# Gemini 4 Carbon — connected models and workflows
Canonical: https://gemini4carbon.app/models.md

This list comes from active application catalogs and effective integration configuration, not the number of marketing pages. Configured does not guarantee a provider will accept every request or promise future availability. Public IDs below are application identifiers; private upstream endpoints, credentials, upload links and internal APIs are excluded. Inputs must satisfy workspace validation. Quotes and reservations: https://gemini4carbon.app/pricing.md.

## Image models (15)
Shared image workspace initial settings: {"modelId":"gpt-image-2","mode":"text","aspectRatio":"auto","resolution":"1K"}. Changing the selected tool/model can select another compatible preset.
### Seedream 5.0 Pro (seedream-5-pro)
- Provider label: Seedream; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: layer-decomposition, text, image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 5000 characters; required: true. Up to 10 reference images. Outputs: 6.
- Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3. Resolutions: 1K, 2K. Configured resolution fallback: 2K. Layer resolutions: auto, 1K, 1.5K, 2K.
- Input MIME types: validated by the workspace. Input byte limit: 31457280. Output format: model/workspace selected.

### GPT Image 2.5 Flare (gpt-image-2.5-flare)
- Provider label: OpenAI; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text, image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 32000 characters; required: true. Up to 16 reference images. Outputs: 10.
- Ratios: 1:1, auto, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, 5:4, 4:5. Resolutions: 1K, 2K, 4K. Configured resolution fallback: 1K. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: model/workspace selected.
- Quality options: {"values":["auto","low","medium","high","xhigh","max"],"default":"high"}; formats: {"values":["png","jpeg","webp"],"default":"png"}; background: {"values":["auto","transparent","opaque"],"default":"auto"}; size rules: {"presets":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9"],"multiple":16,"maxEdge":3840,"minPixels":655360,"maxPixels":8294400,"maxAspectRatio":3}; compression: {"min":0,"max":100,"formats":["jpeg","webp"]}; output count: {"min":1,"max":10,"default":1}; optional mask: {"modes":["image"],"optional":true}.

### GPT Image 2.5 Sunburst (gpt-image-2.5-sunburst)
- Provider label: OpenAI; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text, image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 32000 characters; required: true. Up to 16 reference images. Outputs: 10.
- Ratios: 1:1, auto, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, 5:4, 4:5. Resolutions: 1K, 2K, 4K. Configured resolution fallback: 1K. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: model/workspace selected.
- Quality options: {"values":["auto","low","medium","high","xhigh","max"],"default":"high"}; formats: {"values":["png","jpeg","webp"],"default":"png"}; background: {"values":["auto","transparent","opaque"],"default":"auto"}; size rules: {"presets":["auto","square_hd","square","portrait_4_3","portrait_16_9","landscape_4_3","landscape_16_9"],"multiple":16,"maxEdge":3840,"minPixels":655360,"maxPixels":8294400,"maxAspectRatio":3}; compression: {"min":0,"max":100,"formats":["jpeg","webp"]}; output count: {"min":1,"max":10,"default":1}; optional mask: {"modes":["image"],"optional":true}.

### GPT Image 2 (gpt-image-2)
- Provider label: OpenAI; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text, image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 20000 characters; required: true. Up to 16 reference images. Outputs: multiple, validated by the workspace.
- Ratios: auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, 9:21, 5:4, 4:5. Resolutions: 1K, 2K, 4K. Configured resolution fallback: 1K. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: model/workspace selected.

### Nano Banana 2 (nano-banana-2)
- Provider label: Nano Banana; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text, image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 20000 characters; required: true. Up to 14 reference images. Outputs: multiple, validated by the workspace.
- Ratios: auto, 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. Resolutions: 1K, 2K, 4K. Configured resolution fallback: 1K. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: model/workspace selected.

### Nano Banana Pro (nano-banana-pro)
- Provider label: Nano Banana; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text, image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 20000 characters; required: true. Up to 14 reference images. Outputs: multiple, validated by the workspace.
- Ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. Resolutions: 1K, 2K, 4K. Configured resolution fallback: 1K. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: model/workspace selected.

### Nano Banana (nano-banana)
- Provider label: Nano Banana; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text, image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 20000 characters; required: true. Up to 10 reference images. Outputs: multiple, validated by the workspace.
- Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9. Resolutions: model default. Configured resolution fallback: model default. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: model/workspace selected.

