ZhenYangCS
Follow
Starred repositories
A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.
A curated list of papers, code and resources pertaining to image harmonization.
Diffusers reimplementation for https://rf-inversion.github.io/
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement 🔥
Trying to implement https://arxiv.org/abs/2305.08891
Official inference repo for FLUX.1 models
Official PyTorch implementation of "Framer: Interactive Frame Interpolation".
Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers
[NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
a collection of awesome autoregressive visual generation models
51
Updated Dec 15, 2024
Nodes for image juxtaposition for Flux in ComfyUI
Neighborhood Attention Extension. Bringing attention to a neighborhood near you!
ControlNet++: All-in-one ControlNet for image generations and editing!
Official implementation of CVPR 2024 paper: "FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition"
Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet
Official Implementation of LOTUS: Diffusion-based Visual Foundation Model for High-quality Dense Prediction
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
Collect super-resolution related papers, data, repositories
The official Pytorch Implementation for ElasticDiffusion: Training-free Arbitrary Size Image Generation (CVPR 2024)
Official repository for "CFG++: manifold-constrained classifier free guidance for diffusion models"