# Kling4 configured models and workflows

Workspaces: https://kling4.tools/ai-video-generator and https://kling4.tools/ai-image-generator
Prices and settlement: https://kling4.tools/pricing.md

This catalog follows the selectable studio definitions and their input-limit helper. It does not guarantee provider uptime, output quality or capabilities outside the configured modes. A tool-page brand name is not an additional engine or official affiliation. Native Kling 4.0 is not connected in this deployment; https://kling4.tools/kling-4-0 presents sourced examples and explicitly labeled compatible engines.

## Video generation and processing
### MiniMax H3 Max Turbo
- Public model ID: minimax-h3-max-turbo; provider label: MiniMax; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 50000 characters.
- Resolutions: 480P, 768P, 1080P.
- Duration options (seconds): 5–15 in steps of 1.
- Ratios by mode: text: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; image: inferred from source / workspace validation.
- Audio: native audio; end frame: true; seed: true.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"480P","duration":5,"aspectRatio":"16:9","audio":true}.

### MiniMax H3
- Public model ID: minimax-h3; provider label: MiniMax; operation: generation.
- Modes: reference, text, image.
- Input limits by mode: reference: at most 9 images, 3 videos, 3 audio, 12 combined; text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 7000 characters.
- Resolutions: 2K.
- Duration options (seconds): 5–15 in steps of 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: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: true; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"2K","duration":5,"aspectRatio":"adaptive","audio":false}.

### H3 Max
- Public model ID: minimax-h3-max; provider label: MiniMax; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 20000 characters.
- Resolutions: 480P, 768P.
- Duration options (seconds): 5–15 in steps of 1.
- Ratios by mode: text: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; image: inferred from source / workspace validation.
- Audio: native audio; end frame: true; seed: true.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":true}.

### Seedance 2.5
- Public model ID: seedance-2.5; provider label: Seedance; operation: generation.
- Modes: reference, text, image.
- Input limits by mode: reference: at most 30 images, 10 videos, 10 audio, 50 combined; text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 20000 characters.
- Resolutions: 480p, 720p.
- Duration options (seconds): 4–30 in steps of 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: inferred from source / workspace validation.
- Audio: optional audio switch; end frame: true; seed: true.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}.

### Seedance 2.0 Fast
- Public model ID: seedance-2.0-fast; provider label: Seedance; operation: generation.
- Modes: reference, text, image.
- Input limits by mode: reference: at most 9 images, 3 videos, 3 audio, 12 combined; text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 20000 characters.
- Resolutions: 480p, 720p.
- Duration options (seconds): 4–15 in steps of 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.
- Audio: optional audio switch; end frame: true; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}.

### Seedance 2.0 Pro
- Public model ID: seedance-2.0-pro; provider label: Seedance; operation: generation.
- Modes: reference, text, image.
- Input limits by mode: reference: at most 9 images, 3 videos, 3 audio, 12 combined; text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 20000 characters.
- Resolutions: 480p, 720p, 1080p, 4k.
- Duration options (seconds): 4–15 in steps of 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.
- Audio: optional audio switch; end frame: true; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}.

### Seedance 2.0 Mini
- Public model ID: seedance-2.0-mini; provider label: Seedance; operation: generation.
- Modes: reference, text, image.
- Input limits by mode: reference: at most 9 images, 3 videos, 3 audio, 12 combined; text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 20000 characters.
- Resolutions: 480p, 720p.
- Duration options (seconds): 4–15 in steps of 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.
- Audio: optional audio switch; end frame: true; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"480p","duration":4,"aspectRatio":"adaptive","audio":true}.

### Seedance 1.5 Pro
- Public model ID: seedance-1.5-pro; provider label: Seedance; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 20000 characters.
- Resolutions: 480p, 720p, 1080p.
- Duration options (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.
- Audio: optional audio switch; end frame: true; seed: true.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"480p","duration":4,"aspectRatio":"16:9","audio":false}.

### Wan 2.7
- Public model ID: wan-2.7; provider label: Wan; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 5000 characters.
- Resolutions: 720p, 1080p.
- Duration options (seconds): 2–15 in steps of 1.
- Ratios by mode: text: 16:9, 9:16, 1:1, 4:3, 3:4; image: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: true; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"720p","duration":5,"aspectRatio":"16:9","audio":false}.

