HighCWu

DiffiT

Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation

dora

Implementation of DoRA

X-Adapter

[CVPR 2024] X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model

HeadStudio

HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting.

pixelsplat

[CVPR 2024 Oral] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacchi, and Vincent Sitzmann

omniavatar-proj

WhisperSpeech

An Open Source text-to-speech system built by inverting Whisper.

SUPIR

SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild

DreamWaltz

[NeurIPS 2023] Official implementation of the paper "DreamWaltz: Make a Scene with Complex 3D Animatable Avatars".

ProPainter

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

AnimateLCM

AnimateLCM: Let's Accelerate the Video Generation within 4 Steps!

sdxl-koala

Compressing SDXL via knowledge-distillation

MiniCPM

MiniCPM-2B: An end-side LLM outperforms Llama2-13B.

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

YOLO-World

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

tauri-ui

🦀 Create modern Tauri desktop apps in just a few simple steps with shadcn/ui. React, Next.js, Sveltekit.

compact-ngp

ChatLM-mini-Chinese

中文对话0.2B小模型（ChatLM-Chinese-0.2B），开源所有数据集来源、数据清洗、tokenizer训练、模型预训练、SFT指令微调、RLHF优化等流程的全部代码。支持下游任务sft微调，给出三元组信息抽取微调示例。

I2V-Adapter-repo

I2V-Adapter: A General Image-to-Video Adapter for Video Diffusion Models

PhotoMaker

PhotoMaker

Moore-AnimateAnyone

TachiyomiSY

Free and open source manga reader for Android

metahuman-stream

Real time streaming digital human based on nerf

TOVA

Token Omission Via Attention

TRIPS

LongLM

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

GRAM

GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation (CVPR 2022 Oral)

GRAM-HD

PyTorch implementation of the ICCV paper "GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifolds"

headcraft

HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMs

UniDream