Awesome GitHub RepositoriesMulti-Stage Refinement

Sana is a framework for high-resolution image and video synthesis based on a linear diffusion transformer. It provides a toolkit for the training, fine-tuning, and execution of text-to-image and text-to-video models, as well as a video generative world model capable of simulating physical environments with precise spatial control. The project is distinguished by its use of linear complexity layers to handle high resolutions and its support for long-form, minute-length video generation in real time. It implements a two-stage inference paradigm that separates structural generation from visual t

MochiDiffusion is a local client for Stable Diffusion that functions as an AI image generation studio. It provides a workspace for performing text-to-image, image-to-image, and inpainting tasks, enabling the production of high-resolution images offline using local hardware and neural engine acceleration. The project includes a local model manager for importing, organizing, and converting machine learning models into compatible formats for offline execution. It features a ControlNet integration tool to guide structural composition and spatial layout, alongside a dedicated image upscaler that u

This project is an AI-powered visual canvas and collaborative whiteboard framework. It functions as a customizable vector drawing engine and a tool for converting hand-drawn interface sketches and wireframes into functional code using artificial intelligence. The system distinguishes itself through the integration of AI agents that can read, modify, and generate visual diagrams directly on the canvas. It also provides a node-based workflow editor for building automation pipelines and data processing flows by connecting multimodal components. The platform covers a broad range of capabilities,

vibesdk 是一个代理式软件开发平台和框架，旨在协调能够从自然语言编写、调试和优化全栈应用程序的自主代理。它作为一个云原生应用程序编排器和 LLM 驱动的代码生成框架，通过迭代对话和多阶段代理行为将提示词转换为功能代码。 该项目的特色在于提供了一套完整的工具链，用于构建 AI 开发平台。这包括集成各种模型提供商、构建自定义 LLM 工具包以及通过无服务器部署工具链和程序化 TypeScript SDK 管理 AI 生成应用的整个生命周期。 该平台涵盖了广泛的功能，包括用于隔离执行和实时预览的 AI 沙箱编排、用于版本跟踪的 Git 后端虚拟文件系统，以及到无服务器工作者平台的自动化云部署。它还集成了用于数据库模式管理、分层密钥加密以及通过 WebSocket 进行实时状态同步的系统。 用户可以通过命令行界面或使用提供的 SDK 以编程方式管理项目工作流。

EchoMimic V2 是一个 AI 视频生成流水线和计算机视觉动画模型，旨在生成合成的人体动画。它作为一个生成式框架，通过将静态参考图像与从驱动视频中提取的姿态动作对齐，来创建半身视频。 该系统利用基于扩散的生成过程，结合潜在空间压缩和时间注意力机制，以确保帧间平滑过渡。它通过基于参考的编码保持人物身份一致性，并通过姿态驱动的运动调节来引导空间位置。 该项目包含多阶段图像细化功能，以提高面部细节和清晰度。它还提供了动画数据集准备工具，包括将视频数据下载并预处理为模型训练和推理所需的格式。

DiffBIR 是一个基于扩散的图像恢复框架，专为盲图像重建而设计。它利用生成式扩散先验，从具有未知或复杂退化的源中恢复高质量图像，而无需显式的退化模型。 该系统包括用于人脸恢复的专用模型，能够恢复退化肖像中的面部特征点、纹理和背景。为了在内存受限的硬件上支持高分辨率输出，它采用了一种平铺图像放大器，在采样过程中将图像划分为较小的补丁。 该框架涵盖了多阶段恢复管线和生成式图像放大。它结合了恢复模型训练功能，并应用专用权重来优化特定场景的增强效果。

Presenton is an AI-powered presentation engine and API designed to transform natural language prompts, uploaded documents, and structured data into professional slide decks. It functions as a generation service that leverages large language models to automate the creation of outlines, slide content, and visual assets. The system is distinguished by its support for both cloud-based and self-hosted infrastructure, allowing for the integration of local language models and image generators to ensure data privacy. It implements a Model Context Protocol server, enabling external AI agents to trigge

ComfyUI-LTXVideo is a generative framework and ComfyUI custom node extension for synthesizing high-fidelity video. It utilizes a latent diffusion and transformer-based system to create cinematic clips from text, image, and audio inputs, providing a modular interface for precise control over subject behavior and temporal consistency. The tool distinguishes itself with production-grade capabilities, including the generation of High Dynamic Range video in linear formats such as ARRI LogC3. It supports multimodal synchronization for audio-driven animation and lip-syncing, and allows for the creat

vibe-vibe is an LLM agent engineering framework and toolchain optimizer designed for orchestrating multi-agent systems. It serves as a comprehensive guide and methodology for transforming conceptual ideas into deployed applications through agentic software engineering. The project focuses on the orchestration of specialized AI agent roles with defined collaboration boundaries and iterative feedback loops. It provides frameworks for toolchain optimization, including the selection and evaluation of protocols that extend model capabilities and the design of standardized tool interfaces. The sys