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
SDXL 1.0
The step up from 1.5: 1024×1024 native, much better at hands, prompts and composition.
- Open weights
- Image
- Filtered adult content
At a glance
- Made by
- Stability AI
- Family
- Stable Diffusion
- Licence
- CreativeML Open RAIL++-M
- Graphics memory
- 8 GB minimum, 12 GB recommended
- Adult content
- FilteredA filter blocks it, with varying success.
The base model was trained with adult material filtered out of the dataset, which is why the community fine-tunes are what people actually run. It needs roughly twice the memory of 1.5 and rewards a 12 GB card.
Still the sensible default for anyone whose hardware can take it.