A powerful set of tools for ComfyUI

ComfyUI nodes to crop before sampling and stitch back after sampling that speed up inpainting

A set of nodes for ComfyUI that can composite layer and mask to achieve Photoshop like functionality.

Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance

PositionBT is a simple, fast, and customizable backtesting framework that empowers traders to efficiently develop and optimize trading strategies with ease.

A collection of ComfyUI nodes to create scenes with random procedural generation.

A Faster LayoutReader Model based on LayoutLMv3, Sort OCR bboxes to reading order.

stock股票.获取股票数据,计算股票指标,筹码分布,识别股票形态,综合选股,选股策略,股票验证回测,股票自动交易,支持PC及移动设备。

Tiny AutoEncoder for Stable Diffusion

👗 DM-VTON: Distilled Mobile Real-time Virtual Try-On

A curated list of awesome research papers, projects, code, dataset, workshops etc. related to virtual try-on.

Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning

S2D2: Simple Stable Diffusion based on Diffusers (Hires.fix on jupyter notebook, ipython or python interactive shell)

[CVPR 2024] When StyleGAN Meets Stable Diffusion: a W+ Adapter for Personalized Image Generation

[CVPR'24] Interactive3D: Create What You Want by Interactive 3D Generation

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

[NeurIPS 2024] Official code for "Neural Gaffer: Relighting Any Object via Diffusion"

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

A controllable image composition model which could be used for image blending, image harmonization, view synthesis.

Diffusion Model-Based Image Editing: A Survey (arXiv)

Official implementations for paper: Anydoor: zero-shot object-level image customization

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

collection of diffusion model papers categorized by their subareas

replace any object you want on the image with whatever you want

OneTrainer is a one-stop solution for all your stable diffusion training needs.

ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

[CVPR'24] MuRF: Multi-Baseline Radiance Fields

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

[CVPR 2024] Official implementation of "SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration"