ([md](https://www.layer.ai/tools/layer--generate-a-sprite-sheet.md)) Turn an image into a series of sprites. #### [Reskin UI](https://www.layer.ai/tools/layer--reskin-ui) ([md](https://www.layer.ai/tools/layer--reskin-ui.md)) Reskin UI elements while retaining pixel perfect proportions. #### [Retexture](https://www.layer.ai/tools/layer--retexture) ([md](https://www.layer.ai/tools/layer--retexture.md)) Edit or regenerate a specific region of a texture map. #### [Reskin A Map](https://www.layer.ai/tools/layer--reskin-a-map) ([md](https://www.layer.ai/tools/layer--reskin-a-map.md)) Reskin a map without changing it's structure. #### [Batch Upscale](https://www.layer.ai/tools/layer--batch-upscale) ([md](https://www.layer.ai/tools/layer--batch-upscale.md)) Increase the resolution (upscale) several images at once. #### [Apply Color Palette To Image](https://www.layer.ai/tools/layer--apply-color-palette-to-image) ([md](https://www.layer.ai/tools/layer--apply-color-palette-to-image.md)) Recolor your image with a color palette reference. #### [Character Swap](https://www.layer.ai/tools/layer--character-swap) ([md](https://www.layer.ai/tools/layer--character-swap.md)) Replace a character with a new one in the same scene. #### [Make a Tiktok video](https://www.layer.ai/tools/layer--make-a-tiktok-video) ([md](https://www.layer.ai/tools/layer--make-a-tiktok-video.md)) Create a 16:9 video perfect for TikTok. #### [Character Rear View](https://www.layer.ai/tools/layer--character-rear-view) ([md](https://www.layer.ai/tools/layer--character-rear-view.md)) Render different angles and perspectives of your character. #### [Add Audio To A Video](https://www.layer.ai/tools/layer--add-audio-to-a-video) ([md](https://www.layer.ai/tools/layer--add-audio-to-a-video.md)) Add sound effects that bring your video to life. #### [Remove From Image](https://www.layer.ai/tools/layer--remove-from-image) ([md](https://www.layer.ai/tools/layer--remove-from-image.md)) Remove unwanted details without changing the rest. #### [Add Reference To Image](https://www.layer.ai/tools/layer--add-reference-to-image) ([md](https://www.layer.ai/tools/layer--add-reference-to-image.md)) Add objects to your scene with a reference image. #### [Sketch to Art Style](https://www.layer.ai/tools/layer--sketch-to-art-style) ([md](https://www.layer.ai/tools/layer--sketch-to-art-style.md)) Turn a pencil sketch into a fully rendered image in your style. Labels: Gemini 3 #### [Recolor Elements](https://www.layer.ai/tools/layer--recolor-elements) ([md](https://www.layer.ai/tools/layer--recolor-elements.md)) Make global color changes or change the color of specific areas. ## Pricing ### Image Generation - GPT Image 2: 6 / megapixel per megapixel - Reve 2.1: 5 / generation per generation - Reve 2.1 Remix: 5 / generation per generation - Gemini 3.1 Flash Image: 2 / generation per generation - Gemini 3.1 Flash Image 2K: 3 / generation per generation - Gemini 3.1 Flash Image 4K: 4 / generation per generation - Gemini 3.1 Flash Image High Effort: 4 / generation per generation - Gemini 3.1 Flash Image 2K, High Effort: 5 / generation per generation - Gemini 3.1 Flash Image 4K, High Effort: 6 / generation per generation - GPT Image 1.5: 3.55 / megapixel per megapixel - MAI Image 2.5: 1 / generation per generation - Gemini 3 Pro Image: 4 / generation per generation - Gemini 3 Pro Image 4K: 8 / generation per generation - Gemini 3.1 Flash-Lite Image: 1 / generation per generation - Gemini 3.1 Flash-Lite Image High Effort: 2 / generation per generation - Grok Imagine Image: 0.8 / generation per generation - Qwen Image 2 Pro: 3 / generation per generation - FLUX.2 [max]: 2.8 / megapixel per megapixel - Krea 2 Turbo: 0.213 / megapixel per megapixel - Krea 2 Turbo with LoRA: 0.267 / megapixel per megapixel - Luma UNI-1 Max: 2.6 / generation per generation - Seedream 4.0: 1.2 / generation per generation - Krea 2 Large: 1.3 / generation per generation - FLUX.2 [flex]: 2.4 / megapixel per megapixel - Ideogram V4: 0.3 / megapixel per megapixel - FLUX.2 [pro]: 1.2 / megapixel per megapixel - Kling Image V3: 1.12 / generation per generation - Seedream 4.5: 1.6 / generation per generation - GPT Image 1: 4 / megapixel per megapixel - Seedream 5.0 Lite: 1.4 / generation per generation - Luma UNI-1: 1.1 / generation per generation - FLUX.2 [dev]: 0.36 / megapixel per megapixel - FLUX.2 [dev] Edit: 0.48 / megapixel per megapixel - HiDream O1 Image Dev: 0.1 / megapixel per megapixel - Kling Image O3: 1.12 / generation per generation - Kling Image O3 4K: 2.24 / generation per generation - HiDream O1 Image 1.0: 0.2 / megapixel per megapixel - Imagen 4 Ultra: 2.4 / generation per generation - Recraft V4.1: 2 / generation per generation - Gemini 2.5 Flash Image: 1.5 / generation per generation - Recraft V4.1 Pro: 7 / generation per generation - Recraft V4: 1.6 / generation per generation - Qwen-Image 2512: 0.9 / megapixel per megapixel - FLUX.2 [klein] 9B: 1.2 / megapixel per megapixel - FLUX.2 [klein] 9B Edit: 1.4 / megapixel per megapixel - Qwen-Image Edit 2511: 0.9 / megapixel per megapixel - FLUX.1 Kontext [max]: 3.2 / generation per generation - Qwen-Image Edit 2509: 0.9 / megapixel per megapixel - Qwen Image 2: 1.4 / generation per generation - Z-Image Turbo: 0.3 / megapixel per megapixel - Z-Image Turbo with LoRA: 0.4 / megapixel per megapixel - Imagen 3: 2 / megapixel per megapixel - Imagen 4: 1.6 / generation per generation - FLUX.2 [klein] 4B: 0.8 / megapixel per megapixel - FLUX.2 [klein] 4B Edit: 0.9 / megapixel per megapixel - FLUX.1 Kontext [pro]: 1.6 / generation per generation - FLUX 1.1 [pro] Ultra: 2.4 / generation per generation - Imagen 4 Fast: 0.8 / generation per generation - FLUX 1.1 [pro]: 1.6 / generation per generation - FLUX.1 [pro]: 2 / megapixel per megapixel - Qwen-Image: 0.6 / megapixel per megapixel - Qwen-Image Edit: 0.9 / megapixel per megapixel - FLUX.1 SRPO [dev]: 0.75 / megapixel per megapixel - Recraft V3: 1.6 / generation per generation - Stable Diffusion 3: 1.2 / megapixel per megapixel - FLUX.1 [dev]: 0.6 / megapixel per megapixel - FLUX.1 [dev] with LoRA: 0.85 / megapixel per megapixel - FLUX.1 [dev] with NAG: 0.85 / megapixel per megapixel - FLUX.1 [dev] Style Transfer: 1 / megapixel per megapixel - FLUX.1 [dev] ControlNet: 1 / megapixel per megapixel - FLUX.1 [dev] with LoRA, ControlNet: 1.25 / megapixel per megapixel - FLUX.1 Krea [dev]: 0.75 / megapixel per megapixel - FLUX.1 Kontext [dev]: 1.6 / generation per generation - FLUX.1 [schnell]: 0.2 / megapixel per megapixel - BiRefNet v2: 0.1 / megapixel per megapixel - SeedVR2 Image Upscaler: 0.1 / megapixel per megapixel - Topaz Enhance: 1 / megapixel per megapixel - Pixelcut Background Removal: 0.5 / generation per generation - Ideogram Remove Background: 0.3 / generation per generation - Qwen-Image Edit 2511 Multiple Angles: 1.5 / megapixel per megapixel - Recraft Vectorize Image: 3 / generation per generation - ESRGAN Upscaler: 0.1 / megapixel per megapixel - Seedream 5.0 Pro Layerize: 2.9 / generation per generation - Clarity Creative Upscaler: 0.5 / megapixel per megapixel - Qwen-Image Layered: 1.8 / generation per generation - Topaz Generative Enhance: 1 / megapixel per megapixel - Recraft Crisp Upscale: 0.5 / generation per generation - Image to SVG: 1 / generation per generation - Recraft Creative Upscale: 8 / generation per generation - Grok Imagine Image 2.0: 0.9 / generation per generation - Grok Imagine Image 2.0 High Quality: 1.3 / generation per generation - Grok Imagine Image 2.0 2K: 1.3 / generation per generation - Grok Imagine Image 2.0 High Quality, 2K: 1.7 / generation per generation - Wan 2.7 Pro: 1.5 / generation per generation - FLUX Pro VTO: 1 / generation per generation - SAM 3.1 Image: 0.2 / generation per generation - Reve 2.0 Remix: 1.3 / generation per generation - Recraft V4.1 Vector: 3 / generation per generation - Reve 2.0: 1.3 / generation per generation - Recraft V4.1 Pro Vector: 10 / generation per generation - Imagen 3 Fast: 1 / megapixel per megapixel - Stable Diffusion XL: 0.2 / megapixel per megapixel - Stable Diffusion XL ControlNet: 0.6 / megapixel per megapixel - Stable Diffusion XL Turbo: 0.2 / megapixel per megapixel - Fooocus: 0.3 / megapixel per megapixel - Seedream 5.0 Pro: 2.4 / generation per generation - StarVector: 3 / generation per generation - FFMPEG Extract Frame: 0 / second per second - Image Preprocessors: 0.5 / megapixel per megapixel - Comfy Image: 0.1 / compute second per compute_second ### Video Generation - Gemini Omni Flash: 2.9 / megapixel second per megapixel_per_second - Gemini Omni Flash Edit: 3.1 / megapixel second per megapixel_per_second - Gemini Omni Flash Reference: 3.1 / megapixel second per megapixel_per_second - MiniMax H3: 8.67 / second per second - MiniMax H3 Reference: 8.67 / second per second - Seedance 2 Reference: 7 / megapixel second per megapixel_per_second - Seedance 2 Reference with Audio: 8.2 / megapixel second per megapixel_per_second - Seedance 2: 7 / megapixel second per megapixel_per_second - Seedance 2 with Audio: 8.2 / megapixel second per megapixel_per_second - Seedance 2.5 Reference: 9.07 / megapixel second per megapixel_per_second - Seedance 2.5 Reference with Audio: 10.27 / megapixel second per megapixel_per_second - Seedance 2.5: 9.07 / megapixel second per megapixel_per_second - Seedance 2.5 with Audio: 10.27 / megapixel second per megapixel_per_second - Seedance 2 Fast Reference: 5.6 / megapixel second per megapixel_per_second - Seedance 2 Fast: 5.6 / megapixel second per megapixel_per_second - Grok Imagine Video 1.5: 5.2 / megapixel second per megapixel_per_second - Grok Imagine Video: 3.2 / megapixel second