### Wan 2.6
- Public model ID: wan-2.6; provider label: Wan; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 1 images, 0 videos, 0 audio, 1 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 1500 characters.
- Resolutions: 720p, 1080p.
- Duration options (seconds): 5, 10, 15.
- Ratios by mode: text: inferred from source / workspace validation; image: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"720p","duration":5,"aspectRatio":"16:9","audio":false}.

### Grok Imagine
- Public model ID: grok-imagine; provider label: Grok; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 1 images, 0 videos, 0 audio, 1 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 5000 characters.
- Resolutions: 720p.
- Duration options (seconds): 6, 10.
- Ratios by mode: text: 16:9, 9:16, 1:1, 3:2, 2:3; image: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: false.
- Versions: no version selector; styles: normal, fun, spicy; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"720p","duration":6,"aspectRatio":"16:9","audio":false}.

### Kling 3.0
- Public model ID: kling-3.0; provider label: Kling; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 2500 characters.
- Resolutions: 720p.
- Duration options (seconds): 3–15 in steps of 1.
- Ratios by mode: text: 16:9, 9:16, 1:1; image: inferred from source / workspace validation.
- Audio: optional audio switch; end frame: true; seed: false.
- Versions: standard, pro; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"720p","duration":3,"aspectRatio":"16:9","audio":false}.

### PixVerse Extend
- Public model ID: pixverse-extend; provider label: PixVerse; operation: extend.
- Modes: reference.
- Input limits by mode: reference: at most 0 images, 1 videos, 0 audio, 12 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 2000 characters.
- Resolutions: 360p, 540p, 720p, 1080p.
- Duration options (seconds): 5.
- Ratios by mode: reference: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"720p","duration":5,"aspectRatio":"adaptive","audio":false}.
- Operation input requirements: Upload one MP4/MOV video under 30 seconds. Each extension adds 5 seconds; credits depend on resolution.

### ByteDance Video Upscaler
- Public model ID: bytedance-video-upscaler; provider label: ByteDance; operation: upscale.
- Modes: reference.
- Input limits by mode: reference: at most 0 images, 1 videos, 0 audio, 12 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: optional, maximum 2000 characters.
- Resolutions: 1080p, 2k, 4k.
- Duration options (seconds): 5.
- Ratios by mode: reference: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"1080p","duration":5,"aspectRatio":"adaptive","audio":false}.
- Operation input requirements: Upload one MP4/MOV video under 30 seconds. Credits depend on source duration and target resolution.

### Bria Video Background Removal
- Public model ID: bria-video-background; provider label: Bria; operation: remove-background.
- Modes: reference.
- Input limits by mode: reference: at most 0 images, 1 videos, 0 audio, 12 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: optional, maximum 2000 characters.
- Resolutions: source.
- Duration options (seconds): 5.
- Ratios by mode: reference: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"source","duration":5,"aspectRatio":"adaptive","audio":false}.
- Operation input requirements: Upload one MP4/MOV video under 30 seconds and below 4000 × 4000 pixels. Download transparent WebM with original audio.

### PixVerse Person Swap
- Public model ID: pixverse-swap; provider label: PixVerse; operation: swap.
- Modes: reference.
- Input limits by mode: reference: at most 1 images, 1 videos, 0 audio, 12 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: optional, maximum 2000 characters.
- Resolutions: 360p, 540p, 720p.
- Duration options (seconds): 5.
- Ratios by mode: reference: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"720p","duration":5,"aspectRatio":"adaptive","audio":false}.
- Operation input requirements: Upload one portrait image and one MP4/MOV video up to 8 seconds. Videos longer than 5 seconds use the second price tier.

### Sync Lip Sync 2
- Public model ID: sync-lipsync-2; provider label: Sync; operation: lipsync.
- Modes: reference.
- Input limits by mode: reference: at most 0 images, 1 videos, 1 audio, 12 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: optional, maximum 2000 characters.
- Resolutions: source.
- Duration options (seconds): 5.
- Ratios by mode: reference: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"source","duration":5,"aspectRatio":"adaptive","audio":false}.
- Operation input requirements: Upload one MP4/MOV video and one WAV/M4A audio file, each under 30 seconds. Credits follow audio duration.

