[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

A pipeline parallel training script for diffusion models.

[CVPR‘ 2025 ] JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration

[ECCV2024] "Raindrop Clarity: A Dual-Focused Dataset for Day and Night Raindrop Removal", https://arxiv.org/abs/2407.16957

Support for miscellaneous image models. Currently supports: DiT, PixArt, HunYuanDiT, MiaoBi, and a few VAEs.

Pathways for Renewable Energy Planning coupling Short-term Hydropower OperaTion

我的 ComfyUI 工作流合集 | My ComfyUI workflows collection

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

The code for paper:Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models

[EMNLP'24] Code and data for paper "Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models"

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Unofficial implementation of InstantID for ComfyUI

InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

Semantic-Aware Discriminator for Image Super-Resolution

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

[AAAI'2024] DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity. First diffusion-based shadow removal performs robustly on hard, soft and self shadows. https://arxiv.o…

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

Lossless Training Speed Up by Unbiased Dynamic Data Pruning

Character Animation (AnimateAnyone, Face Reenactment)

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.