Qwen/Qwen-Image-Edit-2511
Image-to-Image β’ 20B β’ Updated β’ 255k β’ β’ 1.45k
Generate captions, detections, and segmentations from images
Analyze human behaviors from videos
IDEA Research's Most Capable Open-Set Object Detection Model
Track, rank and evaluate open LLMs and chatbots
Manipulate images by dragging points
Clean and edit images with AI-powered inpainting
Generate creative Stable Diffusion prompts