Watercolor diorama from one photo: Gemini nails a scroll-driven story task
AI_Andrew · x · 2026-11-11
A user gave Gemini a single photo and asked it to "understand the assignment": create a watercolor diorama of the moment as a scroll-driven web story, then recorded the whole process as a video. The model handled the multi-step creative task in one shot.
Related event: Gemini Turns a Single Photo into a Watercolor Diorama Scrolling Story(3 posts)→
More from Multimodal
- Hybrid AI Video Pipeline Test: MiniMax H3 for Audio, Nano Banana 2 for Visuals — RollingMeteors · 2026-11-11
- Slopus and Slopfab add MiniMax H3 Image support with editing and outpainting — BittiAI · 2026-11-11
- IFM open-sources PAN2: 29B latent diffusion video model, 20s 720p, training code included — Aggressive-Zebra-949 · 2026-11-11
- AI art thread: 'He ran so fast that time eventually lost track of him' — LudovicCreator · 2026-11-11
- Google Antigravity agent edits your photo, adjusting trees and figures to taste — AI_Andrew · 2026-11-11
- ElevenLabs ships Scribe v3: 43% fewer real-time errors, 102 languages — minchoi · 2026-11-11