Open Vision Banana: Flux 2 Klein finetunes give generative models vision, 7 tasks in one
linoy_tsaban · x · 2026-11-16
- Linoy Tsaban released Open Vision Banana: Flux 2 Klein 4B/9B finetunes trained to give generative models actual visual perception ("seeing") capabilities.
- The project ships a fully open recipe for generative visual perception, with one model covering 7 vision and generation tasks.
- Model weights, code, and a demo Space are all publicly available.
Related event: Open Vision Banana Open-Sources Recipe to Give Image Generators Vision(2 posts)→
More from Multimodal
- Bicycle glissando: an unusual MIDI editor built in Antigravity with Gemini 4 Carbon — alexanderchen · 2026-11-16
- Inside the curved-paths MIDI editor built in Antigravity that plays music with bicycles — alexanderchen · 2026-11-16
- Synthesia launches Syren, an AI agent that turns one prompt into on-brand video — synthesiaIO · 2026-11-16
- MiniMax H3's official images look stunning—why can't ComfyUI users reproduce them? — cptdurr · 2026-11-16
- AI-animated short "Three Dollars, Two Wants" debuts its first episode trailer — Intelligent-Past1633 · 2026-11-16
- Hugging Face releases definitive fine-tuning guide for 3D generation model TRELLIS.2 — ariG23498 · 2026-11-16