Description

Open Vision Banana is a fine-tuned FLUX.2 transformer that performs multiple visual perception tasks—including semantic, instance, and referring segmentation, as well as depth and surface-normal estimation—through a single model using natural language prompts. It demonstrates how generative image models can be repurposed for precise geometric and semantic scene understanding.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.