Awesome GitHub RepositoriesImage Diffusion Models

Stable Diffusion is a generative machine learning pipeline that synthesizes high-resolution visual content by performing iterative denoising within a compressed latent space. By mapping natural language embeddings into pixel outputs through conditioned probabilistic processes, the framework enables the generation of images from text prompts and the transformation of existing visual inputs based on semantic instructions. The architecture utilizes a modular execution environment that decouples model loading, scheduler logic, and inference components to support diverse hardware configurations. I

Sglang is a high-performance inference engine and serving system designed for large language and multimodal models. It provides a programmable interface for orchestrating complex generation workflows, enabling developers to coordinate multi-turn dialogues, tool invocations, and reasoning chains through a domain-specific language. The platform is built to support production-scale deployments, offering an OpenAI-compatible API that allows for integration with existing application ecosystems. The system distinguishes itself through a disaggregated architecture that separates compute-intensive pr

Flux is a diffusion model inference engine designed for text-to-image generation and image-to-image manipulation. It provides a system for executing open-weight models to transform natural language descriptions into visual imagery or to modify existing images. The project distinguishes itself through a flow-matching framework for image generation and a structural image controller. This controller allows for guided synthesis by using depth maps and Canny edge detection to constrain the geometry and composition of the output. The toolkit covers a broad range of image editing capabilities, incl

Audiocraft is a deep learning audio library and machine learning framework designed for training, fine-tuning, and evaluating generative models for music and sound effects. It functions as a text-to-music generative model and a neural audio codec, providing the tools necessary to compress audio signals into discrete representations and synthesize high-fidelity waveforms from textual descriptions. The framework is distinguished by its ability to combine multiple conditioning signals, allowing for the generation of audio based on text prompts, melodic excerpts, or style-based audio clips. It al

Lama Cleaner is an AI-powered image editing application focused on inpainting, object removal, and generative filling. It provides a suite of tools for erasing unwanted elements from photos and filling the resulting gaps using generative artificial intelligence. The project includes specialized capabilities for image outpainting to extend borders, background removal through object segmentation, and face restoration to fix visual defects. It also features an image upscaler to increase resolution and clarity via super-resolution AI, as well as a Stable Diffusion-based editor for replacing speci

F5-TTS is a text-to-speech system that utilizes a flow matching engine and diffusion transformers to generate fluent synthetic speech. It functions as a multilingual speech synthesizer and neural training framework, providing tools for voice cloning and high-performance inference serving. The project distinguishes itself through a voice cloning toolkit capable of mimicking specific speaker characteristics and tones from reference audio clips. It supports cross-lingual generation, allowing for the synthesis of audio across various global languages or the mixing of multiple languages within a s

This project is a machine learning research automation system designed to manage the full research lifecycle, from idea discovery to final paper submission. It utilizes markdown-based skill templates to execute autonomous research tasks and manage iterative loops of deep review and experimentation. The system distinguishes itself through integrated capabilities for academic communication and integrity auditing. It can automate the generation of LaTeX papers, conference slide decks, and evidence-grounded peer review rebuttals. To ensure rigor, it employs cross-model review routing and adversar

Z-Image is an AI image editing engine and generation framework designed for photorealistic synthesis and the refinement of diffusion models. It functions as a multilingual text-to-image renderer and a system for training custom foundation models to generate and edit visuals using natural language instructions. The project distinguishes itself through a reasoning-based prompt enhancer that expands simple descriptions into detailed visual instructions using a structured reasoning chain. It also features specialized capabilities for rendering high-quality Chinese and English typography within ge

This is a PyTorch implementation of a text-to-image model designed for synthesizing high-fidelity images from natural language descriptions. It utilizes a diffusion image generator to transform latent embeddings into visual data through an iterative denoising process. The system employs a two-stage latent mapping process, using a CLIP-based latent prior to map text embeddings to image embeddings before decoding them into pixels. It features a cascading diffusion decoder that produces high-resolution imagery by passing low-resolution outputs through a sequence of models at increasing scales.