per megapixel_per_second - PixVerse v6: 1 / megapixel second per megapixel_per_second - PixVerse v6 with Audio: 1.3 / megapixel second per megapixel_per_second - Grok Imagine Video Extend: 3.2 / megapixel second per megapixel_per_second - Happy Horse 1.1: 5.31 / megapixel second per megapixel_per_second - Happy Horse 1.0: 3 / second per second - Happy Horse 1.0 1080p: 6.2 / second per second - Happy Horse 1.0 Edit: 6 / second per second - Happy Horse 1.0 Edit 1080p: 12.4 / second per second - Happy Horse 1.0 Reference: 3 / second per second - Happy Horse 1.0 Reference 1080p: 6.2 / second per second - Kling v2.5 Turbo Pro: 1.6 / second per second - Kling V3 Pro: 5.6 / second per second - Kling V3 Pro with Audio: 7 / second per second - Kling V3 4K: 9.1 / second per second - Vidu Q3 Pro: 3.3 / second per second - PixVerse v5.5: 2 / megapixel second per megapixel_per_second - PixVerse v5.5 with Audio: 2.12 / megapixel second per megapixel_per_second - PixVerse v5.5 Fast: 1.6 / megapixel second per megapixel_per_second - Kling O3 Pro: 5.6 / second per second - Kling O3 Pro with Audio: 7 / second per second - Kling O3 4K: 9.1 / second per second - Kling O3 4K Reference: 9.1 / second per second - Kling O3 Standard: 4.2 / second per second - Kling O3 Standard with Audio: 5.6 / second per second - Kling V3 Standard: 4.2 / second per second - Kling V3 Standard with Audio: 5.6 / second per second - PixVerse v5: 1.8 / megapixel second per megapixel_per_second - Runway Gen-4.5: 2.8 / second per second - Veo 3.1 Fast: 2.5 / second per second - Veo 3.1 Fast with Audio: 3.75 / second per second - Veo 3.1 Fast 4K: 7.5 / second per second - Veo 3.1 Fast with Audio, 4K: 8.75 / second per second - Veo 3.1 Fast Reference to Video: 2.5 / second per second - Veo 3.1 Fast Reference to Video with Audio: 3.75 / second per second - Veo 3.1 Fast Reference to Video 4K: 7.5 / second per second - Veo 3.1 Fast Reference to Video with Audio, 4K: 8.75 / second per second - Kling v2.6 Pro: 1.65 / second per second - Kling v2.6 Pro with Audio: 3.3 / second per second - Veo 3.1: 4.5 / second per second - Veo 3.1 with Audio: 10 / second per second - Veo 3.1 4K: 9 / second per second - Veo 3.1 with Audio, 4K: 14.5 / second per second - Veo 3.1 Reference to Video: 4.5 / second per second - Veo 3.1 Reference to Video with Audio: 10 / second per second - Veo 3.1 Reference to Video 4K: 9 / second per second - Veo 3.1 Reference to Video with Audio, 4K: 14.5 / second per second - Seedance 1.5 Pro: 1.2 / megapixel second per megapixel_per_second - Seedance 1.5 Pro with Audio: 2.4 / megapixel second per megapixel_per_second - Veo 3.1 Lite: 2 / second per second - Veo 3.1 Lite with Audio: 3 / second per second - Minimax Hailuo-2.3 Pro: 11 / generation per generation - Minimax Hailuo-02 Pro: 1.8 / second per second - Minimax Hailuo-2.3 Standard: 1.2 / second per second - Wan 2.5: 4.5 / megapixel second per megapixel_per_second - Minimax Hailuo-02 Standard: 1 / second per second - Seedance Pro: 2.5 / megapixel second per megapixel_per_second - Veo 3: 6 / second per second - Veo 3 with Audio: 12 / second per second - Wan 2.6: 4.5 / megapixel second per megapixel_per_second - Kling v2.1 Master: 4.5 / second per second - Pika 2.5: 1.7 / megapixel second per megapixel_per_second - Kling O1: 2.8 / second per second - Kling O1 Edit: 4.2 / second per second - Kling O1 Reference: 2.8 / second per second - Kling O1 Reference Video Reference: 4.2 / second per second - Minimax Hailuo-2.3 Fast: 0.8 / second per second - LTX Video 2.0 Pro: 0.9 / megapixel second per megapixel_per_second - Kling v2.1 Pro: 2 / second per second - LTX Video 2.0 Fast: 0.6 / megapixel second per megapixel_per_second - Kling v2.0 Master: 6 / second per second - Veo 3 Fast: 3.2 / second per second - Veo 3 Fast with Audio: 4.8 / second per second - LTX Video 2.3 Fast: 0.6 / megapixel second per megapixel_per_second - LTX Video 2.5 Fast: 2 / second per second - LTX Video 2.5 Fast 1080p: 2.8 / second per second - LTX Video 2.5 Fast 2K: 4.1 / second per second - LTX Video 2.5 Fast 4K: 6.5 / second per second - LTX Video 2.5 Fast Audio-to-Video: 2.8 / second per second - LTX Video 2.3: 0.9 / megapixel second per megapixel_per_second - LTX Video 2.5 Pro: 2.6 / second per second - LTX Video 2.5 Pro 1080p: 3.7 / second per second - LTX Video 2.5 Pro Audio-to-Video: 3.7 / second per second - Seedance Lite: 1.6 / megapixel second per megapixel_per_second - Kling v1.6 Pro: 3 / second per second - Hunyuan Video 1.5: 3 / second per second - Veo 2: 8 / second per second - Wan 2.2: 4.55 / megapixel second per megapixel_per_second - Runway Aleph 2: 6.5 / second per second - Runway Gen-4 Aleph: 3.5 / second per second - Runway Gen-4 Turbo: 1.2 / second per second - Minimax Video 01: 10 / generation per generation - Wan 2.1: 4 / megapixel second per megapixel_per_second - Hunyuan Video: 10 / generation per generation - Ray 2 Flash: 1 / second per second - Ray 2 Flash Reframe: 1.5 / second per second - Ray 2 Flash Modify: 3 / second per second - Ray 2: 2.5 / second per second - Ray 2 Reframe: 5 / second per second - Ray 2 Modify: 7.5 / second per second - Bria Video Background Removal: 3.5 / second per second - Topaz Video Upscaler: 3 / second per second - SeedVR2 Video Upscaler: 10 / megapixel second per megapixel_per_second - Video Subtitles: 0.02 / second per second - FLUX.3: 1.7 / second per second - ESRGAN Video Upscaler: 0.8 / megapixel second per megapixel_per_second - Pixelcut Video Background Removal: 0.7 / second per second - Bria Video Background Removal v3: 0.2 / second per second - Sora 2 Pro: 7.5 / megapixel second per megapixel_per_second - FLUX.3 Extend: 4.1 / second per second - Hunyuan Video Foley: 0.3 / second per second - Sora 2: 2.5 / megapixel second per megapixel_per_second - Bria Video Increase Resolution: 3.5 / second per second - Magi Distilled: 8 / megapixel second per megapixel_per_second - Wan 3.0: 4.5 / megapixel second per megapixel_per_second - Wan 3.0 Reference: 4.5 / megapixel second per megapixel_per_second - SAM 3.1 Video: 0.3 / second per second - Sonilo Video Music 1.1: 0.25 / second per second - Sonilo Video Sound Effects 1.1: 0.25 / second per second - FLUX.3 Keyframes: 1.7 / second per second - OmniHuman: 5.6 / megapixel second per megapixel_per_second - AI Avatar: 18 / megapixel second per megapixel_per_second - Framepack: 1.3 / megapixel second per megapixel_per_second - Minimax Video 01 Live: 10 / generation per generation - FFMPEG Merge Videos: 0 / generation per generation - Video Timeline Render: 0.25 / megapixel second per megapixel_per_second ### 3D Generation - Meshy V6: 26.7 / generation per generation - Hunyuan 3D v3.1 Pro: 21 / generation per generation - Tripo v3.0: 6.7 / generation per generation - Meshy V7: 26.7 / generation per generation - Meshy V5 Remesh: 6.7 / generation per generation - Hunyuan 3D 3.0: 21 / generation per generation - Meshy Rigging: 10.7 / generation per generation - Tripo Remesh: 10 / generation per generation - Rodin Gen-1.5: 30 / generation per generation - Tripo Retexture: 3.3 / generation per generation - Tripo Rig: 8.3 / generation per generation - Tripo Segment: 13.3 / generation per generation - Tripo P1: 13.3 / generation per generation - Tripo Animate: 8.3 / generation per generation - Meshy V5 Retexture: 10 / generation per generation - Hi3D Parts: 8.7 / generation per generation - Tripo v3.1: 6.7 / generation per generation - Trellis 2: 12 / generation per generation - Hunyuan 3D v2 Mini: 4 / generation per generation - Rodin Bang: 30 / generation per generation - Rodin Gen-2: 30 / generation per generation - Rodin Gen-2.5: 30 / generation per generation - Hi3D: 10.8 / generation per generation - Hi3D Texture: 4.3 / generation per generation - Hunyuan 3D v3.1 Fast: 9 / generation per generation - Bytedance Seed 3D: 13.2 / generation per generation - SAM 3D Align 1.0: 0.4 / generation per generation - SAM 3D Body 1.0: 0.4 / generation per generation - SAM 3D Objects 1.0: 0.4 / generation per generation - Anything World Animate: 80 / generation per generation - Tripo Turbo v1.0: 6.7 / generation per generation - Tripo v2.5: 6.7 / generation per generation - Hunyuan 3D v2: 15 / generation per generation - Trellis: 0.8 / generation per generation - Tripo Retarget: 3.3 / generation per generation - Anything World Rig: 80 / generation per generation ### Audio Generation - Qwen 3 TTS: 0.03 / character count per character_count - Gemini 3.1 Flash TTS: 0.03 / character count per character_count - ElevenLabs TTS V3: 0.03 / character count per character_count - xAI TTS V1: 0.03 / character count per character_count - ElevenLabs Multilingual V2: 0.03 / character count per character_count - ElevenLabs Sound Effects: 0.3 / second per second - Seed Audio 1.0: 0.07 / second per second - Sonilo Sound Effects 1.1: 0.05 / second per second - ElevenLabs Music: 0.8 / second per second - Lyria 3 Pro: 2.4 / generation per generation - ACE-Step: 0.02 / second per second - Stable Audio 2.5: 5.6 / generation per generation - Stable Audio: 0.01 / character count per character_count - Lyria 3: 1.2 / generation per generation - MiniMax Music 3: 0.04 / second per second - Sonilo Video to Music 1.1: 0.25 / second per second - Sonilo Video to Sound Effects 1.1: 0.25 / second per second - Sonilo Music 1.1: 0.07 / second per second - Minimax Music V2.6: 4.2 / generation per generation - Minimax Music V2.5: 4.2 / generation per generation - CassetteAI Sound Effects: 0.5 / generation per generation - SAM Audio Separate: 1.4 / generation per generation - Inworld TTS 1.5 Max: 0.03 / character count per character_count - ElevenLabs Text to Dialogue: 0.03 / character count per character_count - ElevenLabs Voice Changer: 0.3 / second per second - CassetteAI Music: 0.02 / second per second - Lyria 2: 2.8 / generation per generation - Minimax Music V2: 0.9 / generation per generation - DeepFilterNet3: 0.1 / second per second - Kling Video to Audio: 1 / generation per generation - ElevenLabs Audio Isolation: 0.1 / second per second - Mirelo SFX 1.6: 0.3 / second per second - Gemini TTS: 0.03 / character count per character_count ### Custom Style Training - FLUX.1 [dev]: 0.04 / training step per training_step - FLUX.1 [dev] Kohya: 0.06 / training step per training_step - FLUX.1 Kontext [dev]: 0.05 / training step per training_step - FLUX.2 [dev]: 0.05 / training step per training_step - FLUX.2 [dev] Edit: 0.05 / training step per training_step - FLUX.1 Krea [dev]: 0.04 / training step per training_step - FLUX.2 [klein] 4B: 0.11 / training step per training_step - FLUX.2 [klein] 4B Edit: 0.1 / training step per training_step - FLUX.2 [klein] 9B: 0.18 / training step per training_step - FLUX.2 [klein] 9B Edit: 0.17 / training step per training_step - Qwen-Image: 0.04 / training step per training_step - Qwen-Image Edit 2511: 0.08 / training step per training_step - Qwen-Image 2512: 0.02 / training step per training_step - Z-Image Turbo: 0.02 / training step per training_step - Krea 2 Turbo: 0.1 / training step per training_step - ElevenLabs TTS V3: 16.7 / generation per generation - Qwen 3 TTS: 1 / generation per generation - Seed Audio 1.0: 54.2 / generation per generation - Stable Diffusion XL: 0.04 / training step per training_step ## Use Cases - [All Use Cases](https://www.layer.ai/use-cases) ([md](https://www.layer.ai/use-cases.md)): AI-powered creative workflows for mobile game UA - [AI Ad Variations for Mobile Game UA](https://www.layer.ai/use-cases/ad-variations) ([md](https://www.layer.ai/use-cases/ad-variations.md)): Generate mobile game UA ad variations at scale. Create dozens of creative tests in minutes for Facebook, Google, TikTok, and Unity Ads. Find winning creatives faster. - [AI App Store Screenshots for Mobile Games](https://www.layer.ai/use-cases/app-store-screenshots) ([md](https://www.layer.ai/use-cases/app-store-screenshots.md)): Generate and A/B test app store screenshots for mobile games. Create scroll-stopping visuals that convert browsers into installers. Optimize ASO with AI. - [AI Brand Asset Creation with Layer](https://www.layer.ai/use-cases/brand-assets) ([md](https://www.layer.ai/use-cases/brand-assets.md)): Create brand assets 10x faster with AI. Logos, icons, illustrations, marketing visuals, and brand kits. Custom style training, SOC 2, no seat fees. - [AI Character Design with Layer](https://www.layer.ai/use-cases/character-design) ([md](https://www.layer.ai/use-cases/character-design.md)): Design game characters 10x faster with AI. Generate concepts, expressions, poses, and full character sheets. 300+ models, PSD export, style training. - [AI Concept Art and Rapid Visual Ideation](https://www.layer.ai/use-cases/concept-art) ([md](https://www.layer.ai/use-cases/concept-art.md)): Generate concept art 10x faster with AI. Rapid ideation for games, film, and entertainment. 300+ models, custom style training, PSD export. Try free. - [AI Environment Art with Layer](https://www.layer.ai/use-cases/environment-art) ([md](https://www.layer.ai/use-cases/environment-art.md)): Generate environment art and world concepts 10x faster with AI. Landscapes, interiors, props, and biomes for games and film. 300+ models, PSD export. - [AI Influencer Creative Kits for Mobile Games](https://www.layer.ai/use-cases/influencer-creative-kits) ([md](https://www.layer.ai/use-cases/influencer-creative-kits.md)): Generate visual asset kits for mobile game influencer and UGC campaigns. Create character art, gameplay graphics, and branded templates at scale. - [AI-Powered IPM Creative Testing for Mobile Games](https://www.layer.ai/use-cases/ipm-creative-testing) ([md](https://www.layer.ai/use-cases/ipm-creative-testing.md)): Maximize installs per mille with AI-powered creative testing at scale. Generate, test, and iterate mobile game ad creatives systematically to drive higher IPM. - [AI Localized UA Creatives for Mobile Games](https://www.layer.ai/use-cases/localized-ua-creatives) ([md](https://www.layer.ai/use-cases/localized-ua-creatives.md)): Generate localized UA creative for mobile game global launches. Produce culturally adapted ad variations, app store screenshots, and campaign assets for every market. - [AI UA Campaign Creatives for Mobile Games](https://www.layer.ai/use-cases/marketing-creatives) ([md](https://www.layer.ai/use-cases/marketing-creatives.md)): Create mobile game UA campaign visuals 10x faster. Generate ad creatives, app store assets, and install-driving imagery at scale with AI. - [AI Playable Ad Creatives for Mobile Games](https://www.layer.ai/use-cases/playable-ad-creatives) ([md](https://www.layer.ai/use-cases/playable-ad-creatives.md)): Design playable ad visuals and interactive end cards for mobile game UA. Generate character art, backgrounds, UI elements, and reward screens at scale. - [AI Rewarded Ad Assets for Mobile Games](https://www.layer.ai/use-cases/rewarded-ad-assets) ([md](https://www.layer.ai/use-cases/rewarded-ad-assets.md)): Generate rewarded ad end cards, interstitials, and offer walls for mobile games. Create reward screens and conversion assets that drive installs at scale. - [AI Social Media Visual Content with Layer](https://www.layer.ai/use-cases/social-media-content) ([md](https://www.layer.ai/use-cases/social-media-content.md)): Generate social media visuals 10x faster with AI. On-brand graphics for Instagram, TikTok, LinkedIn, X, and more. Style training, batch export, no seat fees. - [AI Sprite Generator for Game Studios](https://www.layer.ai/use-cases/sprite-generation) ([md](https://www.layer.ai/use-cases/sprite-generation.md)): AI sprite generator for game studios. Create 2D character sprites, sprite sheets, and pixel art 10x faster. Style training, batch generation, no seat fees. - [AI Storyboarding and Visual Narrative Development](https://www.layer.ai/use-cases/storyboarding) ([md](https://www.layer.ai/use-cases/storyboarding.md)): Create storyboards 10x faster with AI. Rapid visual narrative development for games, film, ads, and animation. 300+ models, style training, PSD export. - [AI Texture Generator for Game Studios](https://www.layer.ai/use-cases/texture-generation) ([md](https://www.layer.ai/use-cases/texture-generation.md)): AI texture generator for game studios. Create seamless, PBR-ready textures and materials 10x faster. Style training, PSD export, no seat fees. - [AI Video Ad Assets for Mobile Game UA](https://www.layer.ai/use-cases/ua-video-ads) ([md](https://www.layer.ai/use-cases/ua-video-ads.md)): Accelerate mobile game video ad production with AI. Generate storyboard frames, thumbnail variations, visual hooks, and end cards for UA video campaigns. ## Solutions by Role - [Layer for Ad Monetization Managers](https://www.layer.ai/for/ad-monetization-managers) ([md](https://www.layer.ai/for/ad-monetization-managers.md)): Ad monetization managers use Layer to create rewarded ad end cards, interstitial designs, and offer wall assets that maximize ad revenue per user. - [Layer for Art Directors](https://www.layer.ai/for/art-directors) ([md](https://www.layer.ai/for/art-directors.md)): Art directors use Layer to maintain style consistency, accelerate iteration, and scale visual production. Access top AI models with professional controls. - [Layer for Compliance & Legal Teams](https://www.layer.ai/for/compliance-legal-teams) ([md](https://www.layer.ai/for/compliance-legal-teams.md)): Layer is SOC 2 Type II certified, GDPR compliant, and built for enterprise security. Give your creative teams AI tools that pass compliance review. - [Layer for Concept Artists](https://www.layer.ai/for/concept-artists) ([md](https://www.layer.ai/for/concept-artists.md)): Concept artists use Layer to explore hundreds of directions in hours. Access top AI models, iterate rapidly, and present stronger concepts to stakeholders. - [Layer for Content Creators](https://www.layer.ai/for/content-creators) ([md](https://www.layer.ai/for/content-creators.md)): Content creators use Layer to produce stunning visuals for social media, YouTube, and digital platforms. Create unique content daily without design skills. - [Layer for Creative Directors](https://www.layer.ai/for/creative-directors) ([md](https://www.layer.ai/for/creative-directors.md)): Empower your creative team with AI-powered workflows. Layer gives creative directors the tools to scale output, maintain brand consistency, and ship faster. - [Layer for Creative Strategists](https://www.layer.ai/for/creative-strategists) ([md](https://www.layer.ai/for/creative-strategists.md)): Creative strategists use Layer to explore more concepts, build performance creative frameworks, and scale winning themes. AI for mobile game UA creative strategy. - [Layer for Freelance Artists](https://www.layer.ai/for/freelance-artists) ([md](https://www.layer.ai/for/freelance-artists.md)): Freelance artists use Layer to increase output, win more clients, and stay competitive. AI-powered tools that amplify your skills without replacing your vision. - [Layer for Game Artists](https://www.layer.ai/for/game-artists) ([md](https://www.layer.ai/for/game-artists.md)): Create stunning game assets 10x faster with Layer. Access top AI models, automate repetitive tasks, and collaborate with your team. Built for professional game artists. - [Layer for Growth