Edit an existing ad video with Gemini Omni Flash on Sume
Sume's Video Router takes a video_url for video edit on gemini-omni-flash-1.1. How to send an edit request and why sume/auto won't tell you the model.
Send an existing clip to POST /v1/video-router/generate with video_url and a gemini-omni-flash-1.1 model to edit it. Read Video Router for the current request fields and models, because they change between releases.
Router behaviour to know
Name gemini-omni-flash-1.1 explicitly when you want to know which model produced the edit; sume/auto does not disclose it.
| Topic | Fact |
|---|---|
| Edit input | video_url is the edit source; the prompt describes the edit |
| Not allowed with edit | image_url, end_image_url, reference_*_urls, aspect_ratio, duration |
resolution | Optional, default 720p |
| Idempotency | Idempotency-Key supported |
Editing vs regenerating
A fresh generation starts from a prompt, frame_images or references, while an edit starts from your clip. See Video generation. Pick edit when you already have the clip and only want to change it.
Source rules
video_url cannot be combined with image or reference inputs, so an edit request carries only the clip and the prompt.
Sources
Related posts
More in Use cases
- Google video experiment results: 70% directional, 95% conclusive
Google labels video experiment results directional at 70% confidence and conclusive at 95%. When to act on each, and how to line up Sume ad variants first.
- Google Ads video experiment: 2 arms or up to 10 AI variants?
Google's basic video A/B test has two arms and only covers Video Reach and Video View campaigns; Custom allows up to 10. How many Sume variants to render.
- GPT Image 2.5 icon set: one anchor icon, then reference it
Make a consistent icon set with GPT Image 2.5 on Sume: approve one anchor icon, pass it as input_references, change only the subject, and keep a style block.
- GPT Image 2.5 pixel art sprite sheet: prompt a grid, slice it
Ask GPT Image 2.5 for a 4x2 sprite sheet at 2048x1024 on Sume, then slice frames and snap to a true pixel grid with Pillow. Prompt and code included.
Written by Sume