Google Upgrades Gemini Omni 1.1 Flash with 4K Video, Scene Extension, and Faster Draft Generation

Google Gemini Omni 1.1 Flash Transforms AI Video Generation

Google has launched Gemini Omni 1.1 Flash, a significant update to its generative video model that introduces advanced controls for AI video generation1

1

. The update is available immediately to developers through Google AI Studio and the Gemini Enterprise Agent Platform, while consumer access is rolling out globally to Google AI Plus, Pro, and Ultra subscribers through Google Flow2

2

. Scene extension capabilities are also available in the Gemini app for these subscribers4

4

.

Enhanced Scene Extension Analyzes 10 Seconds of Context

The updated scene extension system represents a major leap in maintaining visual consistency. Gemini Omni 1.1 Flash can now analyze up to 10 seconds of prior video context when generating new content, compared with just the final second in earlier models2

2

. This expanded context window gives the generative AI model significantly more information to maintain visual consistency and narrative continuity as footage continues1

1

. Creators can extend clips in 10-second increments up to a cumulative 40 seconds5

5

, providing substantial flexibility for building longer sequences while preserving the original aesthetic and storytelling elements.

Keyframe-Based Video Generation Offers Precise Control

A new first-and-last-frame control lets creators specify two keyframes, with the model generating continuous motion between them1

1

. This keyframe-based video generation feature supports complex camera movements including camera orbits, zoom transitions, and looping clips2

2

. The capability allows creators to lock in consistent characters and narratives while planning out scene transitions, rather than leaving the entire sequence to the AI-powered video creation tool3

3

. This level of control marks a shift from purely generative outputs to more directed video production.

360p Draft Generation Accelerates Prototyping

Gemini Omni 1.1 Flash introduces 360p draft generation that renders up to 60% faster and costs one-third as much as standard 720p output2

2

. This quick-drafting workflow lets editors rapidly test visual concepts and scene compositions at lower resolution before committing to full-resolution renders3

3

. The 360p mode is designed for rapid prototyping, storyboard iteration, and making experimentation cheaper and faster1

1

. For mobile video creation workflows, this feature is especially valuable, allowing users to quickly draft generated content on their phones and upscale preferred versions later3

3

.

4K Video Upscaling Delivers Professional Quality

Once a concept is finalized, Gemini Omni 1.1 Flash can produce polished 1080p or 4K video upscaling outputs1

1

. This capability transforms the generative video model from a prototyping tool into a production-ready solution. Users can export their video in either 1080p or 4K resolution after finishing a rough cut3

3

, ensuring high-resolution outputs suitable for professional distribution. The workflow from 360p drafts to 4K finals creates an efficient pipeline that balances speed during iteration with quality in final delivery.

Video References Maintain Character Continuity

The model accepts up to three seconds of video as multimodal references when creating a scene1

1

. This reference capability helps maintain character consistency and visual context based on existing footage4

4

. Reference videos can provide visual context and help carry over details such as character appearance and environmental settings from the source material5

5

. This feature addresses one of the persistent challenges in AI video generation: maintaining consistent visual elements across multiple generated clips.

Industry Integration Signals Broader Adoption

Several major platforms are integrating Gemini Omni Flash into their products. Adobe has added it to Firefly, while Figma Creative Director Itay Schiff noted the model lets teams move "beyond generating videos to truly directing them"2

2

. Other companies including Figma Weave, GMI Cloud, and Runway are also incorporating the technology into their video workflows4

4

. Google has published comprehensive developer documentation, a cookbook, and prompting guides covering scene extension, video references, and upscaling through the Gemini API5

5

. This ecosystem development suggests the technology is moving from experimental to production-grade, positioning Google Flow as a serious contender in professional creative workflows alongside established tools.