### Seedream 5 Lite (seedream-5-lite)
- Provider label: Seedream; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text, image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 5000 characters; required: true. Up to 10 reference images. Outputs: multiple, validated by the workspace.
- Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9. Resolutions: 2K, 3K. Configured resolution fallback: 2K. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: model/workspace selected.

### Seedream 4.5 (seedream-4-5)
- Provider label: Seedream; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text, image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 3000 characters; required: true. Up to 10 reference images. Outputs: multiple, validated by the workspace.
- Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9. Resolutions: 2K, 4K. Configured resolution fallback: 2K. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: model/workspace selected.

### Seedream V4 (seedream-v4)
- Provider label: Seedream; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text, image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 5000 characters; required: true. Up to 10 reference images. Outputs: multiple, validated by the workspace.
- Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9. Resolutions: 1K, 2K, 4K. Configured resolution fallback: 1K. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: model/workspace selected.

### Bria RMBG 2.0 (bria-background-remove)
- Provider label: Bria; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 0 characters; required: false. Up to 1 reference images. Outputs: 1.
- Ratios: auto. Resolutions: original. Configured resolution fallback: original. Layer resolutions: not offered.
- Input MIME types: image/jpeg, image/png, image/webp. Input byte limit: 31457280. Output format: png.

### Illusion Diffusion (illusion-diffusion)
- Provider label: Illusion Diffusion; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 2000 characters; required: true. Up to 1 reference images. Outputs: 1.
- Ratios: 1:1. Resolutions: 1K. Configured resolution fallback: 1K. Layer resolutions: not offered.
- Input MIME types: image/jpeg, image/png, image/webp. Input byte limit: 10485760. Output format: png.

### Z-Image (z-image)
- Provider label: Z-Image; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 1000 characters; required: true. Up to 0 reference images. Outputs: 1.
- Ratios: 1:1, 4:3, 3:4, 16:9, 9:16. Resolutions: model default. Configured resolution fallback: model default. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: model/workspace selected.

### Nano Banana 2 Lite (nano-banana-2-lite)
- Provider label: Nano Banana; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 50000 characters; required: true. Up to 0 reference images. Outputs: 4.
- Ratios: auto, 1:1, 21:9, 16:9, 3:2, 4:3, 5:4, 4:5, 3:4, 2:3, 9:16, 4:1, 1:4, 8:1, 1:8. Resolutions: 1K. Configured resolution fallback: 1K. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: png.

### GPT Image 1.5 (gpt-image-1.5)
- Provider label: OpenAI; workspace: https://gemini4carbon.app/ai-image-generator.
- Modes: text, image. Image mode requires an image; layer decomposition is a separate workflow.
- Prompt limit: 32000 characters; required: true. Up to 10 reference images. Outputs: 4.
- Ratios: 1:1, 3:2, 2:3. Resolutions: 1K. Configured resolution fallback: 1K. Layer resolutions: not offered.
- Input MIME types: validated by the workspace. Input byte limit: validated by the workspace. Output format: png.

