Stars
The official repository for DreamSampler (ECCV24)
the official code of "Diffusion-Based Image-to-Image Translation by Noise Correction via Prompt Interpolation" (ECCV2024)
[ICCV 2023] Consistent Image Synthesis and Editing
The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".
Official Implementation of Rethinking Score Distillation as a Bridge Between Image Distributions
AnimeDiffusion: Anime Diffusion Colorization
Implementation of Diffusart from CVPR 2023
Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning
Official pytorch implementation of the paper: "An Edit Friendly DDPM Noise Space: Inversion and Manipulations". CVPR 2024.
Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"
Official implementation of AAAI-2024 paper "Enhancing RAW-to-sRGB with Decoupled Style Structure in Fourier Domain"
Code for RSHazeDiff: A Unified Fourier-aware Diffusion Model for Remote Sensing lmage Dehazing
[CVPR2024] Official code for Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation
collection of diffusion model papers categorized by their subareas
[CVPR 2024] Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation
Unofficial implementation of paper NULL-text Inversion for Editing Real Images using Guided Diffusion Models ( https://arxiv.org/abs/2211.09794 )
Official implementation of "DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization" (CVPR 2024)
FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)
Official repo for Artist: Aesthetically Controllable Text-Driven Stylization without Training
[ICCV 2023 Oral] "FateZero: Fusing Attentions for Zero-shot Text-based Video Editing"
Software that can perform photorealistic style transfer without the need of any post-processing steps.
StyleShot: A SnapShot on Any Style. 一款可以迁移任意风格到任意内容的模型,无需针对图片微调,即能生成高质量的个性风格化图片!
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.