Stars
人工智能学习资料超全整理，包含机器学习基础ML、深度学习基础DL、计算机视觉CV、自然语言处理NLP、推荐系统、语音识别、图神经网路、算法工程师面 8000 题
Official implementations for paper: VACE: All-in-One Video Creation and Editing
Spirit Lora Trainer is a robust toolkit for training Flux1-LoRA models with a focus on simplicity and reliability and based on kohya-ss script. 智灵训练器.
OneTrainer is a one-stop solution for all your stable diffusion training needs.
Dead simple FLUX LoRA training UI with LOW VRAM support
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
kingbri1 / flash-attention
Forked from Dao-AILab/flash-attentionFast and memory-efficient exact attention
Rembg is a tool to remove images background
这个工具利用Ollama的多个视觉模型，高效地对图片进行打标，并通过AI进行润色优化。如果你觉得对大量图片进行打标是一件繁琐的事情，那么这个工具就是为你量身打造的。 主要特点： 多模型打标：利用各种开源模型，同时对图片进行打标。 AI润色：自动优化和润色已打标的图片。 成本效益：通过使用免费的开源模型，减少对昂贵的GPT-4V的依赖。 无论你是开发者、数据科学家，还是需要处理大量图片的用户，…
The ultimate training toolkit for finetuning diffusion models
Wan: Open and Advanced Large-Scale Video Generative Models
SkyReels V1: The first and most advanced open-source human-centric video foundation model
The official implementation of CVPR'25 Oral paper "Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise"
A pipeline parallel training script for diffusion models.
ComfyUI native implementation of IC-Light
HunyuanVideo: A Systematic Framework For Large Video Generation Model
A small .NET package to generate YouTube-like hashes from one or many numbers. Use hashids when you do not want to expose your database ids to the user.
[CVPR2025 Highlight] Video Generation Foundation Models: https://saiyan-world.github.io/goku/
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Scalable and memory-optimized training of diffusion models
Official Code for DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing (CVPR 2024)
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience