Self-host app.enfugue.ai
0.3.3Open-source web app for AI image and video generation
- Stars
- 755
- Ports
- 45554 (HTTPS/SSL server), 45555 (HTTP/insecure server)
- Requires
- Stable Diffusion models
What is app.enfugue.ai?
ENFUGUE is a self-hosted web application for generating studio-grade images and videos using generative AI. It provides a unified pipeline supporting text-to-image, image-to-video, inpainting, and ControlNet operations without switching tabs. The app includes an in-app CivitAI browser for discovering community models, optional authentication with a two-tier user/admin hierarchy for shared environments, a safety checker enabled by default, and automatic GPU memory management. All features are accessible via a JSON API or Python diffusers extensions. It runs on Windows, Linux, and macOS via installation scripts or Docker, with configurable ports, SSL, and directories. The project is licensed under GPL-3.0.
Should you self-host app.enfugue.ai?
app.enfugue.ai scores 48/100 on selfhost.directory (how scoring works) and ranks #59 of 125 in AI. It has 755 GitHub stars.
There was no stable release in the past 12 months, so check the repository's recent activity before you rely on it.
Setup is moderate: expect some configuration beyond a single command. It is GPL-3.0-licensed and written mostly in Python.
Its closest alternative on selfhost.directory is ComfyUI (93/100, 143 714 stars). It scores higher overall, so compare the two before you pick. See app.enfugue.ai vs ComfyUI side by side.
Features
- Configurable server settings
- ControlNet support
- GPU memory management
- Image-to-video generation
- In-app CivitAI model browser
- In-app tooltips and documentation
- Inpainting
- JSON API
- Local-first Privacy
- Optional authentication
- Python diffusers extensions
- Safety checker
- TensorRT support
- Text-to-image generation
- Unified pipeline
app.enfugue.ai README
FAQ
Where can I learn more?
The project Wiki (in progress) and GitHub Discussion Boards are the main resources for learning more.
What are the best settings for the best images?
There is no one-size-fits-all; a great starting point is preconfigured, but experimentation is needed to find optimal parameters for each type of image.
What is "Full FP32", "Pruned PickleTensor", etc.?
These flags indicate the precision level and format of the model. Enfugue can convert between formats as needed, but Pruned and FP16/Half are recommended for fastest download and processing.
More in Image Generation
avatarSelf-hosted open-source Node.js service generating random geometric or initials-based avatars via REST API with configurable shapes, colors, and symmetry.
BelullamaSelf-hosted AI app bundling Ollama, Open WebUI, and Automatic1111 for local LLMs and image generation with one-command Docker install.
ChatGPT Web Midjourney ProxySelf-hosted open-source web UI that combines ChatGPT, Midjourney, Suno, Luma, Runway, Pika, and other AI models into a single interface with PWA support.
ComfyUISelf-hosted, open-source AI engine for visual creators with a node-based workflow system covering images, video, 3D, audio, and text.
ComfyUI Agent PanelSelf-hosted ComfyUI sidebar with AI agent powered by your Claude/ChatGPT sub. Edits workflows live, installs nodes, one-shot loads, rewind/rollback — no API keys.
comfyui-mcpLocal-first agent for ComfyUI generating images, video, audio via MCP server and Claude Code plugin. Works with Claude, ChatGPT, Gemini, or local LLMs.
ComfyUI-Nvidia-DockerComfyUI for NVIDIA GPU in a Docker container with user configurable uid/gid
GuaardvarkSelf-hosted AI studio on your own GPU: chat with your files (RAG), screen and browser agents, coding swarms, LoRA training, an MCP server for Claude Code and Cursor, and local video, image, music and voice generation. No telemetry.
InvokeAISelf-hosted, open-source AI image generation studio with a layered Unified Canvas, node-based workflows, ControlNet, and broad local model support from SD 1.5 to Flux.
JaazAn open-source AI creative agent with an infinite canvas for one-prompt image and video generation, a Canva alternative that runs locally on Windows and macOS.
LanceOpen-source, self-hosted unified multimodal model from ByteDance: 3B active parameters covering text-to-image, video synthesis, media editing, and visual Q&A.
Mix StudioSelf-hosted, open-source AI workspace built on ComfyUI that runs curated image and video workflows locally with a touch-friendly web interface.
0 comments