Krea Wan 14B
/v1/runKrea Wan Video To Video is krea's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.
Request body
Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.
Model identifier. Set to krea/krea-wan/video-to-video.
Default: krea/krea-wan/video-to-video
Prompt for the video-to-video generation.
URL of the input video. Currently, only outputs of 16:9 aspect ratio and 480p resolution are supported. Video duration should be less than 1000 frames at 16fps, and output frames will be 6 plus a multiple of 12, for example 18, 30, 42, etc.
Denoising strength for the video-to-video generation. 0.0 preserves the original, 1.0 completely remakes the video.
Range: 0.01 to 1
Default: 0.85
Seed for the video-to-video generation.
Response Schema
The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.
Error message if the task failed. Empty on success.
Unique identifier for the generation task.
Model ID used for the prediction.
Array of generated content. Empty when status is not completed.
Status of the task: pending, running, completed, failed, or timeout.
Allowed values: pending, running, completed, failed, timeout
Model capabilities
Capabilities declared by the model registry.
Default: video-to-video
Execution mode declared by the model registry.
Default: async

