Directory
Published directory entries matching your search.
Multidiffusion Upscaler For Automatic1111 is an AI Image Generation project hosted on GitHub that provides tiled diffusion and VAE optimization for the Stable Diffusion web UI, distributed under the CC BY-NC-SA 4.0 license.
An open-source model registry that uses an image registry to distribute machine learning models. Users upload and download models with ormb pull and ormb push, and describe model information in ormbfile.yaml, similar to a Dockerfile.
Paper2GUI is an AI desktop application toolbox that is free and ready to use out of the box. It supports more than 10 AI models covering speech synthesis, video frame filling, video overscoring, target detection, image stylization and OCR recognition, on Windows, Mac OS and Linux.
pixray is an image generation system combining perception engines, CLIP-guided GAN imagery and CLIPDraw. It is a Python library and command line utility that can also run in Google Colab notebooks or inside Docker using Cog. Installation requires a recursive git clone and a fresh Python 3.8 environment.
prompt-to-asset is a GitHub repository containing an MCP server and command-line interface tool for generating production-grade software assets including logos, app icons, favicons, Open Graph images and illustrations. The tool routes requests across more than 30 image models, supports zero-key initial usage, and includes validation functionality to review assets before they are shipped.
SD Dynamic Prompts is a custom script built for the AUTOMATIC1111 stable-diffusion-webui. It implements a small template language that enables random generation of prompts for use with Stable Diffusion image generation workflows.
timm is a collection of PyTorch image encoders and backbones, including train, eval, inference and export scripts with pretrained weights. It covers architectures such as ResNet, EfficientNet, Vision Transformer, MobileNet and ConvNeXt.
Creates or edits images with generative models and visual controls.
Tool designed to streamline the fine-tuning of various AI models, offering support for multiple configurations and architectures.
Optimized Stable Diffusion modified to run on lower GPU VRAM.
Creates or edits images with generative models and visual controls.
Collection of stable diffusion webui colab for different checkpoints.
Civitai is a platform where people share stable diffusion models, including textual inversions, hypernetworks, aesthetic gradients and VAEs. Users can create an account, upload their models, browse models shared by others, and leave comments and feedback to support collaboration and knowledge sharing. The project is built with Next.js, tRPC, and Prisma with Postgres.
ClearTK is a framework for developing statistical natural language processing components in Java, built on top of Apache UIMA. It is developed by the Center for Computational Language and Education Research (CLEAR) at the University of Colorado at Boulder. The project is built with Maven, and the repository includes sub-projects such as cleartk-feature and modules for several machine learning libraries.
ComfyUI-ZLUDA is a Windows-only version of ComfyUI that uses ZLUDA to improve performance with AMD GPUs. It is a fork of Comfy-Org/ComfyUI and keeps the graph/nodes interface for Stable Diffusion.
This GitHub repository hosts the official Deforum extension for AUTOMATIC1111's Stable Diffusion web user interface. The extension integrates Deforum functionality into the Stable Diffusion webui, and the repository includes resources such as a FAQ, getting started guide, and known issues list for users.
Dione is an Electron-based open-source application designed to install complex applications with a single click, without a terminal or technical knowledge. Developers can distribute apps through a JSON script file. The repository is archived and read-only.
Frankensteinian amalgamation of notebooks, models and techniques for the generation of AI Art and Animations.
Collection of Google Colab Notebooks for ML Arts.
FEDOT is an open-source framework for automated modeling and machine learning. It provides automatic generative design of machine learning pipelines, with an evolutionary approach supporting classification, regression, clustering and time series prediction. Pipelines are represented as graphs defining connections between data preprocessing and model blocks. It is distributed under the 3-Clause BSD license.
GANSpace is a public GitHub repository for the research project 'Discovering Interpretable GAN Controls', which was presented at the NeurIPS 2020 conference. The repository includes setup instructions, usage guides, and resources for reproducing the project's results.
Tool used to create multiple different instances of artworks based on provided layers.
Creates or edits images with generative models and visual controls.
Invoke AI is a creative engine for Stable Diffusion models hosted on GitHub, designed to enable professionals, artists, and enthusiasts to generate visual media using AI-driven technologies, featuring an industry-standard web user interface and serving as the foundation for multiple commercial products.
