One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer

A CLI tool to train LoRA adapters for text-to-image models using a folder of images with intelligent content-aware cropping

Hybrid-Hierarchical Fashion Graph Attention Network for Compatibility-Oriented and Personalized Outfit Recommendation

Repo for Qwen Image Finetune

Synthetic defect generation for minority datasets to improve classification accuracy

[ICCV 2025] Code Implementation of "Any2AnyTryon: Leveraging Adaptive Position Embeddings for Versatile Virtual Clothing Tasks"

Train Qwen-Image-Edit LoRAs on DPO datasets

🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

Official Repository of "OmniTry: Virtual Try-On Anything without Masks"

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Qwen-Image text to image lora trainer

LoRA training of FLUX.1 Kontext[dev] for the Virtual Try-Off task.

OmniGen2: Exploration to Advanced Multimodal Generation.

OCR using VLM

Official implementation of "XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation".

This repository contains the code for training FLUX.1-Fill-dev.

This repository contains the code for training FLUX.1-Kontext-dev, a powerful image editing model.

[CVPR'25-Demo] Official repository of "TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models".

[ICME2025] DPDEdit: Detail-Preserved Diffusion Models for Multimodal Fashion Image Editing

Official inference repo for FLUX.1 models

Scripts to teach Flux the task of image editing from language with the Flux Control framework.

This project focuses on the application effect of existing virtual fitting model on men's clothing in different seasons, and deeply analyzes its technical bottleneck and improvement direction.