Gemini Omni Flash 1.1
gemini-omni-flash-1-1-text-to-videogoogle/gemini-omni-flash/v1.1/text-to-video- 🎬 Google's text-to-video model generating clips with synchronized audio
- 🆕 Production-ready 1.1 update focused on developer control over generated video
- 📏 Extend clips in 10-second steps, up to 40 seconds total
- 🧠 Uses 10 seconds of prior context, versus one second previously
- 🔧 Adds camera-move control, first/last-frame interpolation, and 4K upscaling
- ⚡ Low-resolution draft mode for faster, cheaper prototyping of ideas
- 🌐 Grounded in Gemini world knowledge and physics understanding
- 🔒 Preview-family model with safety filters on prompts and outputs
Google is an American multinational technology corporation and one of the world's most valuable brands. A subsidiary of parent company Alphabet Inc., Google operates across search, cloud computing, consumer electronics, and artificial intelligence. Its DeepMind and Google…
Explore 28 more models by Google →Gemini Omni Flash 1.1 is the text-to-video entry point for Google's Omni line, a multimodal family that pairs Gemini's reasoning with DeepMind's generative media stack to produce video (with synchronized audio) alongside text in a single model. From a written prompt it renders a clip grounded in Gemini's real-world knowledge, with physics understanding intended to make motion and interactions more coherent.
Compared with the original Gemini Omni Flash, the 1.1 release is described by Google as a production-ready update centered on control. The most concrete change: when continuing a scene, the model now conditions on up to 10 seconds of prior context, where earlier models referenced only the final second, which Google credits with better visual consistency and narrative adherence. Videos can be extended in 10-second increments to a 40-second total, with the last 10 seconds used as context to keep motion, characters and audio coherent. Also new are explicit camera-movement control, first-and-last-frame interpolation, 4K upscaling, and a fast low-resolution draft mode for cheaper iteration.
The same 1.1 generation covers other input modes: image-to-video, R2V for reference-guided generation, and Edit for conversational revision of existing footage.
Google positions Omni as conversational video creation and editing, applies content safety filters to both prompts and generated video, and notes that English is fully supported while other languages remain unevaluated.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · Gemini Omni Flash 1.1 · Organic sellers
Top sellers · Gemini Omni Flash 1.1 · Organic
- Open Forge77.8%
- Venice.ai Proxy20.7%
- antseed-tidal-falcon-88cd1.4%
- attacompute.ai0.1%
- ▲ Apex Ant0.1%
| Seller | Health | Rep↓ | Sales | Video | Routing | $ / s | $ / video |
|---|---|---|---|---|---|---|---|
| Open Forge 0x1d90…b0aa | healthy | 91.11 | $197.11 | 33.9 min | #1 | $0.10 | — |
| ▲ Apex Ant 0x73b4…e736 | — | 81.71 | $0.14 | 8 s | #3 | $0.0525 | — |
| attacompute.ai 0xd5e7…7be0 | — | 51.22 | $0.20 | 4 s | gated | $0.136 | — |
| antseed-tidal-falcon-88cd 0x80d1…88cd | — | 12.78 | $3.45 | 15 s | gated | $0.08 | — |
| OpenCheap 0x0ee1…6c41 | — | 12.43 | — | — | gated | $0.095 | — |
| Venice.ai Proxy 0x1f22…18c9 | failingupstream error · 3.7 h · stale | 86.84 | $52.33 | 15.7 min | #2 | $0.0641 | — |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.