113
Qwen2.5 VL 32B Instruct Demo
ð
Chat with images and videos using Qwen
Extract text from images using OCR
Generate personalized images with a face preservation
Interact with Florence-2 to analyze images and generate descriptions
Generate key frames and videos from a single image
In-browser speech recognition w/ word-level timestamps
Generate images from prompts using powerful LORA models
Apply the motion of a video on a portrait