## Video generation and processing (34)
### MiniMax H3 Max Turbo (minimax-h3-max-turbo)
- Provider label: MiniMax; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 50000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480P, 768P, 1080P. Durations (seconds): {"min":5,"max":15,"step":1}. Ratios by mode: {"text":["21:9","16:9","4:3","1:1","3:4","9:16"],"image":[]}.
- Defaults: {"mode":"text","resolution":"480P","duration":5,"aspectRatio":"16:9","audio":true}. Audio supported: false; behavior: native. End image: true; seed: true.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### MiniMax H3 (minimax-h3)
- Provider label: MiniMax; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 7000; prompt supported: true; prompt required: true.
- Modes/input caps: reference: {"images":9,"videos":3,"audio":3,"total":12}; text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 2K. Durations (seconds): {"min":5,"max":15,"step":1}. Ratios by mode: {"reference":["adaptive","21:9","16:9","4:3","1:1","3:4","9:16"],"text":["21:9","16:9","4:3","1:1","3:4","9:16"],"image":[]}.
- Defaults: {"mode":"reference","resolution":"2K","duration":5,"aspectRatio":"adaptive","audio":false}. Audio supported: false; behavior: not specified. End image: true; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### H3 Max (minimax-h3-max)
- Provider label: MiniMax; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 20000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480P, 768P. Durations (seconds): {"min":5,"max":15,"step":1}. Ratios by mode: {"text":["21:9","16:9","4:3","1:1","3:4","9:16"],"image":[]}.
- Defaults: {"mode":"text","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":true}. Audio supported: false; behavior: native. End image: true; seed: true.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Seedance 2.5 (seedance-2.5)
- Provider label: Seedance; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 20000; prompt supported: true; prompt required: true.
- Modes/input caps: reference: {"images":30,"videos":10,"audio":10,"total":50}; text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480p, 720p. Durations (seconds): {"min":4,"max":30,"step":1}. Ratios by mode: {"reference":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"],"text":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"],"image":[]}.
- Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}. Audio supported: true; behavior: not specified. End image: true; seed: true.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Seedance 2.0 Fast (seedance-2.0-fast)
- Provider label: Seedance; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 20000; prompt supported: true; prompt required: true.
- Modes/input caps: reference: {"images":9,"videos":3,"audio":3,"total":12}; text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480p, 720p. Durations (seconds): {"min":4,"max":15,"step":1}. Ratios by mode: {"reference":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"],"text":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"],"image":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]}.
- Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}. Audio supported: true; behavior: not specified. End image: true; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Seedance 2.0 Pro (seedance-2.0-pro)
- Provider label: Seedance; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 20000; prompt supported: true; prompt required: true.
- Modes/input caps: reference: {"images":9,"videos":3,"audio":3,"total":12}; text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480p, 720p, 1080p, 4k. Durations (seconds): {"min":4,"max":15,"step":1}. Ratios by mode: {"reference":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"],"text":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"],"image":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]}.
- Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}. Audio supported: true; behavior: not specified. End image: true; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Seedance 2.0 Mini (seedance-2.0-mini)
- Provider label: Seedance; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 20000; prompt supported: true; prompt required: true.
- Modes/input caps: reference: {"images":9,"videos":3,"audio":3,"total":12}; text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480p, 720p. Durations (seconds): {"min":4,"max":15,"step":1}. Ratios by mode: {"reference":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"],"text":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"],"image":["adaptive","16:9","9:16","1:1","4:3","3:4","21:9"]}.
- Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}. Audio supported: true; behavior: not specified. End image: true; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Seedance 1.5 Pro (seedance-1.5-pro)
- Provider label: Seedance; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 20000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480p, 720p, 1080p. Durations (seconds): [4,8,12]. Ratios by mode: {"text":["16:9","9:16","1:1","4:3","3:4","21:9"],"image":["16:9","9:16","1:1","4:3","3:4","21:9"]}.
- Defaults: {"mode":"text","resolution":"480p","duration":4,"aspectRatio":"16:9","audio":false}. Audio supported: true; behavior: not specified. End image: true; seed: true.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Wan 2.7 (wan-2.7)
- Provider label: Wan; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 5000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 720p, 1080p. Durations (seconds): {"min":2,"max":15,"step":1}. Ratios by mode: {"text":["16:9","9:16","1:1","4:3","3:4"],"image":[]}.
- Defaults: {"mode":"text","resolution":"720p","duration":5,"aspectRatio":"16:9","audio":false}. Audio supported: false; behavior: not specified. End image: true; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Wan 2.6 (wan-2.6)
- Provider label: Wan; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 1500; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":1,"videos":0,"audio":0,"total":1}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 720p, 1080p. Durations (seconds): [5,10,15]. Ratios by mode: {"text":[],"image":[]}.
- Defaults: {"mode":"text","resolution":"720p","duration":5,"aspectRatio":"16:9","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Grok Imagine (grok-imagine)
- Provider label: Grok; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 5000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":1,"videos":0,"audio":0,"total":1}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 720p. Durations (seconds): [6,10]. Ratios by mode: {"text":["16:9","9:16","1:1","3:2","2:3"],"image":[]}.
- Defaults: {"mode":"text","resolution":"720p","duration":6,"aspectRatio":"16:9","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: false.
- Versions: none exposed. Styles: normal, fun, spicy. Output formats: model/workspace selected.

### Kling 3.0 (kling-3.0)
- Provider label: Kling; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 2500; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 720p. Durations (seconds): {"min":3,"max":15,"step":1}. Ratios by mode: {"text":["16:9","9:16","1:1"],"image":[]}.
- Defaults: {"mode":"text","resolution":"720p","duration":3,"aspectRatio":"16:9","audio":false}. Audio supported: true; behavior: not specified. End image: true; seed: false.
- Versions: standard, pro. Styles: none exposed. Output formats: model/workspace selected.

