Mixer AI
Gemini Omni 1.1 Flash
Gemini Omni 1.1 Flash combines text, references, first/last frames, and video transformation in one variant.
When to choose it
Gemini Omni 1.1 Flash is a specific Omni variant in Mixer AI. For a new clip, use text, image references, or the dedicated first-frame and optional last-frame workflow. You can also transform a short segment of source video. Version 1.1 differs from 1.0 by adding the frame workflow and a 360p option.
- A dedicated first/last-frame workflow in addition to text and ordinary image references.
- Four output resolutions from 360p through 4K for new clips.
Modes and settings
- From text, 1–7 image references, first/last frames, or source-video transformation.
- New clips: 4, 6, 8, or 10 seconds; 360p, 720p, 1080p, or 4K; 16:9 and 9:16.
Price in coins
| Quality / size | Input | Duration | Coins / generation |
|---|---|---|---|
| 360p | Video transformation | Segment up to 10s | 108 |
| 360p | Text or images | 4 s | 42 |
| 360p | Text or images | 6 s | 55 |
| 360p | Text or images | 8 s | 68 |
| 360p | Text or images | 10 s | 82 |
| 720p | Video transformation | Segment up to 10s | 108 |
| 720p | Text or images | 4 s | 42 |
| 720p | Text or images | 6 s | 55 |
| 720p | Text or images | 8 s | 68 |
| 720p | Text or images | 10 s | 82 |
| 1080p | Video transformation | Segment up to 10s | 108 |
| 1080p | Text or images | 4 s | 42 |
| 1080p | Text or images | 6 s | 55 |
| 1080p | Text or images | 8 s | 68 |
| 1080p | Text or images | 10 s | 82 |
| 4K | Video transformation | Segment up to 10s | 161 |
| 4K | Text or images | 4 s | 95 |
| 4K | Text or images | 6 s | 108 |
| 4K | Text or images | 8 s | 121 |
| 4K | Text or images | 10 s | 134 |
Coins are Mixer AI balance units. The table shows a base request without extra variations. Multiple results and new attempts can increase the total; check it before submitting.
What you can make
- A transition between prepared opening and ending compositions.
- Short generation or video transformation that needs image references.
How to direct the result
- In frame mode, describe the movement that should connect the opening and ending compositions.
- For video transformation, list what must remain first: character, camera, motion, and objects.
Example: transition between two frames
Start exactly from the first frame and transition smoothly to the final frame. The camera moves slowly forward while the character takes two steps toward the window and the light shifts toward evening. Preserve clothes, face, furniture, and room geometry; no abrupt cuts.
What to keep in mind
- The first/last-frame workflow cannot be mixed with the ordinary image-reference set.
- Video transformation works on a selected segment up to 10 seconds and does not treat the new-clip duration selector as a promise for edited output length.
Sources
- Prices and availability — Mixer AI catalog, updated 2026-10-02.
- Official maker site: Google
Model facts verified: 2026-10-02.
Guides and comparisons using this model
FAQ
What is different in 1.1 versus 1.0?
In Mixer AI, 1.1 adds the dedicated first/last-frame workflow and a 360p option.
Which durations are available for a new clip?
4, 6, 8, or 10 seconds.
How many image references can I use?
The ordinary reference workflow accepts one to seven images.
Can I upload an existing video?
Yes. There is a separate workflow for transforming a short source-video segment.
Which aspect ratios are available?
16:9 and 9:16.
Can I mix a last frame with ordinary references?
No. Frame mode is a separate input workflow.
What changes the price?
It depends on version, quality and mode. The table prices one generation at the listed settings. Additional results, new attempts and chargeable input materials can increase the total.
Do I need a separate model subscription?
No. In Mixer AI, you top up one coin balance and use it for the tasks you need. You do not need a separate subscription to this model.