### Sync Talking Photo
- Public model ID: sync-talking-photo; provider label: Sync; operation: talking-photo.
- Modes: reference.
- Input limits by mode: reference: at most 1 images, 0 videos, 1 audio, 12 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: optional, maximum 2000 characters.
- Resolutions: source.
- Duration options (seconds): 5.
- Ratios by mode: reference: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"source","duration":5,"aspectRatio":"adaptive","audio":false}.
- Operation input requirements: Upload one portrait image and one WAV/M4A audio file under 30 seconds. Credits follow audio duration.

### Hailuo 02 Pro
- Public model ID: hailuo-02-pro; provider label: MiniMax; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 2000 characters.
- Resolutions: 1080p.
- Duration options (seconds): 6.
- Ratios by mode: text: inferred from source / workspace validation; image: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: true; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"1080p","duration":6,"aspectRatio":"16:9","audio":false}.

### Hailuo 02 Standard
- Public model ID: hailuo-02-standard; provider label: MiniMax; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 2000 characters.
- Resolutions: 768p.
- Duration options (seconds): 6, 10.
- Ratios by mode: text: inferred from source / workspace validation; image: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: true; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"768p","duration":6,"aspectRatio":"16:9","audio":false}.

### Hailuo 2.3 Pro
- Public model ID: hailuo-2.3-pro; provider label: MiniMax; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 1 images, 0 videos, 0 audio, 1 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 2000 characters.
- Resolutions: 1080p.
- Duration options (seconds): 6.
- Ratios by mode: text: inferred from source / workspace validation; image: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"1080p","duration":6,"aspectRatio":"16:9","audio":false}.

### Hailuo 2.3 Standard
- Public model ID: hailuo-2.3-standard; provider label: MiniMax; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 1 images, 0 videos, 0 audio, 1 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 2000 characters.
- Resolutions: 768p.
- Duration options (seconds): 6, 10.
- Ratios by mode: text: inferred from source / workspace validation; image: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"768p","duration":6,"aspectRatio":"16:9","audio":false}.

### Seedance 1.0 Pro
- Public model ID: seedance-1.0-pro; provider label: Seedance; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 2000 characters.
- Resolutions: 480p, 720p, 1080p.
- Duration options (seconds): 2–12 in steps of 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.
- Audio: no optional generated-audio switch; end frame: true; seed: true.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":false}.

### Wan 2.5
- Public model ID: wan-2.5; provider label: Wan; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 1 audio, 1 combined; image: at most 1 images, 0 videos, 1 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 1500 characters.
- Resolutions: 480p, 720p, 1080p.
- Duration options (seconds): 5, 10.
- Ratios by mode: text: 16:9, 9:16, 1:1; image: inferred from source / workspace validation.
- Audio: native audio; end frame: false; seed: true.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":true}.

### Kling 2.6 Pro
- Public model ID: kling-2.6-pro; provider label: Kling; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 2500 characters.
- Resolutions: 1080p.
- Duration options (seconds): 5, 10.
- Ratios by mode: text: 16:9, 9:16, 1:1; image: inferred from source / workspace validation.
- Audio: optional audio switch; end frame: true; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":true}.

### Veo 3.1
- Public model ID: veo-3.1; provider label: Google; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 1 images, 0 videos, 0 audio, 1 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 20000 characters.
- Resolutions: 720p, 1080p, 4k.
- Duration options (seconds): 4, 6, 8.
- Ratios by mode: text: 16:9, 9:16; image: auto, 16:9, 9:16.
- Audio: optional audio switch; end frame: false; seed: true.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"720p","duration":8,"aspectRatio":"16:9","audio":true}.

### HappyHorse 1.0
- Public model ID: happyhorse-1.0; provider label: Alibaba; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 1 images, 0 videos, 0 audio, 1 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 2500 characters.
- Resolutions: 720p, 1080p.
- Duration options (seconds): 3–15 in steps of 1.
- Ratios by mode: text: 16:9, 9:16, 1:1, 4:3, 3:4; image: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: true.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":false}.

