Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

Some personal original ComfyUI workflows

Code repository for Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model.

Single Image to 3D using Cross-Domain Diffusion for 3D Generation

Continuous Remeshing For Inverse Rendering

SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

Pytorch Implementation of "Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model"

[SIGGRAPH Asia 2024 (Journal Track)] StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal

StableDelight: Revealing Hidden Textures by Removing Specular Reflections

A bare metal programming guide (ARM microcontrollers)

A One Inch CMOS sensor (IMX283) camera board designed for Raspberry Pi

Machine learning from scratch

A comprehensive roadmap for aspiring Embedded Systems Engineers, featuring a curated list of learning resources.

real time face swap and one-click video deepfake with only a single image

[NeurIPS'21] Projected GANs Converge Faster

Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app

CodeGeeX4-ALL-9B, a versatile model for all AI software development scenarios, including code completion, code interpreter, web search, function calling, repository-level Q&A and much more.

这儿是一批由StyleGAN生成的定制化的人脸数据集

Here is a series of face generators based on StyleGAN2

[TOG 2022] SofGAN: A Portrait Image Generator with Dynamic Styling

[NeurIPS 2023] PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

A collection of state-of-the-art face super-resolution/hallucination methods

Graphic notes on Gilbert Strang's "Linear Algebra for Everyone", 线性代数的艺术中文版, 欢迎PR.

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

We write your reusable computer vision tools. 💜

StyleGAN Encoder - converts real images to latent space

Code for Talk-to-Edit (ICCV2021). Paper: Talk-to-Edit: Fine-Grained Facial Editing via Dialog.