Swap the gift in a Christmas clip with Gemini Omni Flash edit
Gemini Omni Flash 1.1 on Sume edits a 3 to 10 second clip by prompt, so one approved Christmas ad can become three gift variants without a reshoot.

Gemini Omni Flash 1.1 on Sume accepts a video_url and a prompt and rewrites the clip, for example replacing the bottle with an apple. That lets one approved Christmas ad become three gift variants. The input is 3 to 10 seconds, so trim a longer clip first.
What the edit mode does
You send an existing clip and describe the change. The model keeps the framing and motion and swaps the object. It does not take reference photos in edit mode, so describe the new gift in words.
| Field | Value |
|---|---|
| Clip length | 3 to 10 seconds |
| Edit input | video_url plus a prompt |
| Example prompt | replace the bottle with an apple |
| Billing | provider list times 1.25 |
Three variants, one source
Write three prompts that change only the object: candle, mug, scarf. Run each as a separate job and review the three clips side by side before captions.
- Keep the prompt short and literal
- One change per prompt
- Check hands and edges frame by frame
When to trim first
If your source clip runs over 10 seconds, cut the best 8 with Sume's video trim at $0.02 per job, then edit the trimmed copy.
Limits worth knowing
A product with a legible logo or label may not survive an edit cleanly. For hero shots with exact packaging, generate from a first frame instead, and keep edit mode for non-label objects.
Sources
Related posts
More in Models
- Do you need streaming transcription? A recorded clip needs a batch job
MAI-Transcribe-2-Streaming is built for live audio. For a finished clip, Sume STT at $0.01 a minute returns text and word timings. How to decide which you need.
- Does Lyria 3.5 audio carry a SynthID watermark?
Yes: Google's Gemini API music docs say Lyria audio carries a SynthID watermark. The Sume docs I read do not describe watermarking either way.
- Draw boxes on a photo, then edit it: Sketch-style markup on Sume
ChatGPT Sketch is a drawing panel inside ChatGPT. On the API you get the same effect by sending a marked-up photo as a reference and saying what the marks mean.
- Eleven v4 stacked tags: direct emotion without them
ElevenLabs v4 adds stackable expression tags and 10-second cloning. Sume's docs list no clone route; here is how to direct a voice via tts_create.
Written by Sume