Gemini Omni Flash 1.2
Gemini Omni Flash 1.2 is Google’s model for creating and revising short clips.
What it's the best tool for
- Short clips from a written scene
- Image-led starts and references
- Dedicated source-video workflows
- Duration validation follows the chosen inputs
When to reach for something else
- References restrict available durations
- Input types cannot be combined arbitrarily
- Review complex motion and fine detail
How Gemini Omni Flash 1.2 responds
Four scenarios where it pays for itself
More about Gemini Omni Flash 1.2
Gemini Omni Flash 1.2: short video from text and frames
Gemini Omni Flash 1.2 is Google’s model for creating and revising short clips. Start with a scene description or a prepared image, then choose a workflow suited to the available inputs. The fox in a dawn forest shown on this page is an actual Omni Flash 1.2 generation.
Available in NetRoom
Text and single-first-frame workflows offer durations from 3 to 15 seconds. Multiple-frame and reference workflows have their own upper limit, which can be 10 seconds. The model accepts supported image and video inputs; editing and extending a clip have distinct constraints.
Preparing the result
Describe one scene, one subject action and a clear camera movement. The forest example combines a fox turning its head with a slow camera approach. Use a first frame when the starting composition matters. Review the available durations again after adding references.
Practical uses
- Wildlife scene: Describe a short animal action and camera move.
- Image animation: Start a clip from a prepared image.
- Advertising concept: Compare short visual directions for a scene.
- Video workflow: Choose the appropriate operation for a source clip.
Reviewing the result
References restrict available durations; Input types cannot be combined arbitrarily; Review complex motion and fine detail.
What changed Gemini Omni Flash 1.2
- ~ Upgraded Gemini Omni Flash 1.1 to Gemini Omni Flash 1.2 (Google).
Use Gemini Omni Flash 1.2 via the API
The same engine, straight from your code: one key and one balance for text, images, video and sound. Pay only for the requests you make.
curl https://netroom.ai/api/v1/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "google/gemini-omni-flash-1-2", "input": {"prompt": "A cinematic mountain sunrise"}}'
The model id is already in the example. The full parameter reference and prices live in GET /api/v1/models and in the docs.
Try Gemini Omni Flash 1.2
right now
Free access to basic models. No card, no obligations.