Leads](https://www.layer.ai/for/growth-leads) ([md](https://www.layer.ai/for/growth-leads.md)): Growth leads use Layer to scale UA creative production, reduce CPI through creative testing volume, and hit install targets without proportional cost increases. - [Layer for Indie Game Developers](https://www.layer.ai/for/indie-game-developers) ([md](https://www.layer.ai/for/indie-game-developers.md)): Indie developers use Layer to create professional game art without hiring artists. Generate characters, environments, UI, and marketing assets at indie budgets. - [Layer for Marketing Teams](https://www.layer.ai/for/marketing-teams) ([md](https://www.layer.ai/for/marketing-teams.md)): Marketing teams use Layer to produce campaign visuals 10x faster. Maintain brand consistency, generate ad variations, and scale content production with AI. - [Layer for Roblox Experience Developers](https://www.layer.ai/for/roblox-experience-developers) ([md](https://www.layer.ai/for/roblox-experience-developers.md)): Roblox developers use Layer to create game assets, environments, and UI at scale. Build professional-quality experiences without a full art team. - [Layer for Roblox UGC Creators](https://www.layer.ai/for/roblox-ugc-creators) ([md](https://www.layer.ai/for/roblox-ugc-creators.md)): Roblox UGC creators use Layer to produce more items faster. Generate clothing variations, accessories, and avatar items at scale. Stand out in the marketplace. - [Layer for Studio Leads](https://www.layer.ai/for/studio-leads) ([md](https://www.layer.ai/for/studio-leads.md)): Studio leads use Layer to multiply team output, reduce production costs, and hit deadlines without sacrificing quality. Enterprise AI for creative operations. - [Layer for UA Managers](https://www.layer.ai/for/ua-managers) ([md](https://www.layer.ai/for/ua-managers.md)): UA managers use Layer to generate ad creative at scale, test more variations, and find winning creative faster. Built for mobile game user acquisition teams. ## Industries - [All Industries](https://www.layer.ai/industries) ([md](https://www.layer.ai/industries.md)) - [Layer for Digital Advertising](https://www.layer.ai/industries/digital-advertising) ([md](https://www.layer.ai/industries/digital-advertising.md)): Digital advertising agencies use Layer to produce ad creatives 5x faster with 300+ AI models, automated workflows, and enterprise security. No seat fees. - [Layer for Mobile Games](https://www.layer.ai/industries/mobile-games) ([md](https://www.layer.ai/industries/mobile-games.md)): Mobile game studios use Layer to scale art production, UA creatives, and LiveOps content 3-5x faster with 300+ AI models and workflow automation. - [Layer for Roblox UGC](https://www.layer.ai/industries/roblox-ugc) ([md](https://www.layer.ai/industries/roblox-ugc.md)): Roblox UGC creators and platforms use Layer to produce game assets, avatars, and virtual items 5x faster with 300+ AI models and workflow automation. - [Layer for Social Media Marketing](https://www.layer.ai/industries/social-media-marketing) ([md](https://www.layer.ai/industries/social-media-marketing.md)): Social media marketing teams use Layer to produce scroll-stopping content 5x faster with 300+ AI models, brand-consistent workflows, and no seat fees. ## Integrations - [All Integrations](https://www.layer.ai/integrations) ([md](https://www.layer.ai/integrations.md)) - [Layer + Blender Integration](https://www.layer.ai/integrations/blender) ([md](https://www.layer.ai/integrations/blender.md)): Generate textures, concepts, and 3D models with Layer AI for your Blender 3D modeling, texturing, and rendering workflows. - [Layer + Chrome Extension](https://www.layer.ai/integrations/chrome-extension) ([md](https://www.layer.ai/integrations/chrome-extension.md)): Save reference images from any website directly to your Layer workspace with the Layer Reference Collector Chrome extension. One-click saving, batch selection, and auto-upload. - [Layer + Figma Integration](https://www.layer.ai/integrations/figma) ([md](https://www.layer.ai/integrations/figma.md)): Integrate Layer AI with Figma to generate UI assets, game art, and marketing visuals directly into your design workflow and handoff pipeline. - [Layer + Illustrator Integration](https://www.layer.ai/integrations/illustrator) ([md](https://www.layer.ai/integrations/illustrator.md)): Generate icon concepts, UI elements, and vector assets with AI, then refine in Illustrator. SVG export for seamless vector workflows. - [Layer + Maya Integration](https://www.layer.ai/integrations/maya) ([md](https://www.layer.ai/integrations/maya.md)): Generate textures, concept art, and 3D models with Layer AI for Maya animation, character rigging, and VFX production workflows. - [Layer + Photoshop Integration](https://www.layer.ai/integrations/photoshop) ([md](https://www.layer.ai/integrations/photoshop.md)): Generate game art and creative assets with AI, then refine in Photoshop. Export as PSD for seamless round-trip editing. Built for professional studios. - [Layer + Premiere Pro Integration](https://www.layer.ai/integrations/premiere-pro) ([md](https://www.layer.ai/integrations/premiere-pro.md)): Generate thumbnails, visual assets, and video ad elements with AI, then edit in Premiere Pro. Accelerate game trailer and UA video production. - [Layer + Roblox Studio Integration](https://www.layer.ai/integrations/roblox-studio) ([md](https://www.layer.ai/integrations/roblox-studio.md)): Integrate Layer AI with Roblox Studio to generate decals, textures, UI assets, and thumbnails for Roblox experiences and UGC items. - [Layer + Unity Integration](https://www.layer.ai/integrations/unity) ([md](https://www.layer.ai/integrations/unity.md)): Layer is a Unity Verified Solution. Generate textures, sprites, UI assets, and concept art directly in your Unity game development pipeline. - [Layer + Unreal Engine Integration](https://www.layer.ai/integrations/unreal-engine) ([md](https://www.layer.ai/integrations/unreal-engine.md)): Integrate Layer AI with Unreal Engine to generate textures, materials, concept art, and UI assets for your Unreal game development pipeline. ## Glossary - [Full Glossary](https://www.layer.ai/glossary) ([md](https://www.layer.ai/glossary.md)) - [AI Model Comparison](https://www.layer.ai/glossary/ai-model-comparison) ([md](https://www.layer.ai/glossary/ai-model-comparison.md)): Learn how to compare and evaluate AI image generation models for creative production. Key criteria, popular models compared, and selection frameworks. - [CPI (Cost Per Install)](https://www.layer.ai/glossary/cpi) ([md](https://www.layer.ai/glossary/cpi.md)): Learn what CPI means in mobile game user acquisition. Understand how cost per install works, benchmarks by genre, and strategies to lower it. - [Creative Fatigue](https://www.layer.ai/glossary/creative-fatigue) ([md](https://www.layer.ai/glossary/creative-fatigue.md)): Learn what creative fatigue is, why it kills ad performance, and proven strategies to combat it with rapid creative production and AI-powered tools. - [eCPM (Effective Cost Per Mille)](https://www.layer.ai/glossary/ecpm) ([md](https://www.layer.ai/glossary/ecpm.md)): Learn what eCPM means in mobile game monetization. Understand how effective cost per mille measures ad revenue and how to optimize it. - [Generative AI for Games](https://www.layer.ai/glossary/generative-ai-for-games) ([md](https://www.layer.ai/glossary/generative-ai-for-games.md)): Learn how generative AI is transforming game development and marketing. From concept art to UA creatives, discover practical applications for game studios. - [IPM (Installs Per Mille)](https://www.layer.ai/glossary/ipm) ([md](https://www.layer.ai/glossary/ipm.md)): Learn what IPM means in mobile game user acquisition. Understand how installs per mille measures ad creative effectiveness and how to improve it. - [Playable Ads](https://www.layer.ai/glossary/playable-ads) ([md](https://www.layer.ai/glossary/playable-ads.md)): Learn what playable ads are, why they outperform other ad formats for mobile games, and how to create effective interactive ad experiences. - [Prompt Engineering](https://www.layer.ai/glossary/prompt-engineering) ([md](https://www.layer.ai/glossary/prompt-engineering.md)): Learn prompt engineering techniques for AI image generation. Practical tips for writing effective prompts that produce consistent, high-quality creative assets. - [Rewarded Video Ads](https://www.layer.ai/glossary/rewarded-video) ([md](https://www.layer.ai/glossary/rewarded-video.md)): Learn what rewarded video ads are, why they dominate mobile game monetization, and how to optimize ad placements for revenue and retention. - [Custom AI Style Training](https://www.layer.ai/glossary/style-training) ([md](https://www.layer.ai/glossary/style-training.md)): Learn how custom AI style training works, why it matters for brand consistency, and how game studios use it to generate on-brand creative assets at scale. - [UA Creative Testing](https://www.layer.ai/glossary/ua-creative-testing) ([md](https://www.layer.ai/glossary/ua-creative-testing.md)): Learn how to build a systematic creative testing methodology for mobile game user acquisition. Frameworks, metrics, and AI-powered scaling strategies. - [AI Workflow Automation](https://www.layer.ai/glossary/workflow-automation) ([md](https://www.layer.ai/glossary/workflow-automation.md)): Learn how AI workflow automation transforms creative production for game studios. Automate repetitive tasks and scale asset generation with AI pipelines. ## Blog - [All Posts](https://www.layer.ai/blog): Guides, updates, and news - [The New Layer Is Here: Why We Rebuilt Creative Production From the Ground