Stars
rCM: SOTA Diffusion Distillation & Few-Step Video Generation
Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.
Kandinsky 5.0: A family of diffusion models for Video & Image generation
A Unified and Flexible Inference Engine with Cache Acceleration, Parallelism and Quantization for 🤗Diffusers.
This is the official implementation of "FastFace: Tuning Identity Preservation in Distilled Diffusion via Guidance and Attention"
[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
Text and image to video generation: Kandinsky 4.0 (2024)
Implementation of Implicit Reparameterization Trick
Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"
Kandinsky x Deforum — generating short animations
Official implementation of "Unraveling the Hessian: A Key to Smooth Convergence in Loss Function Landscapes"
Cutting-edge Python library designed for generative image augmentation!
Official inference repo for FLUX.1 models
Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model
Awesome diffusion Video-to-Video (V2V). A collection of paper on diffusion model-based video editing, aka. video-to-video (V2V) translation. And a video editing benchmark code.
Efficient DL/ML Models Seminars
Paint by Inpaint: Learning to Add Image Objects by Removing Them First
The aim of this repository is to test and implement Flow-Matching-based models