Qwen/Qwen3.6-27B
Image-Text-to-Text • 28B • Updated • 6.9M • • 2.15k
Upscale images using custom-trained models
Generate detailed captions or prompts for any image
ZIM: Zero-Shot Image Matting for Anything demo
Generate descriptive captions for any image
Extract foreground and replace background using image matting
Generate videos and key frames from a single image
Remove background from photos with accurate segmentation
Segment objects in images using text prompts or scribbles
Generate depth map from any photo
Apply image transformations with Albumentations