### PixVerse Extend (pixverse-extend)
- Provider label: PixVerse; workspace: https://gemini4carbon.app/ai-video-generator; operation: extend.
- Prompt limit: 2000; prompt supported: true; prompt required: true.
- Modes/input caps: reference: {"images":0,"videos":1,"audio":0,"total":12}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 360p, 540p, 720p, 1080p. Durations (seconds): [5]. Ratios by mode: {"reference":[]}.
- Defaults: {"mode":"reference","resolution":"720p","duration":5,"aspectRatio":"adaptive","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### ByteDance Video Upscaler (bytedance-video-upscaler)
- Provider label: ByteDance; workspace: https://gemini4carbon.app/ai-video-generator; operation: upscale.
- Prompt limit: 2000; prompt supported: true; prompt required: false.
- Modes/input caps: reference: {"images":0,"videos":1,"audio":0,"total":12}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 1080p, 2k, 4k. Durations (seconds): [5]. Ratios by mode: {"reference":[]}.
- Defaults: {"mode":"reference","resolution":"1080p","duration":5,"aspectRatio":"adaptive","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Bria Video Background Removal (bria-video-background)
- Provider label: Bria; workspace: https://gemini4carbon.app/ai-video-generator; operation: remove-background.
- Prompt limit: 2000; prompt supported: true; prompt required: false.
- Modes/input caps: reference: {"images":0,"videos":1,"audio":0,"total":12}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: source. Durations (seconds): [5]. Ratios by mode: {"reference":[]}.
- Defaults: {"mode":"reference","resolution":"source","duration":5,"aspectRatio":"adaptive","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### PixVerse Person Swap (pixverse-swap)
- Provider label: PixVerse; workspace: https://gemini4carbon.app/ai-video-generator; operation: swap.
- Prompt limit: 2000; prompt supported: true; prompt required: false.
- Modes/input caps: reference: {"images":1,"videos":1,"audio":0,"total":12}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 360p, 540p, 720p. Durations (seconds): [5]. Ratios by mode: {"reference":[]}.
- Defaults: {"mode":"reference","resolution":"720p","duration":5,"aspectRatio":"adaptive","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Sync Lip Sync 2 (sync-lipsync-2)
- Provider label: Sync; workspace: https://gemini4carbon.app/ai-video-generator; operation: lipsync.
- Prompt limit: 2000; prompt supported: true; prompt required: false.
- Modes/input caps: reference: {"images":0,"videos":1,"audio":1,"total":12}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: source. Durations (seconds): [5]. Ratios by mode: {"reference":[]}.
- Defaults: {"mode":"reference","resolution":"source","duration":5,"aspectRatio":"adaptive","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Sync Talking Photo (sync-talking-photo)
- Provider label: Sync; workspace: https://gemini4carbon.app/ai-video-generator; operation: talking-photo.
- Prompt limit: 2000; prompt supported: true; prompt required: false.
- Modes/input caps: reference: {"images":1,"videos":0,"audio":1,"total":12}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: source. Durations (seconds): [5]. Ratios by mode: {"reference":[]}.
- Defaults: {"mode":"reference","resolution":"source","duration":5,"aspectRatio":"adaptive","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Hailuo 02 Pro (hailuo-02-pro)
- Provider label: MiniMax; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 2000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 1080p. Durations (seconds): [6]. Ratios by mode: {"text":[],"image":[]}.
- Defaults: {"mode":"text","resolution":"1080p","duration":6,"aspectRatio":"16:9","audio":false}. Audio supported: false; behavior: not specified. End image: true; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Hailuo 02 Standard (hailuo-02-standard)
- Provider label: MiniMax; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 2000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 768p. Durations (seconds): [6,10]. Ratios by mode: {"text":[],"image":[]}.
- Defaults: {"mode":"text","resolution":"768p","duration":6,"aspectRatio":"16:9","audio":false}. Audio supported: false; behavior: not specified. End image: true; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Hailuo 2.3 Pro (hailuo-2.3-pro)
- Provider label: MiniMax; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 2000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":1,"videos":0,"audio":0,"total":1}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 1080p. Durations (seconds): [6]. Ratios by mode: {"text":[],"image":[]}.
- Defaults: {"mode":"text","resolution":"1080p","duration":6,"aspectRatio":"16:9","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Hailuo 2.3 Standard (hailuo-2.3-standard)
