Weifeng-Chen
Follow
Lists (7)
Stars
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Official Pytorch Implementation of Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think (ICLR 2025)
COYO-700M: Large-scale Image-Text Pair Dataset
Open and extensible continuous delivery solution for Kubernetes. Powered by GitOps Toolkit.
Official inference repo for FLUX.1 models
A general fine-tuning kit geared toward diffusion models.
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
[NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
Speed up Stable Diffusion with this one simple trick!
A method to increase the speed and lower the memory footprint of existing vision transformers.
VideoSys: An easy and efficient system for video generation
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
Official Repository of the paper "Trajectory Consistency Distillation"
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Open-Sora: Democratizing Efficient Video Production for All
Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".
PyTorch code and models for the DINOv2 self-supervised learning method.
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
[AAAI 2025] Follow-Your-Click: This repo is the official implementation of "Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts"
Implementation of "ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs"
A comprehensive collection of IQA papers