Unified Framework for Generalized Video Face Restoration
Dense Grounded Understanding of Images and Videos
FitDiT is a high-fidelity virtual try-on model.
GANs are so back!
Gaze Target Estimation
Video Super-Resolution with Text-to-Video Model
https://huggingface.co/papers/2501.03006
Gaze detection using Moondream
Audio Conditioned LipSync with Latent Diffusion Models
Estimate CO2 activities from an image
Animation Sketches sequence Colorization
Build support agent with CrewAI multi-agents and Gradio
Reconstruct 3D Gaussians from unposes images.