Up](https://www.layer.ai/blog/the-new-layer-is-here) ([md](https://www.layer.ai/blog/the-new-layer-is-here.md)) (2026-07-30): For the past several months, we've been rebuilding Layer. Not a redesign, a rethink. Instead of a tool you operate, Layer is now an agent you direct. - [Introducing Layer MCP: Your Creative Engine, Inside Every AI You Use](https://www.layer.ai/blog/introducing-layer-mcp-your-creative-os-inside-every-ai-you-use) ([md](https://www.layer.ai/blog/introducing-layer-mcp-your-creative-os-inside-every-ai-you-use.md)) (2026-03-30): Introducing Layer MCP: Your Creative OS, Inside Every AI You Use Imagine a future where you could brief a campaign and immediately get production-ready creative back without switching tools, or - [GDC 2026 Recap: How AI Workflows Are Transforming UA Creative Production for Game Studios](https://www.layer.ai/blog/gdc-2026-recap-how-ai-workflows-are-transforming-ua-creative-production-for-game-studios) ([md](https://www.layer.ai/blog/gdc-2026-recap-how-ai-workflows-are-transforming-ua-creative-production-for-game-studios.md)) (2026-03-17): GDC 2026 Recap: How AI Workflows Are Transforming UA Creative Production for Game Studios GDC 2026 felt… different. Not because of flashy announcements or breakthrough demos. But because of what - [Layer Update (Feb '26) Workflows, Rich Exports, New Models, GDC 🚀](https://www.layer.ai/blog/monthly-updates-february-2026) ([md](https://www.layer.ai/blog/monthly-updates-february-2026.md)) (2026-03-06): February was a month of meaningful upgrades across Layer . New models landed, the export experience got a full overhaul, workflow tooling became shareable and smarter, and we kicked off the year on - [IP-Consistent AI Generation for Game Studios: The Complete Guide (2026)](https://www.layer.ai/blog/ip-consistency-ai-generation-guide-game-studios) ([md](https://www.layer.ai/blog/ip-consistency-ai-generation-guide-game-studios.md)) (2026-02-27): What Is IP-Consistent AI Generation? IP-consistent AI generation is the ability to produce creative assets using AI that maintain: Character identity Art style integrity Brand guidelines Color - [Google Nano Banana 2 🍌 & ByteDance SeedDream 5 Lite Are Now Live on Layer](https://www.layer.ai/blog/google-gemini-31-flash-image-bytedance-seeddream-5-lite-are-now-live-on-layer) ([md](https://www.layer.ai/blog/google-gemini-31-flash-image-bytedance-seeddream-5-lite-are-now-live-on-layer.md)) (2026-02-26): Production-Grade AI Image Generation and Editing for Game Studios Layer’s AI image generation stack just expanded. We’ve added four powerful new models to the platform: Google Gemini 3.1 Flash Image - [How Game Studios Choose a Creative Automation Vendor for UA and LiveOps (2026 Guide)](https://www.layer.ai/blog/battle-tested-ai-user-acquisition) ([md](https://www.layer.ai/blog/battle-tested-ai-user-acquisition.md)) (2026-02-19): How Game Studios Choose a Creative Automation Vendor for UA and LiveOps (2026 Guide) Best Creative Automation Software for Game Studios: UA & LiveOps Vendor Guide (2025) Learn how to evaluate and - [Layer Update (Jan ‘26) - Scaling UA Creatives with Workflows](https://www.layer.ai/blog/layer-update-january-2026) ([md](https://www.layer.ai/blog/layer-update-january-2026.md)) (2026-02-01): From Foundations to Scale Hello 👋 After a short break over the holidays - and several important updates behind the scenes - we’re back with our first monthly update of the year. For those who’ve been - [PGC London 2026 Recap: The Year UA Could Become Good, Fast, and Cheap](https://www.layer.ai/blog/pgc-london-2026-recap) ([md](https://www.layer.ai/blog/pgc-london-2026-recap.md)) (2026-02-01): PGC London 2026: The Year UA Could Become Good, Fast, and Cheap Pocket Gamer Connects London is always intense. This year was no different. Over two packed days, the Layer team met with studios, - [Layer Update (Nov ‘25) - Building the future of UA creative 🚀](https://www.layer.ai/blog/layer-updates-nov25-workflows) ([md](https://www.layer.ai/blog/layer-updates-nov25-workflows.md)) (2025-12-02): The biggest shift of the year is FINALLY HERE - introducing Layer Workflows . Currently in private beta ( sign up to try it early! ), this new node-based automation system that turns your creative - [Layer Update (Oct ‘25) - Tricks, Treats, & Templates](https://www.layer.ai/blog/monthly-updates-october-2025) ([md](https://www.layer.ai/blog/monthly-updates-october-2025.md)) (2025-11-10): Seasons are changing, and so is Layer with new features & improvements that make creating games a bit less scary 👻 We’ve released our huge new Templates system where you can jump right into premade - [New 3D features: Meshy, Seed3D, quad support, & retexturing](https://www.layer.ai/blog/seed-3d-meshy-quad-retexturing-support) ([md](https://www.layer.ai/blog/seed-3d-meshy-quad-retexturing-support.md)) (2025-11-10): The world of AI-driven 3D content creation continues to evolve at an incredible pace - and so does Layer. As more game studios integrate gen-AI directly into their pipelines for engines like Unreal - [Layer Update (Sept ‘25) - Create smarter, edit faster 🧠](https://www.layer.ai/blog/monthly-update-sept25) ([md](https://www.layer.ai/blog/monthly-update-sept25.md)) (2025-10-15): September was one of our biggest months yet. Our new pricing model is now live with Creative Units (CUs) as the new way to measure generation usage. You can now view and manage your usage directly - [Building the Future of Layer: Welcome John Wood👾](https://www.layer.ai/blog/new-hire-john-wood-engineering) ([md](https://www.layer.ai/blog/new-hire-john-wood-engineering.md)) (2025-10-08): As more game studios rely on Layer to power their creative pipelines, our engineering team plays a critical role in making sure everything scales smoothly, securely, and with the speed game creators - [New models: Kling 2.5, Wan 2.5, Ray 2, Seedream 4, & more 🔥](https://www.layer.ai/blog/new-models-kling-wan-ray-seedream) ([md](https://www.layer.ai/blog/new-models-kling-wan-ray-seedream.md)) (2025-10-06): We’re expanding Layer’s lineup again in a big way - adding a wave of new models that give game studios even more flexibility across every part of their creative pipeline. From cinematic video - [Designing the Future of Layer: Welcome Megan Whelen 🎨](https://www.layer.ai/blog/new-hire-designer-megan-whelen) ([md](https://www.layer.ai/blog/new-hire-designer-megan-whelen.md)) (2025-09-15): 2025 is already a milestone year for Layer. From audio generation, to new pricing models, prompt editing, new style training and more - we’ve added a LOT to the platform. This is all great stuff, but - [Layer Update (Aug ‘25) - Better features, new models, more flex 💪](https://www.layer.ai/blog/update-august-2025) ([md](https://www.layer.ai/blog/update-august-2025.md)) (2025-09-02): This summer has been all about leveling up the creative process for game studios. From sound effects and VO with our brand-new Audio Generation, to faster and smarter Custom Style Training, to - [Gemini 2.5 Flash by Google - now available on Layer](https://www.layer.ai/blog/gemini-2-5-flash-by-google) ([md](https://www.layer.ai/blog/gemini-2-5-flash-by-google.md)) (2025-08-27): Google’s newest image generation and editing model, Gemini 2.5 Flash Image , is now available on Layer. This is a big upgrade for game studios - giving you advanced control, higher fidelity images, - [Layer’s Pricing Changes: Simpler. Easier. More accessible.](https://www.layer.ai/blog/pricing-updates-2025) ([md](https://www.layer.ai/blog/pricing-updates-2025.md)) (2025-08-18): We’re changing how pricing works on Layer, starting on September 9th. The goal is simple: Make it easier for game teams of all sizes to access powerful AI tools - and only pay for what they create. - [Layer partners with ElevenLabs to deliver game-ready audio generation](https://www.layer.ai/blog/partners-eleven-labs-audio-generation-lipsync) ([md](https://www.layer.ai/blog/partners-eleven-labs-audio-generation-lipsync.md)) (2025-07-24): At Layer, our goal has always been simple: Give game studios everything they need to build. Today, we’re making that mission even stronger with a powerful new addition to the platform - audio - [#TeamLayer Updates: Product and Business Leadership](https://www.layer.ai/blog/new-hires-ilya-kuznetsov-alex-engel) ([md](https://www.layer.ai/blog/new-hires-ilya-kuznetsov-alex-engel.md)) (2025-07-15): It’s an exciting time at Layer. As more game studios adopt our AI tools to speed up production, scale content pipelines, and unlock new creative workflows, we’re expanding the team strategically. Our - [Layer Update (June ‘25) - Summer sounds with Audio gen 🌞🎶](https://www.layer.ai/blog/layer-update-june-25) ([md](https://www.layer.ai/blog/layer-update-june-25.md)) (2025-07-09): It’s summertime! Time to grab that laptop, hit the beach, and bring those games to life. From audio generation to advanced editing tools, this month’s updates are all about giving teams more creative - [Layer Update (May ‘25) - Funding & next-level video🥳](https://www.layer.ai/blog/update-may-25-funding-next-level-video) ([md](https://www.layer.ai/blog/update-may-25-funding-next-level-video.md)) (2025-06-06): We completed a HUGE seed funding round, raising 6.5M to keep making awesome tools for game studios. We also released like a billion new AI models this month. COINCIDENCE? I think not! But seriously, - [Veo 3 by Google - now available on Layer](https://www.layer.ai/blog/google-veo-3-layer-availability) ([md](https://www.layer.ai/blog/google-veo-3-layer-availability.md)) (2025-06-04): Creating high-quality game trailers, cutscenes, and marketing content is essential