image synthesis
High-Resolution Image Synthesis with Latent Diffusion Models
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
DALL·E Mini - Generate images from a text prompt
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
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.
Using Low-rank adaptation to quickly fine-tune diffusion models.
Official Implementation for "TEXTure: Text-Guided Texturing of 3D Shapes"
Upload a photo of your room to generate your dream room with AI.
fast-stable-diffusion + DreamBooth
Code for Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation (CVPR 2021)
Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
AI绘画资料合集（包含国内外可使用平台、使用教程、参数教程、部署教程、业界新闻等等） Stable diffusion、AnimateDiff、Stable Cascade 、Stable SDXL Turbo
Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.
[ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators
fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。
Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
The source code of the ICCV2021 paper "PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering"
Generate 3D objects conditioned on text or images
Code for Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach
[TVCG 2023] 3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation
An algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video.