Starred repositories
该项目包括一个基于 GPT 等大语言模型的长篇小说生成器,同时还有各类小说生成 Prompt 以及教程。我们欢迎社区贡献,持续更新以提供最佳的小说创作体验。
A high-throughput and memory-efficient inference and serving engine for LLMs
Notion-style WYSIWYG editor with AI-powered autocompletion.
Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning
ControlNet++: All-in-one ControlNet for image generations and editing!
[CVPR2024] MotionEditor is the first diffusion-based model capable of video motion editing.
Understand Human Behavior to Align True Needs
Official implementation of ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation
AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation
PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
InstantID-ROME: Improved Identity-Preserving Generation in Seconds 🔥
[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"
Fast and memory-efficient exact attention
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis
[ECCV 2024] HiDiffusion: Increases the resolution and speed of your diffusion model by only adding a single line of code!
[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild
CnSTD: 基于 PyTorch/MXNet 的 中文/英文 场景文字检测(Scene Text Detection)、数学公式检测(Mathematical Formula Detection, MFD)、篇章分析(Layout Analysis)的Python3 包
Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"
[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Accepted as [NeurIPS 2024] Spotlight Presentation Paper
Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.