Google's Gemini Omni 1.2 Flash shows 9 wild demos: motion transfer, lipsync, virtual try-on
minchoi · x · 2026-11-06
minchoi shared 9 demos of Google's newly released Gemini Omni 1.2 Flash, claiming AI video is getting insanely good. Highlights include:
- Multi-turn motion transfer: same characters and performance across changing worlds (tent → forest → stable → market → castle)
- Multi-speaker lipsync with more natural dialogue
- Virtual try-on video from one model photo and three outfits
- Typography that holds together in motion
- One-shot camera moves from outside a ramen bar to inside
- Style frame to science explainer, two reference photos into a flight through the Pantheon, and a shoreline expanded into an entire island
Related event: Google Launches Gemini Omni 1.2 Flash: 15-Second Video, 30% Cheaper(23 posts)→
More from Multimodal
- Pai v1.0: Open-Source App Merges Painting and AI Generation in One Workspace — g45t345rt · 2026-11-06
- ChatGPT's New GIF Feature Flops: Flickering Frames, Mutated Limbs, No Seamless Loops — Pentunee · 2026-11-06
- GPT Image 2.6 tops Image Arena, up to 2.6x faster, redefines Pareto frontier — cantrell · 2026-11-06
- FLUX 3 Image Hits Artificial Analysis Leaderboards, Strongest in Animation & Gaming — ArtificialAnlys · 2026-11-06
- FLUX 3 models beat FLUX.2 in all 19 Text-to-Image categories; Klein tops $9/1k price frontier — ArtificialAnlys · 2026-11-06
- Minimax character-swap LoRA nails maskless character tracking on first tries — tindell- · 2026-11-06