Edits Restyle with a prompt vs Sume video router edit mode
Edits Restyle changes a clip's look from a text prompt. In Sume, send video_url to the video router with a prompt to use gemini-omni-flash-1.1 edit mode.

Edits Restyle is an in-app control. The Sume equivalent for an existing clip is the video router's edit mode: send model: "gemini-omni-flash-1.1", a prompt describing the edit, and video_url as the source to POST /v1/video-router/generate.
Restyle is from Instagram's creators blog; Sume behavior is from Video Router and Video generation, read 2026-10-01.
What does Edits Restyle do?
Instagram says you can transform the look of a video with a simple text prompt: tap a clip on the timeline, tap Restyle, then browse presets or type a prompt. It is available in select countries and generation limits may apply.
How does edit mode work in Sume?
The Video Router docs list video_to_video (edit) as taking video_url, with the prompt describing the edit and resolution optional (default 720p). There is no aspect_ratio or duration field in this mode. video_url is the edit source, not a reference, and cannot be combined with image_url, end_image_url or reference_*_urls.
curl -X POST https://api.sume.com/v1/video-router/generate \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: video-router-edit-001" \
-d '{
"model": "gemini-omni-flash-1.1",
"prompt": "Restyle the clip as a watercolor painting. Keep the motion the same.",
"video_url": "https://example.com/clip.mp4",
"resolution": "720p",
"mode": "async"
}'What limits does the model state?
| Item | Docs statement |
|---|---|
| Length | 3 to 10 seconds |
| Resolutions | 360p, 720p, 1080p, 4K |
| Ratios | 16:9 or 9:16 |
| Inputs | Image and video input_references (no audio) |
| Edit mode | Reached through the Video Router video_url field |
How should I write the prompt?
Describe the change and say what stays the same, as the docs' own example does ("Keep everything else the same"). More prompt patterns are in edit a video with a prompt.
Sources
Related posts
More in Models
- Edits audio vibe filter vs a Sume music prompt (no duration field)
Edits lets you filter audio by vibe like chill or bossy. Sume music takes a text prompt instead, with no duration, seed or temperature parameter to pin.
- Kling 4.0 10-bit HDR at 1080p and 4K: what later edits keep
Kling says 4.0 outputs 10-bit HDR at 1080p and 4K. Sume's exact video_trim re-encodes to yuv420p; keyframe trims stream-copy. Verify before you grade.
- Kling 4.0 21:9 ultrawide: check Sume's aspect ratios
Kling 4.0 supports 21:9 output. Sume documents 21:9 as a ratio, but each model lists its own supported_aspect_ratios, so read them before sending.
- Kling 4.0 five reference videos vs Sume's 1 to 3 video URLs
Kling 4.0 takes up to 5 reference videos, 30 seconds combined. Sume lists 1-3 reference_video_urls on the legacy shape and varies per model.
Written by Sume