### HappyHorse 1.1
- Public model ID: happyhorse-1.1; provider label: Alibaba; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 1 images, 0 videos, 0 audio, 1 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 2500 characters.
- Resolutions: 720p, 1080p.
- Duration options (seconds): 3–15 in steps of 1.
- Ratios by mode: text: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21, 5:4, 4:5; image: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: true.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"1080p","duration":5,"aspectRatio":"16:9","audio":false}.

### Grok Imagine 1.5
- Public model ID: grok-imagine-1.5; provider label: Grok; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 1 images, 0 videos, 0 audio, 1 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 4096 characters.
- Resolutions: 480p, 720p, 1080p.
- Duration options (seconds): 1–15 in steps of 1.
- Ratios by mode: text: 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16; image: inferred from source / workspace validation.
- Audio: native audio; end frame: false; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"720p","duration":6,"aspectRatio":"16:9","audio":true}.

### H3 Max Styles
- Public model ID: h3-max-styles; provider label: MiniMax; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 1 images, 0 videos, 0 audio, 1 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 49868 characters.
- Resolutions: 768P.
- Duration options (seconds): 5–15 in steps of 1.
- Ratios by mode: text: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; image: inferred from source / workspace validation.
- Audio: native audio; end frame: false; seed: true.
- Versions: no version selector; styles: hand-drawn, vhs, retro-toon-70s, low-poly, 16bit-pixel; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":true}.

### H3 Max Camera Control
- Public model ID: h3-max-camera-control; provider label: MiniMax; operation: generation.
- Modes: image.
- Input limits by mode: image: at most 1 images, 0 videos, 0 audio, 1 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: optional, maximum 50000 characters.
- Resolutions: 480P, 768P, 1080P.
- Duration options (seconds): 3–15 in steps of 1.
- Ratios by mode: image: inferred from source / workspace validation.
- Audio: no optional generated-audio switch; end frame: false; seed: true.
- Versions: no version selector; styles: orbit-right, orbit-left, push-in, pull-back, crane-up; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"image","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":false}.

### H3 Max Lip Sync
- Public model ID: h3-max-lip-sync; provider label: MiniMax; operation: h3-lipsync.
- Modes: reference.
- Input limits by mode: reference: at most 1 images, 0 videos, 1 audio, 12 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: optional, maximum 2000 characters.
- Resolutions: 480P, 768P, 1080P, 2K.
- Duration options (seconds): 5.
- Ratios by mode: reference: inferred from source / workspace validation.
- Audio: native audio; end frame: false; seed: true.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"reference","resolution":"768P","duration":5,"aspectRatio":"adaptive","audio":true}.
- Operation input requirements: Upload one portrait image and WAV/M4A audio lasting at least 5 seconds and under 30 seconds. Audio beyond 14.8 seconds is clipped. Credits follow the clipped audio duration.

### Gemini Omni
- Public model ID: gemini-omni; provider label: Google; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 1 images, 0 videos, 0 audio, 1 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 20000 characters.
- Resolutions: 720p.
- Duration options (seconds): 3–10 in steps of 1.
- Ratios by mode: text: 16:9, 9:16; image: 16:9, 9:16.
- Audio: native audio; end frame: false; seed: false.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"720p","duration":8,"aspectRatio":"16:9","audio":true}.

### H3 LoRA
- Public model ID: h3-lora; provider label: MiniMax; operation: generation.
- Modes: text, image.
- Input limits by mode: text: at most 0 images, 0 videos, 0 audio, 0 combined; image: at most 2 images, 0 videos, 0 audio, 2 combined. Required inputs depend on the mode; a maximum is not a minimum.
- Prompt: required, maximum 50000 characters.
- Resolutions: 480P, 768P, 2K, 4K.
- Duration options (seconds): 5–15 in steps of 1.
- Ratios by mode: text: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16; image: inferred from source / workspace validation.
- Audio: native audio; end frame: true; seed: true.
- Versions: no version selector; styles: no style selector; web search: false; return last frame: false; output formats: model-defined video.
- Defaults: {"mode":"text","resolution":"768P","duration":5,"aspectRatio":"16:9","audio":true}.


