Stars
Janus-Series: Unified Multimodal Understanding and Generation Models
Official Repository of **CaPa**: Carve-n-Paint Synthesis for Efficient 4K Textured Mesh Generation
Extracts and formats text annotations from a PDF file
Official implementation of "MangaNinja: Line Art Colorization with Precise Reference Following"
HunyuanVideo: A Systematic Framework For Large Video Generation Model
A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
[WACV 2025] Official implementation for the paper "Diffusion-based Visual Anagram as Multi-task Learning"
A theme for Slidev, inspired by the Frankfurt theme in Beamer.
🎞️ [NeurIPS'24] MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
A markdown based tool for slide deck creation.
MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D
Audio Beat and Tempo Tracking
Stable-Hair: Real-World Hair Transfer via Diffusion Model (AAAI 2025)
3DGANTex: 3D Face Reconstruction with StyleGAN3-based Texture Synthesis from Multi-View Images
DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 Spotlight.
🚀 [ICLR 2025] Pytorch implementation of 'Fast Feedforward 3D Gaussian Splatting Compression'
Code of Pyramidal Flow Matching for Efficient Video Generative Modeling
Select a portrait, click to move the head around (please use your own space / GPU!)
Official Implementation of KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion Models
[ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration
[NeurIPS 2024]Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs
Statewide Visual Geolocalization in the Wild (ECCV 2024)
Dynamic 2D Gaussians: Geometrically accurate radiance fields for dynamic objects
This is an open collection of state-of-the-art (SOTA), novel Text to X (X can be everything) methods (papers, codes and datasets).
Text-to-Music Generation with Rectified Flow Transformers