- Provider label: MiniMax; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 2000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":1,"videos":0,"audio":0,"total":1}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 768p. Durations (seconds): [6,10]. Ratios by mode: {"text":[],"image":[]}.
- Defaults: {"mode":"text","resolution":"768p","duration":6,"aspectRatio":"16:9","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Seedance 1.0 Pro (seedance-1.0-pro)
- Provider label: Seedance; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 2000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480p, 720p, 1080p. Durations (seconds): {"min":2,"max":12,"step":1}. Ratios by mode: {"text":["21:9","16:9","4:3","1:1","3:4","9:16"],"image":["auto","21:9","16:9","4:3","1:1","3:4","9:16"]}.
- Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":false}. Audio supported: false; behavior: not specified. End image: true; seed: true.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Wan 2.5 (wan-2.5)
- Provider label: Wan; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 1500; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":1,"total":1}; image: {"images":1,"videos":0,"audio":1,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480p, 720p, 1080p. Durations (seconds): [5,10]. Ratios by mode: {"text":["16:9","9:16","1:1"],"image":[]}.
- Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":true}. Audio supported: false; behavior: native. End image: false; seed: true.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Kling 2.6 Pro (kling-2.6-pro)
- Provider label: Kling; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 2500; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 1080p. Durations (seconds): [5,10]. Ratios by mode: {"text":["16:9","9:16","1:1"],"image":[]}.
- Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":true}. Audio supported: true; behavior: not specified. End image: true; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Veo 3.1 (veo-3.1)
- Provider label: Google; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 20000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":1,"videos":0,"audio":0,"total":1}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 720p, 1080p, 4k. Durations (seconds): [4,6,8]. Ratios by mode: {"text":["16:9","9:16"],"image":["auto","16:9","9:16"]}.
- Defaults: {"mode":"text","resolution":"720p","duration":8,"aspectRatio":"16:9","audio":true}. Audio supported: true; behavior: not specified. End image: false; seed: true.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### HappyHorse 1.0 (happyhorse-1.0)
- Provider label: Alibaba; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 2500; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":1,"videos":0,"audio":0,"total":1}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 720p, 1080p. Durations (seconds): {"min":3,"max":15,"step":1}. Ratios by mode: {"text":["16:9","9:16","1:1","4:3","3:4"],"image":[]}.
- Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: true.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### HappyHorse 1.1 (happyhorse-1.1)
- Provider label: Alibaba; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 2500; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":1,"videos":0,"audio":0,"total":1}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 720p, 1080p. Durations (seconds): {"min":3,"max":15,"step":1}. Ratios by mode: {"text":["16:9","9:16","1:1","4:3","3:4","21:9","9:21","5:4","4:5"],"image":[]}.
- Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: true.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Grok Imagine 1.5 (grok-imagine-1.5)
- Provider label: Grok; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 4096; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":1,"videos":0,"audio":0,"total":1}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480p, 720p, 1080p. Durations (seconds): {"min":1,"max":15,"step":1}. Ratios by mode: {"text":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"image":[]}.
- Defaults: {"mode":"text","resolution":"720p","duration":6,"aspectRatio":"16:9","audio":true}. Audio supported: false; behavior: native. End image: false; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### H3 Max Styles (h3-max-styles)
- Provider label: MiniMax; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 49868; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":1,"videos":0,"audio":0,"total":1}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 768P. Durations (seconds): {"min":5,"max":15,"step":1}. Ratios by mode: {"text":["21:9","16:9","4:3","1:1","3:4","9:16"],"image":[]}.
- Defaults: {"mode":"text","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":true}. Audio supported: false; behavior: native. End image: false; seed: true.
- Versions: none exposed. Styles: hand-drawn, vhs, retro-toon-70s, low-poly, 16bit-pixel. Output formats: model/workspace selected.

