Multimodal OCR3
Chandra-OCR / Nanonets-OCR2 / olmOCR-2 / Dots.OCR
generate a video from an image with a text prompt
Generate high-quality images from text prompts
Fast 4 step inference with Qwen Image Edit 2509
Edit image camera angle with interactive 3D controls
Edit images using natural language prompts
Fast high quality video with audio generation with FA3
Generate images from text prompts with customizable resolution
An interactive demo for the DeepSeek-OCR model.
Wan2.2 Animate