## Image generation, editing and decomposition
### Seedream 5.0 Pro
- Public model ID: seedream-5-pro; provider label: Seedream.
- Modes: layer-decomposition, text, image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 5000 characters; prompt validation applies.
- Image reference maximum: 10. MIME types: use the workspace upload control; configured per-image byte limit: 31457280.
- Resolutions: 1K, 2K; explicit default resolution: 2K.
- Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3.
- Multiple outputs: true; maximum 6 in the workspace. Output format: model-defined.
- Layer resolutions: auto, 1K, 1.5K, 2K; layer input types: image/jpeg, image/png, image/webp, image/bmp, image/tiff, image/gif.

### GPT Image 2.5 Flare
- Public model ID: gpt-image-2.5-flare; provider label: OpenAI.
- Modes: text, image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 32000 characters; prompt validation applies.
- Image reference maximum: 16. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: 1K, 2K, 4K; explicit default resolution: 1K.
- 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.
- Multiple outputs: true; maximum 10 in the workspace. Output format: model-defined.
- Quality: auto, low, medium, high, xhigh, max (default high); background: auto, transparent, opaque (default auto); formats: png, jpeg, webp (default png); output count default 1, maximum 10.
- Custom dimensions: multiples of 16, longest edge <= 3840, total pixels 655360–8294400, aspect ratio at most 3:1; edit mask optional in image mode.

### GPT Image 2.5 Sunburst
- Public model ID: gpt-image-2.5-sunburst; provider label: OpenAI.
- Modes: text, image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 32000 characters; prompt validation applies.
- Image reference maximum: 16. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: 1K, 2K, 4K; explicit default resolution: 1K.
- 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.
- Multiple outputs: true; maximum 10 in the workspace. Output format: model-defined.
- Quality: auto, low, medium, high, xhigh, max (default high); background: auto, transparent, opaque (default auto); formats: png, jpeg, webp (default png); output count default 1, maximum 10.
- Custom dimensions: multiples of 16, longest edge <= 3840, total pixels 655360–8294400, aspect ratio at most 3:1; edit mask optional in image mode.

### GPT Image 2
- Public model ID: gpt-image-2; provider label: OpenAI.
- Modes: text, image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 20000 characters; prompt validation applies.
- Image reference maximum: 16. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: 1K, 2K, 4K; explicit default resolution: 1K.
- 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.
- Multiple outputs: true; maximum 4 in the workspace. Output format: model-defined.

### Nano Banana 2
- Public model ID: nano-banana-2; provider label: Nano Banana.
- Modes: text, image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 20000 characters; prompt validation applies.
- Image reference maximum: 14. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: 1K, 2K, 4K; explicit default resolution: chosen 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.
- Multiple outputs: true; maximum 4 in the workspace. Output format: model-defined.

### Nano Banana Pro
- Public model ID: nano-banana-pro; provider label: Nano Banana.
- Modes: text, image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 20000 characters; prompt validation applies.
- Image reference maximum: 14. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: 1K, 2K, 4K; explicit default resolution: chosen by the workspace.
- Ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9.
- Multiple outputs: true; maximum 4 in the workspace. Output format: model-defined.

### Nano Banana
- Public model ID: nano-banana; provider label: Nano Banana.
- Modes: text, image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 20000 characters; prompt validation applies.
- Image reference maximum: 10. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: model-defined; explicit default resolution: chosen by the workspace.
- Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Multiple outputs: true; maximum 4 in the workspace. Output format: model-defined.

### Seedream 5 Lite
- Public model ID: seedream-5-lite; provider label: Seedream.
- Modes: text, image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 5000 characters; prompt validation applies.
- Image reference maximum: 10. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: 2K, 3K; explicit default resolution: chosen by the workspace.
- Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Multiple outputs: true; maximum 4 in the workspace. Output format: model-defined.

### Seedream 4.5
- Public model ID: seedream-4-5; provider label: Seedream.
- Modes: text, image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 3000 characters; prompt validation applies.
- Image reference maximum: 10. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: 2K, 4K; explicit default resolution: chosen by the workspace.
- Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Multiple outputs: true; maximum 4 in the workspace. Output format: model-defined.

