ComfyUI
A node graph for image and video models. Steeper to learn than anything else here, and the only one that lets you build exactly the pipeline you want.
- Self-hosted
- Allowed
Tools
Every tool we have written up, with the things that are usually hard to find out: where it runs, what it allows, and what it does with what you give it. When we do not know, the page says so rather than guessing.
44 tools
-
-
Hugging Face
Where the weights live. Almost every open model in this catalog is downloaded from here.
- Hosted
- Filtered
-
Ollama
One command to download and run a language model on your own machine. The easiest honest answer to "how do I do this without a cloud".
- Self-hosted
- Allowed
- No GPU needed
-
SillyTavern
The roleplay front-end. It is not a model: you bring one, local or hosted, and it handles characters, memory, formatting and everything around the conversation.
- Self-hosted
- Allowed
- No GPU needed
-
Stable Diffusion WebUI
The original web interface for Stable Diffusion, by AUTOMATIC1111. Enormously extended, widely copied, and no longer moving quickly.
- Self-hosted
- Allowed
-
Agnaistic
An open-source roleplay front-end you can self-host for a group, with a hosted instance for people who would rather not.
- Hybrid
- Allowed
- No GPU needed
-
AnimateDiff
Motion added to an existing image model. The technique that made short animated clips possible on a home graphics card.
- Self-hosted
- Allowed
-
Backyard AI
A desktop companion app that downloads a model and runs it locally, with character chat built in. Formerly called Faraday.
- Hybrid
- Allowed
- No GPU needed
-
Character.AI
The largest character chat service by a wide margin, and a filtered one. Worth knowing about mostly because everyone starts here.
- Hosted
- Filtered
-
Chub AI
A character card repository first, a chat service second. The place people actually get the cards they import elsewhere.
- Hosted
- Allowed
-
Civitai
The image model hub: checkpoints, LoRAs and the example images that show what they actually do. Indispensable, and volatile.
- Hosted
- Opt-in
-
Draw Things
Image generation as a native Mac and iPhone app. Free, local, and startlingly good at running large models on Apple silicon.
- Self-hosted
- Allowed
- No GPU needed
-
ElevenLabs
The best-known hosted speech synthesis service. Very good, and the one with the most developed consent process for cloning a voice.
- Hosted
- Unknown
-
Fooocus
Image generation with almost every setting hidden. Type a prompt, get a good picture. No longer actively developed.
- Self-hosted
- Abandoned
- Allowed
-
GPT4All
A local chat desktop app with a long history, aimed squarely at ordinary hardware and people who do not want a terminal.
- Self-hosted
- Allowed
- No GPU needed
-
Glaze
Adds imperceptible changes to your artwork so that models trained on it learn the wrong style. Free, local, from the University of Chicago.
- Self-hosted
- Allowed
- No GPU needed
-
Have I Been Trained?
Search the large public training datasets for your own images, and register an opt-out that some model trainers honour.
- Hosted
- Allowed
-
HunyuanVideo
A large open-weights text-to-video model from Tencent. Genuinely good output, and a genuinely large hardware bill.
- Self-hosted
- Unknown
-
InvokeAI
A polished, professional-feeling image studio with a unified canvas. The one to show someone who bounced off the others.
- Hybrid
- Allowed
-
Jan
An open-source desktop assistant that runs models locally by default and can be pointed at a hosted one when you choose.
- Hybrid
- Allowed
- No GPU needed
-
Janitor AI
A character chat site with a large user-made library, which can also be pointed at your own model or API key.
- Hosted
- Allowed
-
Kindroid
A companion app with fine-grained control over the character's backstory and voice, and video selfies.
- Hosted
- Unknown
-
KoboldAI
The original open-source AI writing interface. Largely superseded by KoboldCpp, and the ancestor of much of this section.
- Self-hosted
- Abandoned
- Allowed
- No GPU needed
-
KoboldCpp
A single-file local model server built for storytelling and roleplay, with the sampler controls that community actually uses.
- Self-hosted
- Allowed
- No GPU needed
-
Kohya's GUI
The standard tool for training your own LoRA. Unglamorous, widely used, and the thing every tutorial eventually points at.
- Self-hosted
- Allowed
-
Krita AI Diffusion
Generation built into a real painting program. You paint, it fills in; you paint over it, it adjusts.
- Self-hosted
- Allowed
-
LM Studio
A desktop app for finding, downloading and chatting with local language models. Free, closed source, and the gentlest way in.
- Self-hosted
- Allowed
- No GPU needed
-
Nightshade
The offensive counterpart to Glaze: images altered so that training on them damages the model rather than teaching it your style.
- Self-hosted
- Allowed
- No GPU needed
-
Nomi
A companion service that leans on long-term memory, marketed on the consistency of the character over months.
- Hosted
- Unknown
-
NovelAI
A subscription writing and image service with an explicit policy of not filtering fiction, and a long record of keeping it.
- Hosted
- Allowed
-
Novelcrafter
A novel-writing workspace with a codex and a planning board, that connects to whichever model you bring — including a local one.
- Hosted
- Allowed
-
OneTrainer
A newer trainer with a friendlier interface than Kohya's and a good record of supporting new architectures quickly.
- Self-hosted
- Allowed
-
OpenRouter
One API key for a great many hosted models, including ones with looser content policies than their originals.
- Hosted
- Unknown
-
Piper
Fast, small, local text-to-speech that runs on a Raspberry Pi. Not a voice cloner — a reliable speaking voice.
- Self-hosted
- Allowed
- No GPU needed
-
Replika
The best-known companion app, and a cautionary tale about depending on a hosted one.
- Hosted
- Unknown
-
Retrieval-based Voice Conversion WebUI
Local voice conversion: sing or speak, and it comes out in a different voice. Powerful, entirely unsupervised, and the consent problem in this catalog at its sharpest.
- Self-hosted
- Allowed
-
RisuAI
A roleplay front-end that runs in a browser tab or as a desktop app, with a lighter touch than SillyTavern.
- Hybrid
- Allowed
- No GPU needed
-
SD.Next
Another descendant of the AUTOMATIC1111 interface, aimed at breadth: many model families, and AMD and Intel GPUs as first-class targets.
- Self-hosted
- Allowed
-
Stable Diffusion WebUI Forge
A fork of AUTOMATIC1111's interface, reworked underneath for speed and lower memory use. The same screen, faster, on less VRAM.
- Self-hosted
- Allowed
-
Sudowrite
A commercial writing tool built for novelists, with structural features — outlines, character bibles, chapter drafting — rather than a chat box.
- Hosted
- Unknown
-
Text generation web UI
The "AUTOMATIC1111 of language models": one interface, many backends, an extension for everything.
- Self-hosted
- Allowed
- No GPU needed
-
faster-whisper
A reimplementation of Whisper that transcribes several times faster on the same hardware. Local, MIT, and the sensible default.
- Self-hosted
- Allowed
- No GPU needed
-
llama.cpp
The C++ engine most local language model software is built on. Runs large models on ordinary hardware, including with no GPU at all.
- Self-hosted
- Allowed
- No GPU needed
-
vLLM
A serious inference server for serving a model to many people at once. Not a chatbot — the thing a chatbot runs on.
- Self-hosted
- Allowed