Wan 3.0 first and last frame: animate between two images
Wan 3.0 can make a clip that starts on one image and ends on another. On Sume, send frame_images with first_frame and last_frame to wan-3.0; last needs first.

Yes, Wan 3.0 can animate between two images. On Sume, send frame_images to wan-3.0 with one entry as first_frame and one as last_frame; the clip starts on the first and is generated toward the second. A last_frame on its own is refused.
Alibaba's Wan3.0 guide lists first-frame and first/last-frame control among its features, and Sume's Video generation docs give the request shape. Read 2026-09-29.
What does the request look like?
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: wan-frames-001" \
-d '{
"model": "wan-3.0",
"prompt": "The seed sprouts and grows into a tall sunflower, time-lapse, static camera",
"duration": 8,
"resolution": "720p",
"frame_images": [
{ "type": "image_url", "image_url": { "url": "https://example.com/seed.png" }, "frame_type": "first_frame" },
{ "type": "image_url", "image_url": { "url": "https://example.com/sunflower.png" }, "frame_type": "last_frame" }
]
}'What are the rules?
| Rule | Detail |
|---|---|
| Frame types | first_frame and last_frame |
| Last frame alone | Refused with unsupported_capability |
| Frames plus references | Frames win; the references are dropped |
| Image URLs | Public HTTPS |
| Length | 2 to 30 seconds, whole seconds |
How do I make the two frames match?
Use images with the same subject, framing and light, and describe the change between them, not the frames themselves. A start and an end that differ in everything leave the model to invent a bridge you may not want.
Does a longer clip help?
It gives the change more time. A 2 second clip suits a small move; a 10 to 30 second clip suits a large one. Price rises with seconds, so see Wan 3.0 pricing per second.
Sources
Related posts
More in Models
- Wan 3.0 omni reference video: images, clips and audio in one prompt
Omni reference means one request carries mixed references. Wan 3.0 takes up to 10 images, 5 videos and 5 audio tracks; on Sume, send them as input_references.
- Wan 3.0 reference limits: how many images, videos and audio clips
Wan 3.0 reference-to-video takes up to 10 images, 5 video clips and 5 audio tracks. See the per-type caps, what Sume rejects with unsupported_capability, why.
- Wan 3.0 thinking mode: why document and web page input needs it
fal says Wan 3.0 needs thinking mode to read a document or web page; Alibaba says prompt_extend must be true. What each means, and why Sume's wan-3.0 skips it.
- Wan 3.0 vertical video: 9:16 for Reels, Shorts and TikTok
Wan 3.0 supports 9:16. Send aspect_ratio 9:16 to wan-3.0 for a vertical clip of 2 to 30 seconds at 480p, 720p or 1080p. Accepted ratios and cost.
Written by Sume