Stability AI
Stable Diffusion 1.5
The original Stable Diffusion. Huge ecosystem of LoRAs, ControlNets, and extensions. Best compatibility.
0.86B parametersunet-diffusioncreativeml-openrail-m4GB - 6GB VRAM
Check Your Hardware
See which quantizations of Stable Diffusion 1.5 your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| FP16 | 16 | 2 GB | 4 GB | 8 GB | 100% |
| FP32 | 32 | 4 GB | 6 GB | 10 GB | 100% |
Frequently Asked Questions
How much VRAM do I need to run Stable Diffusion 1.5?
Stable Diffusion 1.5 requires 4GB VRAM minimum with FP16 quantization. For full precision, you need 6GB VRAM.
What is the best quantization for Stable Diffusion 1.5?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.