
google/gemini-omni-flash/reference-to-videoA natively multimodal Google DeepMind model that generates cinematic, sound-enabled videos from a text prompt plus 1-5 reference images, carrying a consistent subject, scene, or style across generations.
Set up the model and run your first generation.
Ctrl ⏎Runs published with this model. Load one into the playground and change whatever you like.
The little doll is jumping happily.
Where this model can run, priced for your account. Auto routing picks the top row and moves down it if a provider fails.
| Provider | Price | Speed | Completed |
|---|---|---|---|
| Atlas CloudLowest price | $0.135 /sec | — | — |
| fal.ai | 1 unit | — | — |
| OpenRouter | — | — | — |
| Replicate | — | — | — |
Speed and reliability appear once this platform has enough recent runs on a provider.