Stable Diffusion models
9 Stable Diffusion models on Hugging Face, from 860M to 1.3B parameters. At the precision each one is published in, the smallest needs about 3.8 GB of VRAM (stable-diffusion-v1-5, cheapest live fit: V100) and the largest about 5.6 GB (controlnet-canny-sdxl-1.0, cheapest live fit: V100). The cheapest way to run stable-diffusion-v1-5 is $0.088/hr.
Stable Diffusion models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| stable-diffusion-v1-5 | 860M | F32 | 3.8 GB | V100 | $0.088/hr |
| stable-diffusion-v1-4 | 860M | F32 | 3.8 GB | V100 | $0.088/hr |
| stable-diffusion-v1-5 | 860M | F32 | 3.8 GB | V100 | $0.088/hr |
| stable-diffusion-2-1-base | 866M | F32 | 3.9 GB | V100 | $0.088/hr |
| stable-diffusion-2-1-base | 866M | F32 | 3.9 GB | V100 | $0.088/hr |
| stable-diffusion-2 | 866M | F32 | 3.9 GB | V100 | $0.088/hr |
| stable-diffusion-2-1 | 866M | F32 | 3.9 GB | V100 | $0.088/hr |
| sd-turbo | 866M | F32 | 3.9 GB | V100 | $0.088/hr |
| controlnet-canny-sdxl-1.0 | 1.3B | F32 | 5.6 GB | V100 | $0.088/hr |
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 XL (33 models)
- Stable Diffusion 3 (3 models)
- StableLM (3 models)
- stabilityai (3 models)
