[CVPR 2025] Learning Flow Fields in Attention for Controllable Person Image Generation - franciszzj/Leffa
About Leffa : Leffa generates high-quality person images with controllable pose, expression, and attire. It utilises flow fields in attention to create realistic, varied images from single input faces.
Realistic 3D avatar creation
AI-assisted performance editing
Black and white image colorizing
Enhances quality of JPG and PNG images effortlessly
Generate 3D animations from video in seconds
One-click video transcription
AI Video Enhancer
Remove blemishes and imperfections from old photographs
AI-powered tattoo design generation