Open Vision Banana open-source generative visual solution
The story so far
Open Vision Banana (OVB) open-sources its data, weights, code, and implementation details, providing a fully open-source and reproducible solution for converting pre-trained generators into a unified multi-task perception system. Its 4B and 9B parameter-based licensed heavy models and 2.1M-3.8M training pairs achieve 73.9 vs 69.9 mIoU zero-shot performance on Cityscapes, comparable to state-of-the-art affine invariant depth estimators.
AI-written from the reports · Updated yesterday
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersOpen Vision Banana: A completely open-source generative visual perception solution.
Open Vision Banana (OVB) has open-sourced its data, weights, code, and implementation details. Its 4B and 9B parameter-based open-weighted large model and 2.1M-3.8M training pairs surpass Vision Banana on Cityscapes with zero-shot performance of 73.9 vs 69.9 mIoU and can rival state-of-the-art affine-invariant depth estimators.
Heat over time
- Now
- 3
- Peak
- 614 Nov, 00:00
- 24h change
- -49%
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.