for most game teams - ideally without relying on expensive production or 3D pipelines. That’s where Veo 3, the - [Introducing FLUX Kontext: Better Editing, Better Control](https://www.layer.ai/blog/flux-kontext-editing-control) ([md](https://www.layer.ai/blog/flux-kontext-editing-control.md)) (2025-05-29): If you’ve followed us for any amount of time, you know we’re big fans of the FLUX model and the work coming out of Black Forest Labs. FLUX powers many of our default game styles and is the backbone - [Imagen 4 by Google - now available on Layer](https://www.layer.ai/blog/google-imagen-4-layer) ([md](https://www.layer.ai/blog/google-imagen-4-layer.md)) (2025-05-22): Google’s latest text-to-image model is now live on Layer - giving game studios access to one of the most accurate, versatile image models available today. Whether you’re working in stylized 2D or - [Layer raises $6.5MM USD to keep delivering leading next-gen tools for game studios](https://www.layer.ai/blog/layer-raises-6-5m-usd-next-gen-tools-game-studios) ([md](https://www.layer.ai/blog/layer-raises-6-5m-usd-next-gen-tools-game-studios.md)) (2025-05-14): We’re thrilled to announce that Layer has successfully closed a seed funding round, raising $6.5 million from renowned games industry leaders, Riccardo Zacconi (co-founder of King) and Akin Babayigit - [Meet Shay Pomeroy: Marketer & Games Industry Veteran](https://www.layer.ai/blog/meet-shay-pomeroy-games-marketing-veteran) ([md](https://www.layer.ai/blog/meet-shay-pomeroy-games-marketing-veteran.md)) (2025-05-10): As we enter a new year, we’re laser focused on expanding Layer into more game studios than ever before. To this end, it’s critical we bring more games industry veterans onto the Layer team, people - [Layer Update (April ‘25) - Edit with AI & Refine at Scale](https://www.layer.ai/blog/april-25-ai-edit-refine-scale) ([md](https://www.layer.ai/blog/april-25-ai-edit-refine-scale.md)) (2025-05-08): April was all about tightening the bolts on core functionality. We launched the new Activity Feed, giving teams a clean, searchable view of every generation across Sessions - a big win for game - [Layer 2025 Offsite: Defining the future of AI-powered game content](https://www.layer.ai/blog/ai-generated-game-content) ([md](https://www.layer.ai/blog/ai-generated-game-content.md)) (2025-04-25): Last week, our team gathered in Napa, California for Layer’s first major offsite. After months of rapid growth, product launches, and new team members joining from across the globe, we took a moment - [Layer Update (Mar ‘25) - Fresh Faces, Fresh Features⚒️](https://www.layer.ai/blog/update-march-25-fresh-faces-new-features) ([md](https://www.layer.ai/blog/update-march-25-fresh-faces-new-features.md)) (2025-04-08): March brought the heat with a wave of updates, fresh features, and new #TeamLayer members. We kicked things off with a new onboarding experience for new users, launched the Hunyuan3D 2.0 model for 3D - [Layer Update (Feb ‘25) - The rise of video📽️](https://www.layer.ai/blog/layer-update-feb-25) ([md](https://www.layer.ai/blog/layer-update-feb-25.md)) (2025-03-25): As we get deeper into the new year, we’re seeing some big trends in the gen-AI space. A big one, of course, has been the rise of video generation in a relatively short period of time. With video - [#TeamLayer Updates: More engineers, more possibilities](https://www.layer.ai/blog/teamlayer-hires-developers) ([md](https://www.layer.ai/blog/teamlayer-hires-developers.md)) (2025-03-25): 2025 is a big year for us. We’re working more game studios every month, and the team is full throttle building features that help game creators scale their work. After plying our existing engineers - [Expanding 3D Creation on Layer with Hunyuan3D 2.0 by Tencent](https://www.layer.ai/blog/expanding-hunyuan3d-creation-v2) ([md](https://www.layer.ai/blog/expanding-hunyuan3d-creation-v2.md)) (2025-03-20): Making high-quality 3D assets has always been time-consuming and expensive for game studios. AI is changing that, making it faster and cheaper to generate detailed models without sacrificing quality. - [Expanding Video Generation on Layer with Wan 2.1](https://www.layer.ai/blog/alibaba-video-generation) ([md](https://www.layer.ai/blog/alibaba-video-generation.md)) (2025-02-27): Video is a critical part of game development, powering everything from trailers and UA campaigns to in-game animations and dynamic backgrounds. High-quality video production has always been expensive - [Layer Update (Jan ‘25) - New year, new tools, new you 🎉](https://www.layer.ai/blog/layer-update-jan-25) ([md](https://www.layer.ai/blog/layer-update-jan-25.md)) (2025-02-14): A new year is always exciting, another chance to reinvent yourself (or your game). With AI models getting better than ever, we’re excited for another year of helping game developers create awesome - [Video Generation is here: Trailers, game items, ads, & more](https://www.layer.ai/blog/game-item-trailer-generator) ([md](https://www.layer.ai/blog/game-item-trailer-generator.md)) (2025-02-04): We’ve all heard it a million times: Video performs better! We need a better game trailer! Where are those video ads! The problem? Video has historically been difficult and expensive to create. Let’s - [Layer Update (Dec ‘24) - Wrapping up a year of growth 🎁](https://www.layer.ai/blog/dec-24-year-end-growth-update) ([md](https://www.layer.ai/blog/dec-24-year-end-growth-update.md)) (2025-01-02): It’s been an amazing year for Layer. We’re incredibly humbled by the amount of studios using Layer every day to power their creations. Our goal has always been to make game development easier, - [New 3D models: Trellis 3D, Tripo AI, & Rodin now on Layer](https://www.layer.ai/blog/new-3d-models-trellis-3d-tripo-ai-rodin) ([md](https://www.layer.ai/blog/new-3d-models-trellis-3d-tripo-ai-rodin.md)) (2024-12-30): The world of AI-powered 3D content creation is rapidly evolving, and we’re committed to giving our game studio partners access to the best the industry has to offer through our private, compliant, - [Layer x Shanghai Vancouver Film School: Bringing innovative gen-AI to students](https://www.layer.ai/blog/shanghai-vancouver-film-school-gen-ai-students) ([md](https://www.layer.ai/blog/shanghai-vancouver-film-school-gen-ai-students.md)) (2024-12-27): One of the key aspects of building industry-changing tools is the importance of supporting the next generation of artists and creators. These students will soon be bringing their dreams to life, and - [Layer Update (Nov ‘24) - Things are getting REALtime 🎉](https://www.layer.ai/blog/layer-update-nov-24-realtime) ([md](https://www.layer.ai/blog/layer-update-nov-24-realtime.md)) (2024-12-12): The weather is cooling off - but our updates are only getting HOTTER 🔥 We’re incredibly excited to announce that our live canvas feature, Realtime, is now live for all creators. This tool is perfect - [Bring your concepts to life with Realtime on Layer](https://www.layer.ai/blog/bring-concepts-life-realtime-layer) ([md](https://www.layer.ai/blog/bring-concepts-life-realtime-layer.md)) (2024-12-03): In game development, ideas evolve in the blink of an eye. Concepting is one of the most important parts of the creative process, the early-stage work that will set the stage for production to come. - [Layer partners with WePlay HUB to bring the power of AI to emerging game studios](https://www.layer.ai/blog/layer-partners-weplay-hub-game-studios) ([md](https://www.layer.ai/blog/layer-partners-weplay-hub-game-studios.md)) (2024-11-28): We're excited to announce our partnership with WePlay HUB , a dynamic gaming accelerator focused on the growth of emerging game studios in Europe, Central Asia, and Turkey. This collaboration - [Layer Update (Oct ‘24) - 3D generation is ALIVE 🧟](https://www.layer.ai/blog/update-oct-24-3d-generation) ([md](https://www.layer.ai/blog/update-oct-24-3d-generation.md)) (2024-11-08): Halloween always brings out the best in creativity. This month's update has BIG new features designed to enhance workflows on Layer. First up, we’re bringing a whole new dimension to the platform: - [Unlock a new dimension with 3D generations on Layer](https://www.layer.ai/blog/unlock-a-new-dimension-with-3d-generations-on-layer) ([md](https://www.layer.ai/blog/unlock-a-new-dimension-with-3d-generations-on-layer.md)) (2024-11-07): Let’s face it—game art today is rarely just 2D or 3D. Most games use a combo of both to achieve their gameplay and style. To this end.. we’re excited to announce that going forward Layer will be - [Mobidictum 2024 Recap: The future of AI workflows & 2025 predictions](https://www.layer.ai/blog/mobidictum-2024-future-workflows-predictions) ([md](https://www.layer.ai/blog/mobidictum-2024-future-workflows-predictions.md)) (2024-11-05): Last month, Layer joined forces with Fortune Mine Games on stage at the Mobidictum Istanbul Conference . As a sponsor, Layer connected with over 1,000 gaming pros, all gathered in Istanbul, Turkey, - [Layer Update (Sept ‘24) - FLUX ‘n Forge ⚒️](https://www.layer.ai/blog/layer-update-sept-24-flux-n-forge) ([md](https://www.layer.ai/blog/layer-update-sept-24-flux-n-forge.md)) (2024-10-18): It’s getting colder, but our Layer updates are hotter than ever. 