vggt (alpha test)
Generate videos from text prompts
Training-free Video Relighting via Progressive Light Fusion
Scene detection using scenedetect library (updated)
Generate images from text prompts
Audio Conditioned LipSync with Latent Diffusion Models
Segment subjects in anime images
Create detailed video masks and propagations
Generate a color palette from an image
Calculate facial embeddings from images
Calculate similarity between two face images
Generate customized photos using face images and text prompts
A Diffusion Model for Video Inpainting
Remove background from images and videos
Generate images using text prompts
ColorFlow: Retrieval-Augmented Image Sequence Colorization