### Seedream V4
- Public model ID: seedream-v4; provider label: Seedream.
- Modes: text, image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 5000 characters; prompt validation applies.
- Image reference maximum: 10. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: 1K, 2K, 4K; explicit default resolution: chosen by the workspace.
- Ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9.
- Multiple outputs: true; maximum 4 in the workspace. Output format: model-defined.

### Bria RMBG 2.0
- Public model ID: bria-background-remove; provider label: Bria.
- Modes: image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 0 characters; no mandatory prompt.
- Image reference maximum: 1. MIME types: image/jpeg, image/png, image/webp; configured per-image byte limit: 31457280.
- Resolutions: original; explicit default resolution: original.
- Ratios: auto.
- Multiple outputs: false; maximum 1 in the workspace. Output format: png.

### Illusion Diffusion
- Public model ID: illusion-diffusion; provider label: Illusion Diffusion.
- Modes: image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 2000 characters; prompt validation applies.
- Image reference maximum: 1. MIME types: image/jpeg, image/png, image/webp; configured per-image byte limit: 10485760.
- Resolutions: 1K; explicit default resolution: 1K.
- Ratios: 1:1.
- Multiple outputs: false; maximum 1 in the workspace. Output format: png.

### Z-Image
- Public model ID: z-image; provider label: Z-Image.
- Modes: text. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 1000 characters; prompt validation applies.
- Image reference maximum: 0. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: model-defined; explicit default resolution: chosen by the workspace.
- Ratios: 1:1, 4:3, 3:4, 16:9, 9:16.
- Multiple outputs: false; maximum 1 in the workspace. Output format: model-defined.

### Nano Banana 2 Lite
- Public model ID: nano-banana-2-lite; provider label: Nano Banana.
- Modes: text. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 50000 characters; prompt validation applies.
- Image reference maximum: 0. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: 1K; explicit default resolution: 1K.
- 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.
- Multiple outputs: true; maximum 4 in the workspace. Output format: png.

### GPT Image 1.5
- Public model ID: gpt-image-1.5; provider label: OpenAI.
- Modes: text, image. Text uses a prompt; image editing requires reference images. Layer decomposition is listed separately below.
- Prompt limit: 32000 characters; prompt validation applies.
- Image reference maximum: 10. MIME types: use the workspace upload control; configured per-image byte limit: workspace validation applies.
- Resolutions: 1K; explicit default resolution: 1K.
- Ratios: 1:1, 3:2, 2:3.
- Multiple outputs: true; maximum 4 in the workspace. Output format: png.


## Separate workflows
### Opus 5.5 · Motion Graphics
- Public engine ID: claude-opus-5-5-motion; tool: https://kling4.tools/opus-5-5-video-generator.
- Prompt limit 6000; up to 4 reference images; durations 10, 15, 20, 30 seconds; resolutions 720p, 1080p; ratios 16:9, 9:16, 1:1; styles sketch, motion.
- Defaults: {"mode":"text","resolution":"720p","duration":20,"aspectRatio":"16:9","audio":false}. Editable motion-graphics scene with a controlled renderer and silent MP4 export; no generated speech/audio. Quoted whole-operation reservation ceiling 92 credits.

### Humanize AI
- Engine humanize-text-v1; language model google/gemini-2.5-flash; tool https://kling4.tools/humanize-ai.
- Rewrite original text in its original language, up to 12000 characters; tones natural, friendly, professional. No detector-evasion or factual-accuracy guarantee. Uses operation reservation and receipt settlement.

### Prompt Seen
- Engine prompt-seen-vision-v1; vision model google/gemini-2.5-flash; tool https://kling4.tools/prompt-seen.
- One uploaded image is normalized to the workflow's supported JPEG input, with guidance up to 1000 characters; styles detailed, concise, cinematic. Returns an English creative prompt, not proof of the original prompt; reservation 2 credits.

### Seedream layer decomposition
- The layer-decomposition mode on Seedream 5.0 Pro returns editable image layers, not a flat multi-image generation request. Reserve up to 16 outputs and settle actual layers; consult pricing.md.

The catalog exposes public model IDs and options only. Provider endpoints, credentials, payment price IDs, user files and signed URLs are intentionally not published.