PHOTOREALISTIC HUMAN RECONSTRUCTION w/ CROSS-SCALE DIFF
Create a 1M faces 3D colored model from an image!
Real-time video captioning powered by FastVLM
Open Models and Data for Training Robust Speech Recognition
https://github.com/hvoss-techfak/TF-JAX-IK
Generate images by combining styles and subjects
Identify 3D objects in images using text prompts
LORE Image Editing
Qwen Image with ControlNet Union
exapand images with Qwen Image Edit