### H3 Max Camera Control (h3-max-camera-control)
- Provider label: MiniMax; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 50000; prompt supported: true; prompt required: false.
- Modes/input caps: image: {"images":1,"videos":0,"audio":0,"total":1}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480P, 768P, 1080P. Durations (seconds): {"min":3,"max":15,"step":1}. Ratios by mode: {"image":[]}.
- Defaults: {"mode":"image","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":false}. Audio supported: false; behavior: not specified. End image: false; seed: true.
- Versions: none exposed. Styles: orbit-right, orbit-left, push-in, pull-back, crane-up. Output formats: model/workspace selected.

### H3 Max Lip Sync (h3-max-lip-sync)
- Provider label: MiniMax; workspace: https://gemini4carbon.app/ai-video-generator; operation: h3-lipsync.
- Prompt limit: 2000; prompt supported: true; prompt required: false.
- Modes/input caps: reference: {"images":1,"videos":0,"audio":1,"total":12}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480P, 768P, 1080P, 2K. Durations (seconds): [5]. Ratios by mode: {"reference":[]}.
- Defaults: {"mode":"reference","resolution":"768P","duration":5,"aspectRatio":"adaptive","audio":true}. Audio supported: false; behavior: native. End image: false; seed: true.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### Gemini Omni (gemini-omni)
- Provider label: Google; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 20000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":1,"videos":0,"audio":0,"total":1}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 720p. Durations (seconds): {"min":3,"max":10,"step":1}. Ratios by mode: {"text":["16:9","9:16"],"image":["16:9","9:16"]}.
- Defaults: {"mode":"text","resolution":"720p","duration":8,"aspectRatio":"16:9","audio":true}. Audio supported: false; behavior: native. End image: false; seed: false.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

### H3 LoRA (h3-lora)
- Provider label: MiniMax; workspace: https://gemini4carbon.app/ai-video-generator; operation: generation.
- Prompt limit: 50000; prompt supported: true; prompt required: true.
- Modes/input caps: text: {"images":0,"videos":0,"audio":0,"total":0}; image: {"images":2,"videos":0,"audio":0,"total":2}. Image mode needs a starting image; reference mode requires suitable reference material.
- Resolutions: 480P, 768P, 2K, 4K. Durations (seconds): {"min":5,"max":15,"step":1}. Ratios by mode: {"text":["21:9","16:9","4:3","1:1","3:4","9:16"],"image":[]}.
- Defaults: {"mode":"text","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":true}. Audio supported: false; behavior: native. End image: true; seed: true.
- Versions: none exposed. Styles: none exposed. Output formats: model/workspace selected.

## Text, reference interpretation and structured motion
- Gemini 4 Carbon: COMING SOON. Material analysis and model-generated motion are disabled. The local Motion template uses a closed two-dimensional scene vocabulary and browser rendering. It is not a model output.
- Opus 5.5 · Motion Graphics: anthropic/claude-opus-5.5; public workflow ID claude-opus-5-5-motion; https://gemini4carbon.app/opus-5-5-video-generator. Text instructions, up to 4 approved image elements and an optional explicitly confirmed public-web brief feed structured editable scenes. Durations: [10,15,20,30]; ratios: ["16:9","9:16","1:1"]; resolutions: 720p, 1080p; defaults: {"mode":"text","resolution":"720p","duration":20,"aspectRatio":"16:9","audio":false}. Styles: sketch, motion. Browser MP4 export has no audio. Visible text uses the renderer's standard English glyph set; CJK/emoji output is not guaranteed.

## Creative audio, 3D and character operations
- ACE-Step · Fal (ace_step): text prompt: true; instrumental toggle: true; 60-second music; FilmCraft/audio studio.
- Hunyuan3D V3 · Fal (hunyuan_3d_3): text support: true; one image support: true; outputs: normal, low_poly, geometry; polygons: triangle, quad; PBR: true; multi-view: false. Editable scene/mesh work continues in the creative studio.
- FLUX Pro masked editing: owned source image plus same-size mask, prompt, maximum 4 MP; one PNG.
- Video background replacement: MP4/MOV input, 3–15 seconds, at most 60 MB; text or a reference environment image; fixed 720p, original audio.
- Character training: 4–20 distinct owned PNG/JPEG/WebP images, up to 10 MB and 16 MP each, 15 MB aggregate, 1000 steps. Character-image generation requires a ready owned character; one 1024×1024 PNG. These are separate operations, not extra ordinary generator models.

## Marble spatial worlds
World Labs integration is configured. Public engine ID: worldlabs/marble; models: marble-1.0-draft, marble-1.1, marble-1.1-plus. Text up to 4000 characters or an owned reference image; optional 360° panorama flag requires an image. Default model: marble-1.0-draft; panorama off. The workflow offers spatial-world previews and available splat/mesh assets; output formats depend on the completed provider result. Manual scene arrangement remains separate from credit-based world generation.

## Browser and office workspaces
FilmCraft, PhotoCraft, PdfCraft, WordCraft, GridCraft and DeckCraft provide browser editing and private signed-in saves/exports. Browser image tools are indexed at https://gemini4carbon.app/llms.txt. A browser editor or tool-page name is not an additional AI model. Import/export compatibility depends on the selected editor and input file. No document grants access to private files or changes login/download permissions.