---

base_model: runwayml/stable-diffusion-v1-5 license: creativeml-openrail-m inference: true model_creator: runwayml model_name: stable-diffusion-v1-5 quantized_by: Second State Inc. tags:

• stable-diffusion
• stable-diffusion-diffusers
• text-to-image

---

---

stable-diffusion-v1-5-GGUF

Original Model

runwayml/stable-diffusion-v1-5

Run with LlamaEdge-StableDiffusion

• Version: v0.2.0
• Run as LlamaEdge service

wasmedge --dir .:. sd-api-server.wasm \
    --model-name sd-v1.5 \
    --model stable-diffusion-v1-5-pruned-emaonly-Q8_0.gguf

Quantized GGUF Models

Using formats of different precisions will yield results of varying quality.

f32	f16	q80	q50	q51	q40	q4_1

Name	Quant method	Bits	Size	Use case
stable-diffusion-v1-5-pruned-emaonly-Q40.gguf	Q40	2	1.57 GB
stable-diffusion-v1-5-pruned-emaonly-Q41.gguf	Q41	3	1.59 GB
stable-diffusion-v1-5-pruned-emaonly-Q50.gguf	Q50	3	1.62 GB
stable-diffusion-v1-5-pruned-emaonly-Q51.gguf	Q51	3	1.64 GB
stable-diffusion-v1-5-pruned-emaonly-Q80.gguf	Q80	4	1.76 GB
stable-diffusion-v1-5-pruned-emaonly-f16.gguf	f16	4	2.13 GB
stable-diffusion-v1-5-pruned-emaonly-f32.gguf	f32	4	4.27 GB