S2V-01 generates videos with highly consistent character identity across frames using a single reference photo, at significantly lower computational cost.
Documentation Index
Fetch the complete documentation index at: https://docs.modellix.ai/llms.txt
Use this file to discover all available pages before exploring further.
Authorizations
API Key authentication. Format: Bearer YOUR_API_KEY.
Body
Subject reference image URLs. Supports publicly accessible HTTP/HTTPS URLs or Base64 Data URLs. Used to maintain the appearance characteristics of the reference subject in the generated video.
1 - 10 elementsImage URL or Base64 Data URL. Image format: JPG/JPEG/PNG/WebP, <20MB, recommended short side >300px.
1["https://example.com/character.jpg"]
Video content description (optional). Describe the subject's actions, scenes, etc. Supports Chinese and English. Max 2000 characters.
1 - 2000"A girl runs toward the camera and winks with a smile."
Whether to automatically optimize the prompt. Default is true. Set to false for more precise control.
true