zhangsdly

llama3

The official Meta Llama 3 GitHub site

DeepLearning

深度学习入门教程, 优秀文章, Deep Learning Tutorial

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

StoryDiffusion

Create Magic Story!

OUCML

llama3-Chinese-chat

Llama3 中文仓库（聚合资料，各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

Lumina-T2X

Lumina-T2X is a unified framework for Text to Any Modality Generation

MagicClothing

Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis

DeepLearing-Interview-Awesome-2024

AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目

PuLID

Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

visual_anagrams

Code for the paper "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models"

LLaVA-pp

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

ConsistentID

Customized ID Consistent for human

Groma

Grounded Multimodal Large Language Model with Localized Visual Tokenization

ComfyUI_MagicClothing

unofficial implementation of Comfyui magic clothing

PLLaVA

Official repository for the paper PLLaVA

Ctrl-Adapter

Official implementation of Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model

ID-Animator

animate-your-word

Official implementations for paper: Dynamic Typography: Bringing Text to Life via Video Diffusion Prior

Parts2Whole

[Arxiv 2024] From Parts to Whole: A Unified Reference Framework for Controllable Human Image Generation

MultiBooth

[arXiv 2024] MultiBooth: This repo is the official implementation of "MultiBooth: Towards Generating All Your Concepts in an Image from Text"

EasyAnimate

📺 Generate your animation easily

stylus

PairCustomization

TF-GPH

Training-and-pormpt Free General Painterly Image Harmonization Using image-wise attention sharing

TalkingGaussian

[arXiv] TalkingGaussian: Structure-Persistent 3D Talking Head Synthesis via Gaussian Splatting

Paint-by-Inpaint

Paint by Inpaint: Learning to Add Image Objects by Removing Them First

CutDiffusion

CutDiffusion: A Simple, Fast, Cheap, and Strong Diffusion Extrapolation Method

TiNO-Edit

TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing (CVPR 2024)

UVMap-ID