Kaz03

ComfyUI-GGUF

GGUF Quantization support for native ComfyUI models

Paints-UNDO

Understand Human Behavior to Align True Needs

CityClassifiers

Code for my collection of predictors/classifiers/etc

ImageVectorViaLayerDecomposition

The source code of the paper: Image vectorization and editing via linear gradient layer decomposition.

PuTT

CFGpp

Official repository for "CFG++: manifold-constrained classifier free guidance for diffusion models"

ReNO

ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization

ComfyUI_TensorRT

LLaVA-NeXT

Scrapegraph-ai

Python scraper based on AI

aesthetic-scorer

A simple aesthetic scorer + pruner + website you can run to view the results from the scoring with

Omost

Your image is almost there!

CLIP-fine-tune

Fine-tuning code for CLIP models

Rope

GUI-focused roop

minRF

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

DMD2

Face-Adapter

IC-Light

More relighting!

PuLID_ComfyUI

PuLID native implementation for ComfyUI

CharacterFactory

🔥 CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models

Long-CLIP

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

SMBSync2

This application performs file synchronization between an Android device and a PC/NAS via wireless LAN using SMB v1/v2/v3 protocol.

LaVi-Bridge

[ECCV 2024] Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation

Euler-Smea-Dyn-Sampler

A sampler base on Euler, aim at generating better picture/一种基于Euler的采样方法，旨在生成更好的图片

CSD

CoMat

Official code for 💫CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching

MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

champ

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

cobra

Cobra: Extending Mamba to Multi-modal Large Language Model for Efficient Inference

ELLA

ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment