Image & VideoIntermediate
165kPython+109/daypushed 222d ago
Use it for: Generate and edit images locally through a browser interface for Stable Diffusion, with txt2img, img2img, inpainting and upscaling.
Quick start
- Install Python and Git
- Clone the repo and follow the README install instructions
- Run the one-click install and run script
- Open the web UI and try txt2img or img2img
Image & VideoIntermediate
137kPython+100/daypushed 0d ago
Use it for: Build and run diffusion-model workflows for AI content creation using a modular graph and node interface.
Quick start
- Clone the repo or download a release and follow the README install section
- Download a model checkpoint and place it in the models folder
- Launch ComfyUI and open the node graph in your browser
- Connect nodes and queue a generation
129kPython+137/daypushed 1d ago
Use it for: Generate high-definition short videos automatically from a topic or keyword, including script, footage, subtitles and background music.
Quick start
- Download the latest release or clone the repo
- Follow the README install section to set up Python 3.11+ and dependencies
- Configure your LLM provider settings
- Open the WebUI, enter a topic or keyword, and generate a video
Image & VideoIntermediate
29.9kJavaScript+24/daypushed 1d ago
Use it for: Run a self-hosted studio for generating AI images and videos with 600+ models and no content filters.
Quick start
- Clone the repo and follow the README install section
- Set up the MuAPI access the app is powered by
- Start the app and open one of the studios
- Enter a prompt to generate an image or video
Image & VideoIntermediate
28.5kTypeScript+19/daypushed 0d ago
Use it for: Generate, refine and iterate on images with Stable Diffusion models through a web UI, with a canvas and workflow builder.
Quick start
- Check that your hardware is compatible
- Open the Installation and Updates docs linked in the README
- Download and install Invoke following those instructions
- Launch the web UI and start generating images
Image & VideoIntermediate
20.6kTypeScript+285/daypushed 0d ago
Use it for: Let AI coding agents clone a viral video as an editable workflow, then swap faces, words and B-roll to make many variants.
Quick start
- Install the skill: npx skills add hypit-ai/hypit -g
- Open your coding agent (e.g. Claude Code or Codex) so it can prepare the Hypit executable
- Drop in a video, start from a template, or describe the video you want
- Configure a model service, either your own API or local models, if you need generation
Image & VideoIntermediate
17.8kPython+205/daypushed 2d ago
Use it for: Rebuild an object from a reference image as a code-only, animation-ready Three.js 3D model without photogrammetry or downloaded assets.
Quick start
- Clone the repo and follow the README install section for your agent such as Claude Code
- Make sure Python 3.10+ is available for the tooling
- Give the agent a reference image of the object
- Review the generated procedural Three.js model and animate it
Image & VideoIntermediate
15.9kJupyter Notebook+11/daypushed 298d ago
Use it for: Run a Stable Diffusion web UI in Google Colab notebooks. The repo is outdated and points to a newer project, TostUI.
Quick start
- Pick a version (lite, stable or nightly) and click its Open In Colab badge
- Run the notebook cells to start the WebUI
- Switch to the training or drive branch for DreamBooth/LoRA training or Google Drive installs
- Consider the newer TostUI repo, since this one is no longer updated
13.6kJavaScript+9/daypushed 709d ago
Use it for: Run Stable Diffusion locally on a Mac with a one-click installer and simple GUI, with no technical setup.
Quick start
- Download the app from diffusionbee.com
- Install and start the application
- Enter a prompt and click generate
- Optionally try image-to-image, inpainting or upscaling
11.8kn/a+8/daypushed 787d ago
Use it for: Browse a curated Chinese-language collection of AI painting resources: platforms, tutorials, deployment guides and news on Stable Diffusion, AnimateDiff and more.
Quick start
- Open the README, in Chinese or English
- Pick a topic such as Stable Cascade, SDXL Turbo or AnimateDiff
- Follow the linked tutorials and workflows
- Try the listed platforms or ComfyUI workflows
Image & VideoIntermediate
11.0kTypeScript+134/daypushed 5d ago
Use it for: Have Claude Code or Codex storyboard and animate cinematic product, promo, and launch videos with Remotion using ready-made shot recipes.
Quick start
- Clone the repo and follow the README install section to add the skill to Claude Code or Codex
- Browse the live Gallery to pick shot styles you like
- Point the agent at your product and ask it to make a promo video
- Render the result with the included Remotion template
10.7kJupyter Notebook+6/daypushed 750d ago
Use it for: Use 50+ AI models, including AI painting, speech synthesis, video frame interpolation and upscaling, OCR and subtitle translation, through free desktop apps.
Quick start
- Download the installer for your OS (Windows, Mac or Linux) from the README table
- Install and open the desktop app
- Choose a tool such as text-to-speech or video upscaling
- Load your content and run it
Image & VideoIntermediate
10.7kPython+9/daypushed 7d ago
Use it for: Generate, inpaint and outpaint images with AI directly inside Krita, with control over selections and reference images.
Quick start
- Download the plugin from the latest release
- Follow the installation guide at docs.interstice.cloud
- Open Krita and enable the plugin
- Select an area, optionally add a prompt, and generate locally or in the cloud
Image & VideoIntermediate
9.0kTypeScript+7/daypushed 892d ago
Use it for: Run an open-source web interface for creating and editing AI-generated images, the community version of DreamStudio.
Quick start
- Install Node.js and Yarn
- git clone https://github.com/Stability-AI/StableStudio.git, then cd StableStudio
- Run yarn, then yarn dev
- Open localhost:3000 and enter your Stability API key if using the default plugin
