Outpainting with Stable Diffusion on an infinite canvas.
Directory
Search results
Published directory entries matching your search.
Langflow is a platform for building and deploying AI-powered agents and workflows, with a visual authoring interface and built-in API and MCP servers. It supports major LLMs, vector databases and AI tools, and allows deployment as an API, JSON export or MCP server.
Lucid Sonic Dreams is an open-source project that syncs GAN-generated visuals to music. It uses NVLabs StyleGAN2 by default, with pre-trained models from Justin Pinkney's consolidated repository, and allows custom weights and other GAN architectures. It requires TensorFlow 1.15, supports Python 3.6 and 3.7, and is installed with pip.
NeuroNER is a program that performs named-entity recognition using neural networks. It relies on Python 3 and TensorFlow 1.0+, optionally uses the BRAT annotation tool, and provides installation instructions, sample datasets and pretrained models.
OpenAI's point cloud diffusion for 3D model synthesis.
PEFT is a library of parameter-efficient fine-tuning methods from Hugging Face. It adapts large pretrained models by fine-tuning only a small number of extra parameters instead of all model parameters, which decreases computational and storage costs. It is integrated with Transformers, Diffusers and Accelerate.
Creates or edits images with generative models and visual controls.
Easily compute CLIP embeddings and build a CLIP retrieval system with them.
Scikit-Opt is an open-source Python library that implements a range of optimization algorithms. Its features include genetic algorithms, particle swarm optimization, simulated annealing, ant colony optimization, immune algorithm, artificial fish swarm algorithm, differential evolution, and tools for the traveling salesman problem. The project is hosted on GitHub and accepts community contributions.
Stable Diffusion WebUI Forge is a platform built on top of Stable Diffusion WebUI (based on Gradio) that aims to ease development, optimize resource management, speed up inference and study experimental features. It is based on SD-WebUI 1.10.1 and syncs with the original WebUI periodically.
segment-anything (SAM) is an open-source GitHub repository from Meta's Facebook Research team for the Segment Anything Model. It provides code for running model inference, links to download trained model checkpoints, and example notebooks demonstrating model usage, with support for segmenting objects in images and videos via SAM 2.
StylePile is a prompt generation helper script and extension for AUTOMATIC1111/stable-diffusion-webui and compatible forks. It mixes and matches elements that affect the style of generated results, with elements placed in a specific order and given strength values. It appears under the Scripts dropdown in txt2img and img2img.
Stability Matrix is a multi-platform package manager designed for Stable Diffusion. It offers one-click installation and updates for Stable Diffusion Web UI packages, a built-in inference interface for the system, and a launcher with a syntax-highlighted terminal emulator and routed GUI input prompts.
Stable Diffusion Akashic Records is a GitHub repository collecting studies, art styles, prompts and other resources for exploring Stable Diffusion. It includes lists of art styles and artists, a keyword list, prompts and guides, and notes that prompts must be 75 tokens or less and are case insensitive.
StableStudio is an open-source community interface for generative AI, developed as the open-source counterpart to the DreamStudio platform. The project repository includes quick start guides, an about section, and a FAQ for users.
Creates or edits images with generative models and visual controls.
Unprompted is a templating language for Stable Diffusion workflows, distributed as an extension for the Automatic1111 WebUI. It is built around shortcodes and includes more than 70 shortcodes, such as conditionals, file imports and choose blocks for wildcards. Templates can be organized into folders and subfolders, and the language supports nested shortcodes and recursion.
Automatically create masks for Stable Diffusion inpainting using natural language.
threestudio is a framework for 3D content generation, described by its repository as a unified framework. The project includes configuration files, documentation, scripts and a Gradio application. It is released under the Apache-2.0 license.
Creates or edits images with generative models and visual controls.
Upscaling refers to the ultimate-upscale-for-automatic1111 project, an upscaling extension for the AUTOMATIC1111 Stable Diffusion web UI. The public repository includes instructions, reference materials, example content, and API usage documentation for the tool, and contributions to the project are accepted from the public.
A public archive of acceleration techniques for the Stable Diffusion model intended to help generate images faster and more efficiently. It covers AITemplate, nvFuser, TensorRT and FlashAttention, with example images and benchmarks. The repository was archived by the owner on Oct 24, 2025, and is now read-only.
ZPar is an open-source statistical parser hosted on GitHub. It offers universal language support contingent on the availability of training data, with dedicated language-specific features for Chinese and English. The tool supports word segmentation, part-of-speech tagging, dependency parsing, and phrase-structure parsing.
AnkiDroid is the official Android port of the open-source Anki spaced repetition flashcard system. It supports spaced repetition learning using the AI-optimized FSRS algorithm, and allows users to create flashcards with text, images, sounds and MathJax content. It offers features including night mode, AnkiWeb syncing, text-to-speech integration, access to over 10,000 premade decks, and the ability to add cards from other applications.