Google · video
Gemini Omni Flash 1.1
Gemini Omni Flash 1.1: from 360p drafts to 4K, with frames and up to 10 image and 3 video references.
Text to videoImage to videoStart and end frameReferencesNative audio
- Length
- 3 to 10 s
- Resolution
- 360p, 720p, 1080p, 4K
- Aspect ratio
- 16:9, 9:16
- References
- Up to 13 image or video files
About Gemini Omni Flash 1.1
Gemini Omni Flash 1.1 is Google's multimodal video model in its newer version, priced at $0.075 per second. It runs as text to video, image to video, start and end frame and references to video, with synchronized audio, from 3 seconds to 10 seconds, and the provider describes camera control expressed in natural language.
In reference mode it reasons across images, videos and the prompt together, and according to the provider characters keep their face, clothing and voice throughout. A typical generation takes about 2 min.
Good for
- Iterating at 360p and delivering the same shot at 4K
- Characters that keep their face, clothing and voice, from image and video references
- Camera moves written in plain language in the prompt
Getting good results
- The price spread across resolutions is wide: $0.60 at 360p against $6.00 at 4K for the default length.
- Reference mode takes images and short video clips, 13 files in all; the provider reads them in upload order, before the prompt.
- Reference videos do not change the price.
Gemini Omni Flash 1.1 questions
What resolutions does Gemini Omni Flash 1.1 offer?
360p, 720p, 1080p and 4K, at 16:9 and 9:16.