A minimal and universal controller for FLUX.1.

Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"

UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization

GitHub repository for the paper 'Personalized Restoration via Dual-Pivot Tuning'.

Finetune Llama 3.3, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

Implementation of aspect ratio bucketing for training generative image models as described in: https://blog.novelai.net/novelai-improvements-on-stable-diffusion-e10d38db82ac

A general fine-tuning kit geared toward diffusion models.

[WACV 2025] MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning

Inference Microsoft Florence2 VLM

Tiled Diffusion, MultiDiffusion, Mixture of Diffusers, and optimized VAE

Some awesome comfyui workflows in here, and they are built using the comfyui-easy-use node package.

BizyAir: Comfy Nodes that can run in any environment.

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution

A collection of design patterns/idioms in Python

Stable Diffusion XL training and inference as a cog model

Containers for machine learning

Head detection model based on Ultralytics YoloV8

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

My learning notes/codes for ML SYS.

An infinite Pinterest crawler/scraper. Crawl image with inifnite-scroll!

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

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

AcadHomepage: A Modern and Responsive Academic Personal Homepage

Pytorch0.4.1 codes for InsightFace