About WAN 2.7 - Reference to Video
WAN 2.7 reference-to-video generates video from one or more reference images and reference videos with optional first-frame joint control, supporting single-character performances, multi-character interactions, and multi-shot narration. Up to 5 reference images and reference videos combined. Output up to 1080P at 2-15s (2-10s when a reference video is included).
Ready to build with WAN 2.7 - Reference to Video?
Try WAN 2.7 - Reference 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-v2-7-reference-to-video",
"prompt": "@Image1 walks through a beautiful garden in the style of @Image2, cinematic lighting.",
"aspect_ratio": "16:9",
"resolution": "1080P",
"duration": 5,
"prompt_extend": true,
"watermark": false
}'Request parameters
Every field WAN 2.7 - Reference to Video accepts in the request body. See the API reference for response formats.
POST
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Text prompt for the video. Chinese and English, up to 5,000 characters. Use @Image1, @Image2 and @Video1, @Video2 to reference the inputs in order. |
input_images | array<object>nullable | No | — | Reference images for character, object, or scene appearance, in @Image order. Up to 5 images and videos combined. JPEG, PNG, BMP, or WEBP up to 20 MB each. |
input_videos | array<object>nullable | No | — | Reference videos for appearance, motion, and voice, in @Video order. Up to 5 images and videos combined. MP4 or MOV, 1 to 30 seconds, up to 100 MB each. |
input_image | stringuri | No | — | Optional first frame. The output takes its aspect ratio from this image. |
aspect_ratio | string | No | "16:9" | 16:99:161:14:33:4 |
resolution | string | No | "1080P" | 720P1080P |
duration | integer | No | 5 | Range: 2 – 15 |
negative_prompt | string | No | — | What to keep out of the video. Up to 500 characters. |
prompt_extend | boolean | No | true | Let the model expand short prompts. Adds processing time. |
watermark | boolean | No | false | Add an AI-generated watermark in the bottom-right corner. |
seed | integer | No | — | Seed for reproducible generation. Range: 0 – 2147483647 |