Gemini Omni Flash has no temperature, top_p or negative prompt
Gemini Omni Flash has no system instructions, temperature, top_p, stop sequences or negative prompts. Put negatives in the prompt; Sume has no such fields.
Gemini Omni Flash does not support system instructions, temperature, top_p, stop sequences or negative prompts. Google's advice is to put negatives in the regular prompt, for example "Do not do X". Sume's video request has no sampling fields either, so the same approach works there.
The vendor list is from Google's video generation guide; the Sume side is from the video generation docs, both read 2026-10-01.
Which controls does Google say are unsupported?
The limitations list names five: system instructions, temperature, top_p, stop sequences, and negative prompts. It also says to write negatives into the prompt text.
What fields does a Sume video request accept?
| Field | What the docs say |
|---|---|
prompt | Text description of the video to generate |
seed | No v1 model accepts it; each reports seed: false and rejects the field |
provider.options | A non-empty value returns 400 unsupported_parameter |
| Sampling fields | Not in the request parameter table |
Where do I put a negative, then?
In the prompt. Write it as a plain instruction, such as "no text overlays", after the description of what you do want. The general technique is covered in AI video negative prompts.
Can I get repeatable output with a seed?
Not through Sume's v1 video route: sending seed is rejected. If you need to repeat a result, keep the job id and the returned artifact rather than trying to regenerate it.
Sources
Related posts
More in Developers
- Gemini Omni Flash video edit: 5 reference images vs Sume
Runway's Gemini Omni Flash video-to-video edit accepts up to 5 reference images. On Sume, a video_url edit cannot be combined with any reference field.
- Gemini Omni store=false sync video vs Sume's 30-second sync cap
Gemini suggests background=false, store=false, stream=false for synchronous video. Sume sync mode waits at most 30 seconds, then you poll status_url.
- Gemini Omni task values mapped to Sume request fields
Google's Omni task field takes text_to_video, image_to_video, reference_to_video, edit or extend. On Sume the fields you send pick the mode; extend is absent.
- Gemini TTS caps 200 voices per project: picking a voice on Sume
Gemini TTS stores at most 200 voices per project for a year. On Sume you list avatars and use one whose voice.status is ready, with no stored-voice quota.
Written by Sume