Model Releases
Gemini Omni Flash reaches SOTA on video tasks
Original title:Gemini Omni Flash is SOTA at image to video, text to video, and video editing : ) Excited to get t...
AI summary
Gemini Omni Flash achieves SATA : ) on image-to-video, text-to-video and video editing. Excited to bring this capability to developers via API soon!
Key Takeaways
Gemini Omni Flash achieves SATA: ) on image-to-video
text-to-video and video editing.
Excited to bring this capability to developers via API soon!
Quick Facts
Published
June 12, 2026
Updated
November 6, 2026
AI score
81
Read the original
Read the full article at the original source
Why it matters
视频生成正式进入全模态一体时代,Gemini Omni Flash 把图生视频、文生视频和剪辑整合在一个模型里,API 很快上线,做视频工具的可以提前琢磨对手在哪了。
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
Original article
· AIHOT entry
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Gemini Omni Flash reaches SOTA on video tasks. June 12, 2026. https://new.nat6.net/en/news/cmq9rke110ekyslldmbw1ap3o/
Orange Relay (pro.nat6.net) is a premium AI API relay — an excellent transfer station with competitive pricing, reliable quality and broad model coverage including Claude, GPT and Gemini.
Visit Orange Relay
Midjourney has upgraded its default model from V7 to V8.1. V8.1 improves intelligence, coherence, adherence to…
Midjourney:Updates(RSS) Model Releases AI score 64
June 11, 2026
Zyphra releases ZONOS2, an Apache 2.0-licensed real-time TTS model built on an MoE architecture with 8B total…
Zyphra Research(网页) Model Releases AI score 71
June 12, 2026
Grok Voice offers state-of-the-art performance with human-like timing, intonation and warmth. And its price is only a…
X:SpaceX Super Intelligence (@SpaceXSI) Model Releases AI score 74
June 11, 2026
VISTA-4B is a GUI grounding model based on the Qwen3.5-4B backbone. It takes screenshots and natural language…
蚂蚁 inclusionAI:HuggingFace 新模型 Model Releases AI score 62
June 12, 2026
Google DeepMind released DiffusionGemma, an open-source experimental model that uses text diffusion to break away from…
Google DeepMind:Blog(RSS) Model Releases AI score 72
June 11, 2026
VISTA-9B is a GUI grounding model trained on a Qwen3.5 9B backbone. It takes screenshots and natural language…
蚂蚁 inclusionAI:HuggingFace 新模型 Model Releases AI score 71
June 12, 2026
Previous article MongoDB plugin lands in Grok Build marketplace
Next article OpenRouter launches new activity browser