LightGlue demo
OmniGen2: Unified Image Understanding and Generation.
The agent using over 9000 vision models from the HF Hub.
nanonets ocr / typhoon ocr / smoldocling / monkey ocr
Qwen2.5-VL 7B & 3B
260+ Impressive LoRA's For Flux.1
VideoRefer x VideoLLaMA3
Generate depth video from input video
Gradio demo for MatAnyone