CatV2TON: Taming Diffusion Transformers for Vision-Based Virtual Try-On with Temporal Concatenation
Paper
•
2501.11325
•
Published
•
4
Extend images using prompts and alignment options
Extract garment images from everyday images!
Colorize black-and-white images with text prompts
Generate a video from text or an image
QwQ-32B-Preview