Various scripts, mostly intended to help with model training and dataset creation

A set of nodes for basic Llama 3.2 Vision support in ComfyUI

Make abliterated models with transformers, easy and fast

Run ComfyUI workflows on multiple local GPUs/networked machines.

Official repo for the #tidytuesday project

Recreations of W.E.B Dubois's Data Portraits

Use Florence 2 to generate prompt words such as flux, sd3, kolors, etc

LoRa trainer for SDXL and SD15

Custom ComfyUI nodes for Vision Language Models, Large Language Models, Image to Music, Text to Music, Consistent and Random Creative Prompt Generation

Massive Dev Chart command line tools

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.

LDSR custom node for ComfyUI

Comfy Nodes (and a CLI script) for shuffling around layers in transformer models, creating a curious confusion.

ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.

Awesome list dedicated to Windows Subsystem for Linux

The Hugging Face Course on Transformers for Audio

Gradio based tool to run opensource LLM models directly from Huggingface

tiny vision language model

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Open-source tool to enforce privacy & security best-practices on Windows, macOS and Linux, because privacy is sexy

A list of Free Software network services and web applications which can be hosted on your own servers

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

fast-stable-diffusion + DreamBooth

Prune stable diffusion checkpoints.

a state-of-the-art-level open visual language model | 多模态预训练模型