What output resolutions, edit/extend limits and provenance marks does Google's Gemini Omni Flash video documentation state, and what is 'upscaled' there?
Problem. A pipeline needs to know which dimensions are native, what edits are possible, and what marks the output carries. Conditions. Gemini API Omni documentation (raw markdown) fetched 2026-10-23; the sibling video page says Veo 3.1 Preview in the Gemini API was shut down on October 22, 2026 and points to Omni (gemini-omni-1.1-flash) or GA Veo via the Gemini Enterprise Agent Platform. Method (documented). aspect_ratio supports 9:16 and 16:9; resolution values 360p, 720p (default), 1080p and 4k, where the table labels 1080p and 4k as upscaled outputs; image-to-video, first and last frame interpolation, subject reference images and stateful conversational editing exist. Limitations list: editing or extending uploaded videos is unavailable in the EEA, Switzerland and the UK (model-generated videos can still be edited); uploaded inputs for editing/extension must be 10 s or less; extension only appends at the end; no extension of an uploaded video where someone talks to add dialogue; ...
Structured fields
{
"citations": [
{
"url": "https://ai.google.dev/gemini-api/docs/omni.md.txt",
"note": "Output resolution; Limitations; Limitations; Limitations; Technical details; Resolution paragraph"
}
]
}Evidence claims
- [sourced_fact] Problem. A pipeline needs to know which dimensions are native, what edits are possible, and what marks the output carries. Conditions. Gemini API Omni documentation (raw markdown) fetched 2026-10-23; the sibling video page says Veo 3.1 Preview in the Gemini API was shut down on October 22, 2026 and points to Omni (gemini-omni-1.1-flash) or GA Veo via the Gemini Enterprise Agent Platform. Method (documented). aspect_ratio supports 9:16 and 16:9; resolution values 360p, 720p (default), 1080p and 4k, where the table labels 1080p and 4k as upscaled outputs; image-to-video, first and last frame interpolation, subject reference images and stateful conversational editing exist. Limitations list: editing or extending uploaded videos is unavailable in the EEA, Switzerland and the UK (model-generated videos can still be edited); uploaded inputs for editing/extension must be 10 s or less; extension only appends at the end; no extension of an uploaded video where someone talks to add dialogue; video references work best with likenesses, any audio in them is ignored, and they allow at most 3 clips of up to 3 s each; multi-video referencing is unsupported and may degrade; negative prompts, temperature and system instructions are unsupported (write 'do not' in the prompt). All generated videos include SynthID watermarking, detectable programmatically. Use [inference]: treat 1080p/4k as upscaled from a lower native size when judging detail, so run a sharpness check before 4K delivery and avoid a second AI upscale unless checked (C3-B582-13 covers when not to upscale). Failure modes. Region restrictions can block edit workflows; negative-prompt habits from other tools do not apply here. Limitations. Documentation only, no clip generated; native generation size is not stated in the passages read. Version/date. Omni docs fetched 2026-10-23. · locator: Output resolution; Limitations; Limitations; Limitations; Technical details; Resolution paragraph source
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Applies to this original summary only, not to the cited sources. |