Stable Diffusion XL models
33 Stable Diffusion XL models on Hugging Face, from 611M to 2.6B parameters. At the precision each one is published in, the smallest needs about 2.7 GB of VRAM (PixArt-Sigma-XL-2-1024-MS, cheapest live fit: V100) and the largest about 11.5 GB (stable-diffusion-xl-1.0-inpainting-0.1, cheapest live fit: V100). The cheapest way to run PixArt-Sigma-XL-2-1024-MS is $0.088/hr.
Stable Diffusion XL models
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from Stability AI
- Stable Diffusion (9 models)
- Stable Diffusion 3 (3 models)
- StableLM (3 models)
- stabilityai (3 models)
