Open Vision Banana Open-Sources Recipe to Give Image Generators Vision
Linoy Tsaban 发布 Open Vision Banana 项目,基于 Black Forest Labs 的 Flux 2 Klein 4B/9B 微调,让原本只会生成图像的模型具备「看懂」图像的视觉感知能力。项目提供一套完全开放的配方,可将图像生成模型改造为统一的感知模型,相关成果已在 HuggingPapers 等渠道公开,引发社区关注。
2026-11-16 ~ 2026-11-16 · 2 related posts
- Open Vision Banana: open recipe turns FLUX.2 image generator into unified perception model for segmentation, depth, normals — NielsRogge · 2026-11-16
- Open Vision Banana: Flux 2 Klein finetunes give generative models vision, 7 tasks in one — linoy_tsaban · 2026-11-16