🥵 As we head into fall, we’re excited to share some big updates to some of our core models and functionality. FLUX is already proven - [Layer Artist Guide: Creating mobile UI elements w/ custom styles](https://www.layer.ai/blog/layer-artist-guide-creating-mobile-ui-elements-custom-styles) ([md](https://www.layer.ai/blog/layer-artist-guide-creating-mobile-ui-elements-custom-styles.md)) (2024-09-30): Welcome back to our Artist Guide series for Layer creators. Building off of our previous blog on creating a style guide , we now need to finalize what our user interface’s art style will look like. - [Layer Update (Aug ‘24) - Empowering Creativity with Artist-first UX](https://www.layer.ai/blog/update-aug-24-empowering-creativity-artist-ux) ([md](https://www.layer.ai/blog/update-aug-24-empowering-creativity-artist-ux.md)) (2024-09-11): The power of AI is amazing, but there’s always been one challenge: Control 🎮 It’s not enough to generate assets, you need to get your image perfect when working with real game assets and IP. This is - [Layer Artist Guide: Exploring different art styles for your game](https://www.layer.ai/blog/artist-guide-exploring-art-styles) ([md](https://www.layer.ai/blog/artist-guide-exploring-art-styles.md)) (2024-08-29): Welcome back to our series on how Layer accelerates a game art pipeline . In the first blog, we covered an introduction of what game art pipelines are, and in the second we showed how Layer can save - [Layer adopts Flux: Taking your gen-AI journey to the next level](https://www.layer.ai/blog/flux-taking-gen-ai-journey-next-level) ([md](https://www.layer.ai/blog/flux-taking-gen-ai-journey-next-level.md)) (2024-08-07): At Layer, we’re committed to staying at the forefront of this evolution by integrating the latest tools that empower game studios to bring their visions to life. That’s why we’re thrilled to announce - [Layer Update (July ‘24) - Start your journey into FLUX 🚀](https://www.layer.ai/blog/layer-update-july-24-start-your-journey-into-flux) ([md](https://www.layer.ai/blog/layer-update-july-24-start-your-journey-into-flux.md)) (2024-08-06): Put down the sunscreen and pick up your computer - Layer is coming at you with some hot summer updates. This month is a big one, with the addition of the FLUX.1 model + major feature improvements - [Layer Artist Guide: From concept to creation with professional game characters](https://www.layer.ai/blog/guide-concept-creation-game-characters) ([md](https://www.layer.ai/blog/guide-concept-creation-game-characters.md)) (2024-07-22): In many games, characters are the first thing to be defined, since they drive so much of the game’s mechanics and storytelling. In the style exploration step, the team begins to solidify the art - [What’s new for Layer creators (June 2024)](https://www.layer.ai/blog/whats-new-june-2024) ([md](https://www.layer.ai/blog/whats-new-june-2024.md)) (2024-07-10): Happy Summer Layer Creators! We hope you’ve been enjoying the sunshine, as well as the ability to create professional game assets with ease. 😅 It’s always been our goal to ensure that Layer is - [Layer Artist Guide: Bringing artist-first AI into your studio workflows](https://www.layer.ai/blog/how-bring-artist-first-ai-studio-workflows) ([md](https://www.layer.ai/blog/how-bring-artist-first-ai-studio-workflows.md)) (2024-07-03): Perhaps you’ve heard of generative AI and the ethical implications it has around art. How it’ll replace artists, how it is stealing artwork, and most importantly how it impacts industries like film - [Meet Michael Sabetta: Mobile games veteran, digital artist, and now Dir of Creative @ Layer](https://www.layer.ai/blog/meet-michael-sabetta-mobile-games-veteran-digital-artist-dir-creative) ([md](https://www.layer.ai/blog/meet-michael-sabetta-mobile-games-veteran-digital-artist-dir-creative.md)) (2024-07-02): We are thrilled to announce that Michael Sabetta has joined the Layer team as our new Director of Creative. This role is all about creating an amazing user experience on Layer, something that’s - [What’s new for Layer creators (May 2024)](https://www.layer.ai/blog/whats-new-layer-creators-may-2024) ([md](https://www.layer.ai/blog/whats-new-layer-creators-may-2024.md)) (2024-06-05): Hello Creators! Another month of development and flown by and we’re excited to share our updates with you. Our focus for May was around building a better user experience on Layer, making it easier - [Meet Emory Irpan: Artist, Game Designer, Product Leader & Layer Advisor](https://www.layer.ai/blog/meet-emory-irpan-artist-game-designer-product-leader-layer-advisor) ([md](https://www.layer.ai/blog/meet-emory-irpan-artist-game-designer-product-leader-layer-advisor.md)) (2024-05-31): We’re excited to announce our newest advisor — games industry veteran Emory Irpan. Emory has been an early supporter of the Layer platform, and brings a wealth of experience as a product leader and - [What’s new for Layer creators (April 2024)](https://www.layer.ai/blog/whats-new-for-layer-creators-april-2024) ([md](https://www.layer.ai/blog/whats-new-for-layer-creators-april-2024.md)) (2024-05-02): April’s been a busy month for the Layer team! We’ve made big updates to the platform, added powerful features dedicated to compliance, and upgraded our data security. We also brought on a new - [Layer partners with BRIA to enable copyright compliant gen-AI for game studios](https://www.layer.ai/blog/layer-partners-with-bria-to-enable-copyright-compliant-gen-ai-for-game-studios) ([md](https://www.layer.ai/blog/layer-partners-with-bria-to-enable-copyright-compliant-gen-ai-for-game-studios.md)) (2024-04-29): We believe in the power of compliant, responsible and friendly generative-AI, where game-changing technology is guided by human principles. This is why Layer is the first gaming focused gen-AI tool - [Layer becomes the first SOC 2 compliant gaming gen AI provider](https://www.layer.ai/blog/layer-becomes-the-first-soc-2-compliant-gaming-gen-ai-provider) ([md](https://www.layer.ai/blog/layer-becomes-the-first-soc-2-compliant-gaming-gen-ai-provider.md)) (2024-04-04): The world of AI is exciting, powerful, and inspiring — but comes with some major challenges when it comes to compliance. As companies move quickly to create new AI-focused solutions, they often lose - [Meet Matt Omernick: Entrepreneur, Games Industry Leader, & (now) Layer Advisor](https://www.layer.ai/blog/meet-matt-omernick-entrepreneur-games-industry-leader-now-layer-advisor) ([md](https://www.layer.ai/blog/meet-matt-omernick-entrepreneur-games-industry-leader-now-layer-advisor.md)) (2024-04-02): We’re excited to announce that games industry leader Matt Omernick (MattO) has officially joined Layer AI as an advisor. Matt has been an early investor and supporter of the Layer platform, and we’re - [Empowering Human Creativity: How Layer’s gen-AI enhances artists while respecting Copyright](https://www.layer.ai/blog/empowering-human-creativity-how-layers-gen-ai-enhances-artists-while-respecting-copyright) ([md](https://www.layer.ai/blog/empowering-human-creativity-how-layers-gen-ai-enhances-artists-while-respecting-copyright.md)) (2024-02-06): Here at Layer, we believe in the creative and transformative benefit offered by generative AI but we also believe it should be used ethically and responsibly, in a manner that is fair and respects - [What Layer Believes in — Using AI, Staying Human](https://www.layer.ai/blog/what-layer-believes-in-using-ai-staying-human) ([md](https://www.layer.ai/blog/what-layer-believes-in-using-ai-staying-human.md)) (2024-01-03): What Layer Believes in — Using AI, Staying Human Here at Layer, we believe in the creative and transformative benefit offered by generative AI, and offer it to our customers and to the users of our - [Navigating In The Era Of AI-Powered Game Production: A guide for safe authorship with Layer](https://www.layer.ai/blog/navigating-in-the-era-of-ai-powered-game-production-a-guide-for-safe-authorship-with-layer) ([md](https://www.layer.ai/blog/navigating-in-the-era-of-ai-powered-game-production-a-guide-for-safe-authorship-with-layer.md)) (2023-12-28): Layer is the leading AI-powered tool for 2D content generation for games. Artists using Layer can train custom AI models using their own art work in their private workspaces, create novel concepts - [Layer AI raises $1.8m to supercharge game art production](https://www.layer.ai/blog/layer-raises-1-8m-to-supercharge-game-art-production) ([md](https://www.layer.ai/blog/layer-raises-1-8m-to-supercharge-game-art-production.md)) (2023-11-16): Layer, the AI-powered productivity tool of choice by the world’s top gaming companies, raises a $1.8M seed round by top ad-tech and gaming angels, and VC funds . The creator-first, enterprise-ready - [Sarp Kerem Yavuz opens his first AI-photography exhibition using Layer AI](https://www.layer.ai/blog/sarp-kerem-yavuz-opens-photography-exhibition-using-layer) ([md](https://www.layer.ai/blog/sarp-kerem-yavuz-opens-photography-exhibition-using-layer.md)) (2023-10-19): In a world where the boundaries between human creativity and technological innovation continue to blur, the art of photography has found itself at the forefront of a digital renaissance. This - [Breaking Boundaries: Unity and Layer AI to Empower Student Game Creators](https://www.layer.ai/blog/unity-layer-student-game-creators) ([md](https://www.layer.ai/blog/unity-layer-student-game-creators.md)) (2023-10-01): Layer AI and Unity making game development more accessible and inspiring than ever before with a goal to unleash the creative potential of students around the world. Driven by a shared belief that - [Layer AI gets accepted to NVIDIA Inception program](https://www.layer.ai/blog/layer-ai-gets-accepted-to-nvidia-inception-program) ([md](https://www.layer.ai/blog/layer-ai-gets-accepted-to-nvidia-inception-program.md)) (2023-09-27): We’re thrilled to announce that Layer AI joins the prestigious NVIDIA Inception Program which is an exclusive program designed for an elite group of startups leading change across industries and - [Layer AI becomes a Unity Verified Solution](https://www.layer.ai/blog/layer-ai-becomes-a-unity-verified-solution) ([md](https://www.layer.ai/blog/layer-ai-becomes-a-unity-verified-solution.md)) (2023-01-28): We are thrilled to announce that Layer AI has become a Unity Verified Solution! The Unity Verified Solutions program is designed to provide Unity customers with access to a network of trusted - [Unleashing Generative AI for Games](https://www.layer.ai/blog/unleashing-generative-ai-games) ([md](https://www.layer.ai/blog/unleashing-generative-ai-games.md)) (2023-01-20): Today, we're thrilled to announce the beta launch of our next-level creation suite for game art. Layer enables any game artist to generate countless new assets based on their unique art styles. All ## Success Stories - [All Success Stories](https://www.layer.ai/success-stories): Case studies from game studios #### [Ace Games](https://www.layer.ai/success-stories/ace-games) ([md](https://www.layer.ai/success-stories/ace-games.md)) How Ace Games cultivated AI-driven production pipelines Learn how this premier mobile game studio in Istanbul leveraged Layer’s AI toolset to create custom styles, character art, backgrounds and more to support Fiona's Farm - a popular live service puzzle game on Android and iOS. Key results: 60 Studio size | 80% Increase in productivity | 120 Est. monthly hours saved in art creation #### [Bunch](https://www.layer.ai/success-stories/bunch) ([md](https://www.layer.ai/success-stories/bunch.md)) How Bunch supercharged player customization with Layer Explore how Bunch leveraged the power of Layer’s professional gen-AI tools to create a strong pipeline of virtual avatars and environments designed to keep player engagement high. Key results: 35 Studio size | 10 Professional game assets in a week | 3x Increase in team productivity | 150K Virtual players engaged #### [Celestial Alpaca Studios](https://www.layer.ai/success-stories/celestial-alpaca-studios) ([md](https://www.layer.ai/success-stories/celestial-alpaca-studios.md)) How Celestial Alpaca Studios created out-of-this-world assets with Layer Learn how this two-person indie studio was able to leverage Layer AI to build an effective asset production pipeline and launch their game Astro Panic into early access. Key results: 2 Studio size | +200 Game assets created | 2-3x Est. asset creation speed | 50 Early access pilots engaged #### [Cosmic Lounge](https://www.layer.ai/success-stories/cosmic-lounge) ([md](https://www.layer.ai/success-stories/cosmic-lounge.md)) How Cosmic Lounge powers their Puzzle Engine with Layer Learn how Cosmic Lounge used Layer’s AI tools to accelerate content production across their mobile puzzle games by integrating Layer’s API into their custom Puzzle Engine + training in-house styles for 2D. Key results: 20 Studio size | 5 Game artists | 75% Increased art concepting speed | 80% Production time saved #### [Fortune Mine Games](https://www.layer.ai/success-stories/fortune-mine-games) ([md](https://www.layer.ai/success-stories/fortune-mine-games.md)) How Fortune Mine Games sped up level design by 72% with Layer Learn how the Fortune Mine team built new gen-AI powered workflows to drastically increase their ability to create new levels in the popular live service game Coin Chef. Key results: 20 Studio size | +1000 Live service assets created | +72% Increase in production efficiency #### [Gamegos](https://www.layer.ai/success-stories/gamegos) ([md](https://www.layer.ai/success-stories/gamegos.md)) How Gamegos boosted mobile live-ops production with Layer Learn how this mobile studio used Layer’s artist-first toolset to create everything from marketing visuals and live-ops artwork to in-game features - all in the style of existing IP for Adventure Bay, Manor Cafe and Cafeland - Restaurant Cooking. Key results: 60 Studio size | 100 Est. hours saved in art creation | 3x Increase in productivity #### [Games United](https://www.layer.ai/success-stories/games-united) ([md](https://www.layer.ai/success-stories/games-united.md)) How Games United boosted art creation by 240% with Layer Learn how the Games United team leveraged Layer’s AI style training to scale out their art production for Merge Park, leading to a huge uptick in live service pipelines. Key results: 41 Studio size | 160 Professional game assets shipped | +240% Increase in team productivity | 4 New games in soft-launch #### [Work Dog Studios](https://www.layer.ai/success-stories/how-work-dog-streamlined-video-creation) ([md](https://www.layer.ai/success-stories/how-work-dog-streamlined-video-creation.md)) How Work Dog streamlined video creation by 70% with Layer Work Dog Studios uses Layer to accelerate early-stage production - turning rough ideas into full campaign mockups, consistent character videos, and pitch-ready visuals in a matter of hours, not days. Key results: 50 Studio size | 70% Faster early-stage production | 40 Avg. hours saved per project #### [LBC Studios](https://www.layer.ai/success-stories/lbc-studios) ([md](https://www.layer.ai/success-stories/lbc-studios.md)) How LBC Studios brewed up game assets in record time using Layer Learn how this independent mobile games studio in Vancouver was able to leverage Layer’s professional AI tools to unblock and ultimately accelerate their art pipeline for Brewtopia producing 10 high quality style consistent game characters as well as vehicles, icons and props in a work week. Key results: 40 Studio size | 250+ Est. hours saved in production | 8x Increase in productivity #### [LBC Studios](https://www.layer.ai/success-stories/lbc-studios-update) ([md](https://www.layer.ai/success-stories/lbc-studios-update.md)) How LBC Studios cultivates assets for Shroomtopia’s new world Learn how LBC Studios used Layer to scale Shroomtopia’s art production pipelines and create new characters, lush environments, and stylized mushrooms in record time, all while keeping their hand-drawn aesthetic intact. Key results: 12 Studio size | 300+ Est. hours saved in production | 8x Increase in productivity #### [Liveplay](https://www.layer.ai/success-stories/live-play-mobile) ([md](https://www.layer.ai/success-stories/live-play-mobile.md)) How Live Play Mobile delivers fresh liveops content with Layer Learn how Live Play Mobile used Layer’s AI-powered tools to scale their collectible assets pipeline for Live Play Bingo. By training custom styles in FLUX for characters and backgrounds, they streamlined their workflow, creating hundreds of high-quality assets in a fraction of the time - while keeping it all on-brand. Key results: 70+ Studio size | +24 Est. hours saved in art creation per week | 300% Increase in productivity #### [Lokum Games](https://www.layer.ai/success-stories/lokum-games) ([md](https://www.layer.ai/success-stories/lokum-games.md)) How Lokum Games reloaded their art pipeline with Layer Learn how this international mobile games studio in Europe leveraged Layer to create a professional AI-powered art pipeline for their newest shooter, Tactical Strike - saving upwards of 2800 hours in production time. Key results: 21 Studio size | 2800+ Est. hours saved in art creation | 90% Increase in art productivity #### [NoExit Games](https://www.layer.ai/success-stories/noexit-games) ([md](https://www.layer.ai/success-stories/noexit-games.md)) How NoExit Games turned AI curiosity into creative momentum Learn how NoExit Games uses Layer to cut production time in half, stay visually consistent, and move faster across everything from load screens to icons for their hyper-casual mobile game Cook Kingdom. Key results: 5 Studio size | +4500 Est. monthly hours saved in art creation | 60% Reduced production time #### [PlayPack Games](https://www.layer.ai/success-stories/playpack) ([md](https://www.layer.ai/success-stories/playpack.md)) How PlayPack created 100s of game-ready assets with Layer Learn how this international studio of industry veterans leveraged Layer’s gen-AI solutions to create item sets, characters, UI elements, and more for mobile games Greentown, Merge Away, and Cozy Lane. Key results: 10 Studio size | 200+ Production-ready assets created | 3+ Live games supported #### [Upland](https://www.layer.ai/success-stories/upland) ([md](https://www.layer.ai/success-stories/upland.md)) How Upland adopted Layer to scale their creativity (and llamas) Learn how this truly international game studio leveraged Layer to create custom styles and scale their art production pipelines across their innovative Web3 powered game - while creating near infinite variations of their beloved mascot Miles. Key results: 50 Studio size | 2-5 Est. hours saved per illustration | +50% Increase in productivity #### [Wixot](https://www.layer.ai/success-stories/wixot) ([md](https://www.layer.ai/success-stories/wixot.md)) How Wixot & Layer merged gen-AI with art production in Journey Home Explore how this small but ambitious mobile games studio in London leveraged Layer’s industry-leading gen-AI to supercharge their live-service art pipelines in Journey Home: Merge & Stories. Key results: 23 Studio size | 600 Est. hours saved in art creation | 3x Increase in productivity ## Resources - [Partners](https://www.layer.ai/partners): Model providers and technology partners - [About](https://www.layer.ai/about): Team, mission, and company information - [Careers](https://www.layer.ai/careers): Open positions at Layer ## Legal - [Acceptable Use Policy](https://www.layer.ai/acceptable-use-policy) - [Copyright Infringement Policy](https://www.layer.ai/copyright-infringement-policy) - [Privacy Policy](https://www.layer.ai/privacy-policy) - [Terms of Service](https://www.layer.ai/terms-of-service)