Code of "ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution"

Train latent diffusion for real-world super-resolution.

Open-Sora: Democratizing Efficient Video Production for All

Official repository of the paper InstructBrush: Learning Attention-based Instruction Optimization for Image Editing

Officail Implementation for "ReNoise: Real Image Inversion Through Iterative Noising"

Official PyTorch implementation of "Ground-A-Score: Scaling Up the Score Distillation for Multi-Attribute Editing"

The implementation of "An item is Worth a Prompt: Versatile Image Editing with Disentangled Control"

InstructGIE: Towards Generalizable Image Editing

Official page for the work StableDrag, which is a stable dragging framework for point-based image editing.

[CVPR 2024] Official code release of our paper "Diff-Plugin: Revitalizing Details for Diffusion-based Low-level tasks"

Official Code Release for [SIGGRAPH 2024] DilightNet: Fine-grained Lighting Control for Diffusion-based Image Generation

Code for ICLR 2024 paper "Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators"

Text Image Inpainting via Global Structure-Guided Diffusion Models (Accepted by AAAI-24)

✏️ Edit One for All: Interactive Batch Image Editing (CVPR 2024)

[CVPR2024] Official code for Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation

Official implementation of the ECCV paper "SwapAnything: Enabling Arbitrary Object Swapping in Personalized Visual Editing"

Responsible Visual Editing

Ofiicial GoodDrag implementation.

HQ-Edit: A High-Quality and High-Coverage Dataset for General Image Editing

[ECCV'24] MaxFusion: Plug & Play multimodal generation in text to image diffusion models

Implementation of "Factorized Diffusion Autoencoder for Unsupervised Disentangled Representation Learning" (AAAI 2024)

Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis

TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing (CVPR 2024)

Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model (SIGGRAPH 2024)

Code Release for 'ReasonPix2Pix: Instruction Reasoning Dataset for Advanced Image Editing' (CVPRW 2024)

EditWorld: Simulating World Dynamics for Instruction-Following Image Editing

Official implementations for paper: Zero-shot Image Editing with Reference Imitation