About WAN 2.6 - Video to Video
WAN 2.6 - Video to Video is a diffusion model designed for reference-based video generation with character and identity consistency. It excels in generating cinematic videos from reference footage while maintaining stable character appearance, voice characteristics, and motion style across multiple shots.
Some noteworthy use cases of WAN 2.6 - Video to Video include character-driven storytelling, brand-consistent video creation, and multi-character dialogue scenes with synchronized audio.
Ready to build with WAN 2.6 - Video to Video?
Try WAN 2.6 - Video to Video in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "wan-v2-6-reference-to-video",
"prompt": "The character from @Video1 walking slowly down a road, cinematic.",
"input_videos": [
"https://hub.oxen.ai/api/repos/ox/Oxen-AI-Assets/file/main/images/winter_summer_ox.mp4"
]
}'Request parameters
Every field WAN 2.6 - Video to Video accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Text description of the video to generate. Use @Video1, @Video2, etc. to reference the input videos. |
input_videos | array<string>nullable | No | — | Reference videos that guide the generated video. Reference them in the prompt as @Video1, @Video2, etc. |