Stable Diffusion 2 models
5 Stable Diffusion 2 models from Stability AI on Hugging Face, from 866M to 866M parameters, published by Stability AI in F32. The smallest official model, sd-turbo, needs about 3.9 GB of VRAM at its published precision; the cheapest live fit is V100 at $0.088/hr.
Part of the Stable Diffusion series · Previous generation: Stable Diffusion 1 · Next generation: Stable Diffusion XL
Pick a size
One row per official Stable Diffusion 2 size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| sd-turbo | 866M | 3.9 GB | 1.0 GB | 0.5 GB | V100 | $0.088/hr | not published for this architecture |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (1)
Fine-tunes and community models (4)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/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 |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. 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 (34 models)
- Stable Diffusion 1 (3 models)
- Stable Diffusion 3 (3 models)
- StableLM (3 models)
- stabilityai (3 models)
