Models
The models underneath the tools. A tool is a steering wheel; this is the engine — and it is usually the engine, not the wheel, that decides what you can make and what it costs to run.
-
FLUX.1 [dev]
A large open-weights image model with notably better prompt adherence and text rendering than the Stable Diffusion line.
- Open weights
- Image
- Filtered
-
Llama 3.3 70B Instruct
A large open-weights text model, and the base for most of the uncensored community fine-tunes people actually use for roleplay.
- Open weights
- Text
- Filtered
-
Mistral NeMo 12B
A genuinely Apache-licensed 12B model that fits on an ordinary desktop card, and the base for a lot of small roleplay fine-tunes.
- Open weights
- Text
- Unknown
-
Qwen2.5 72B Instruct
A large open-weights model strong at multilingual work, widely used as a fine-tuning base.
- Open weights
- Text
- Filtered
-
Illustrious XL
An SDXL-based anime model that displaced Pony as the usual base for illustration checkpoints.
- Open weights
- Image
- Allowed
-
Pony Diffusion V6 XL
An SDXL fine-tune that became the base model for a large share of community art checkpoints.
- Open weights
- Image
- Allowed
-
SDXL 1.0
The step up from 1.5: 1024×1024 native, much better at hands, prompts and composition.
- Open weights
- Image
- Filtered
-
Stable Diffusion 1.5
The old workhorse. Small, fast, endlessly fine-tuned, and still the model most community checkpoints are built on.
- Open weights
- Image
- Allowed
-
Whisper large-v3
Speech to text, MIT-licensed, running entirely on your machine. The one uncomplicated thing on this page.
- Open weights
- Audio
- Allowed
-
XTTS v2
Voice cloning from a few seconds of audio, in seventeen languages, running locally. The company behind it shut down; the weights remain.
- Open weights
- Audio
- Unknown