Google's Gemini Omni 1.1 Flash makes AI video generation cheaper and more flexible
Source: The Decoder · Matthias Bastian
Intel Summary
Google has updated its Gemini Omni 1.1 Flash video generation model with enhanced scene extension and a lower-cost preview tier. The model can now analyze up to ten seconds of existing footage for context rather than just the final second, enabling extensions in 10-second increments up to a total duration of 40 seconds. Additionally, a new 360p draft mode is reported to generate previews up to 60 percent faster at one-third of the standard compute cost.
Why It Matters
Context continuity has been a core technical limitation in generative video, where sequential scene extensions frequently suffer from visual drift. Expanding the reference window improves temporal coherence for multi-clip workflows. Concurrently, rapid draft modes reduce experimentation costs for developers and media teams prototyping video assets before committing full rendering budgets.
Part of an ongoing development
SourceGoogle updated Gemini Omni 1.1 Flash model with enhanced scene extension and 360p draft mode
Google has updated its Gemini Omni 1.1 Flash video generation model with enhanced scene extension and a lower-cost preview tier. The model can now analyze up to ten seconds of existing footage for context rather than just the final second, enabling extensions in 10-second increments up to a total duration of 40 seconds. Claims are as reported; this summary makes no determination about accuracy or significance.
Organizations & Entities
Related Intelligence
- ReportAlso involving Google
‘Model fatigue’ sets in as AI labs race to roll out new versions at frenetic pace
CNBC reports that Anthropic, OpenAI, Meta, and Google all rolled out model updates in a single week amid emerging model fatigue, while Nvidia announced it is acquiring open-source AI platform Hugging Face.
CNBC Tech - DevelopmentNewAlso involving Google
Google announces Gemini 3.5 Transcribe
Google has launched Gemini 3.5 Transcribe, an automated speech-to-text model supporting more than 85 languages. Google reports a 4.0 percent word error rate in streaming mode alongside a 70 percent reduction in latency compared to its previous Chirp 3 system. Claims are as reported; this summary makes no determination about accuracy or significance.
2 independent sources - DevelopmentNewAlso involving Google
OpenAI and coalition publish open letter warning of imminent AI cyberattacks
More than 100 technology companies and artificial intelligence developers, including OpenAI, Anthropic, Google, and Microsoft, have formed a coalition calling for urgent measures to counter next-generation cyber threats enabled by rogue AI systems. The group is advocating for coordinated defensive protocols and promoting new collective solutions designed to protect enterprise infrastructure from automated, AI-driven attacks and emerging autonomous security vulnerabilities across the global digital ecosystem. Claims are as reported; this summary makes no determination about accuracy or significance.
2 independent sources - DevelopmentNewAlso involving Google
Google launched Gemini 3.8 Flash and Gemini 3.8 Flash Cyber models
Google launched Gemini 3.8 Flash and Gemini 3.8 Flash Cyber, two large language models built on the same technical foundation with advanced reasoning capabilities. Gemini 3.8 Flash functions as a general-purpose model, while Gemini 3.8 Flash Cyber is tailored specifically for cybersecurity researchers. Claims are as reported; this summary makes no determination about accuracy or significance.
1 reporting source