RoomGPT is a generative AI image processor designed to transform photographs of existing rooms into redesigned interior spaces. It functions as an AI interior design generator and room visualizer that applies new styles and layouts to uploaded images using machine learning models. The system utilizes diffusion-based image transformation and prompt-template engineering to modify visual environments and generate home decor visualizations. These capabilities allow for the creation of diverse interior design variations based on specific style prompts. The infrastructure includes client-side imag

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Facechain is a generative AI toolchain and portrait generator designed to create personalized synthetic identities and consistent digital portraits. It provides a pipeline for training and refining diffusion models to produce subject-driven image synthesis from reference photos. The project focuses on digital twin generation, enabling the creation of a personalized model from a single image to maintain identity consistency across various poses and artistic styles. It utilizes identity fusion and similarity sorting to balance facial accuracy with stylized visual effects. The toolkit covers a

IC-Light is a diffusion-based image editor and generative tool designed for controlling the illumination of foreground subjects. It functions as an image relighting system that uses latent diffusion models to modify lighting effects on isolated subjects. The project provides two primary methods for lighting control: text-based relighting, which uses descriptive prompts and lighting directions, and background-based relighting, which conditions the foreground lighting to match the visual properties of a provided background image. Beyond illumination, the system includes a surface normal estima

This is a classifier-guided diffusion framework for high-fidelity image generation. It implements a cascaded diffusion pipeline that chains a base diffusion model with a dedicated upsampler to progressively increase image resolution in stages, and uses classifier-guided diffusion sampling to steer the reverse diffusion process toward higher-quality outputs. The framework provides tools for training diffusion models from scratch using distributed processes with gradient accumulation, as well as training classifier models that provide gradient-based guidance during sampling. It supports both un

AI NovelGenerator est un outil pour générer de la fiction longue en utilisant de grands modèles de langage. Il fonctionne comme un architecte narratif et un assistant d'écriture, automatisant la création de romans multi-chapitres tout en gérant la structure globale de l'histoire et le suivi des personnages. Le projet se distingue par un système de récupération de contexte sémantique et un vérificateur de cohérence d'histoire par IA. Ces outils utilisent la recherche sémantique pour rappeler des détails spécifiques de l'histoire à partir des chapitres précédents et scanner le texte généré pour détecter des contradictions d'intrigue ou des incohérences comportementales. Le système couvre un cycle de vie narratif complet, incluant la conception des fondations de l'histoire, le worldbuilding et la planification de la structure du roman. Il utilise un pipeline multi-étapes pour rédiger des chapitres cohérents et intègre un atelier de workflow créatif pour gérer les paramètres et la relecture.

Ce projet est un framework de synthèse vocale neuronale et un modèle PyTorch conçu pour synthétiser la parole humaine. Il convertit le texte écrit en audio synthétique en prédisant des spectrogrammes mel, qui servent de représentation intermédiaire pour la génération de voix. Le système inclut un modèle de conditionnement pour WaveNet afin d'assurer une sortie audio au son naturel. Il fournit un framework d'entraînement distribué qui utilise le traitement multi-GPU et la précision mixte automatique pour optimiser la vitesse d'entraînement et réduire l'utilisation de la mémoire. Le projet couvre le pipeline complet de synthèse vocale neuronale, de l'entraînement du modèle utilisant des jeux de données de texte et d'audio à la génération de voix artificielles. Il emploie un encodeur-décodeur convolutif et une attention séquence-à-séquence pour mapper les caractéristiques linguistiques aux trames acoustiques.

AnyText est un framework de synthèse visuelle de texte et un modèle de diffusion latente conçu pour générer et éditer du texte au sein d'images. Il fonctionne comme un générateur de texte par diffusion multilingue qui mélange les données de glyphes et de traits dans les caractéristiques d'image latente pour assurer un placement et un rendu précis des caractères. Le système permet la modification ou le remplacement de caractères et de mots existants dans les images tout en préservant le contexte visuel environnant. Il prend en charge la création d'effets de texte stylisés grâce à l'utilisation d'un pipeline de fusion de poids qui combine des poids de modèles spécialisés et des couches d'adaptation pour étendre les capacités linguistiques et esthétiques. Le framework couvre une gamme de fonctionnalités incluant la génération de texte visuel multilingue, la personnalisation de l'apparence du texte pour les polices et les couleurs, et l'entraînement de modèles texte-vers-image. Il inclut également des outils d'évaluation de la qualité pour quantifier la précision du texte visuel et la fidélité de l'image en utilisant des métriques de distance et de précision.

This project is a PyTorch-based generative model framework designed to transform noise into complex data distributions by learning vector fields and probability paths. It serves as a multimodal generative toolkit for producing synthetic text and images through learned probability flows. The library distinguishes itself by supporting continuous, discrete, and Riemannian manifold integrations. This allows the framework to handle a variety of data types, including categorical data via discrete-state flow matching and non-Euclidean spaces through Riemannian manifold integration. The toolkit cove

This project is a comprehensive instructional resource and course for building neural networks using PyTorch. It covers the fundamental building blocks of deep learning, including tensor manipulation, automatic differentiation, and the construction of modular neural network components. The repository serves as a technical guide for several specialized domains. It provides implementation details for computer vision tasks such as image classification, object detection, and semantic segmentation, as well as natural language processing workflows involving transformers, recurrent networks, and gen

ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,