Vidu 2 Reference
How TheRouter serves this differently from the vendor
Zhipu's native MaaS API exposes Vidu 2 Reference at /api/paas/v4/videos/generations using upstream model name vidu2-reference and accepts image_url as an array of reference images.
TheRouter serves the same reference-video capability under public id zhipu/vidu2-reference through its routed video-generation surface with unified TheRouter auth, model catalog pricing, and supported-parameter metadata.
Media Generation Capabilities
- sizes
- 1280x720
- durations_seconds
- 4
- max_reference_images
- 3
- defaults
- size
- 1280x720
- duration_seconds
- 4
API guide
Async reference-video task
Submit reference images, a prompt, duration, aspect ratio, and motion controls to create a 4-second 720p video. Snippets are illustrative until human-approved verification is funded.
curl https://api.therouter.ai/v1/videos \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "zhipu/vidu2-reference",
"prompt": "A cheerful rabbit character drives a tiny car through a sunny market, consistent character design",
"image_url": [
"https://example.com/reference-character.jpg",
"https://example.com/reference-car.jpg",
"https://example.com/reference-style.jpg"
],
"duration": 4,
"size": "1280x720",
"aspect_ratio": "16:9",
"movement_amplitude": "auto",
"with_audio": true
}'Reference-image controls
Use multiple reference images when the generated clip must keep character, object, and style cues aligned. Snippets are illustrative until human-approved verification is funded.
curl https://api.therouter.ai/v1/videos \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "zhipu/vidu2-reference",
"image_url": ["https://example.com/character.jpg", "https://example.com/product.jpg"],
"prompt": "Keep the same character identity while presenting the product with smooth camera motion",
"duration": 4,
"size": "1280x720",
"movement_amplitude": "auto"
}'Fact ledger β every claim on this page traces here
| source | URL | retrieved | |
|---|---|---|---|
| Generation mode | docs.bigmodel.cn β | 2026-09-14 | verified |
| Input images | docs.bigmodel.cn β | 2026-09-14 | verified |
| Duration | docs.bigmodel.cn β | 2026-09-14 | verified |
| Output resolution | docs.bigmodel.cn β | 2026-09-14 | verified |
| Upstream model name | docs.bigmodel.cn β | 2026-09-14 | verified |
| Upstream list price | docs.bigmodel.cn β | 2026-09-14 | verified |
| Generated URL validity | docs.bigmodel.cn β | 2026-09-14 | verified |
| Concurrent in-flight tasks | docs.bigmodel.cn β | 2026-09-14 | verified |
| Official output specification | docs.bigmodel.cn β | 2026-09-14 | verified |
| Multi-reference consistency | docs.bigmodel.cn β | 2026-09-14 | verified |
| Cost versus Vidu Q1 generation | docs.bigmodel.cn β | 2026-09-14 | verified |
| Zhipu documents Vidu 2 Reference for 4-second 720p reference-video generation | docs.bigmodel.cn β | 2026-09-14 | verified |
| How is Vidu 2 Reference different from Vidu 2 Start-End? | docs.bigmodel.cn β | 2026-09-14 | to verify |
| How long and what resolution are Vidu 2 Reference outputs? | docs.bigmodel.cn β | 2026-09-14 | to verify |
| Are the snippets on this page verified against the live API? | docs.bigmodel.cn β | 2026-09-14 | to verify |