metadata
base_model: CompVis/stable-diffusion-v-1-4-original
license: creativeml-openrail-m
library_name: stable-diffusion
inference: false
model_creator: runwayml
model_name: stable-diffusion-v-1-4-original
quantized_by: Second State Inc.
tags:
- stable-diffusion
- text-to-image
stable-diffusion-v-1-4-GGUF
Original Model
CompVis/stable-diffusion-v-1-4-original
Run with LlamaEdge-StableDiffusion
Version: v0.2.0
Run as LlamaEdge service
wasmedge --dir .:. sd-api-server.wasm \ --model-name sd-v1.4 \ --model stable-diffusion-v1-4-Q8_0.gguf
Quantized GGUF Models
Using formats of different precisions will yield results of varying quality.
| f32 | f16 | q8_0 | q5_0 | q5_1 | q4_0 | q4_1 |
|---|---|---|---|---|---|---|
 |
 |
 |
 |
 |
 |
 |
| Name | Quant method | Bits | Size | Use case |
|---|---|---|---|---|
| stable-diffusion-v1-4-Q4_0.gguf | Q4_0 | 2 | 1.57 GB | |
| stable-diffusion-v1-4-Q4_1.gguf | Q4_1 | 3 | 1.59 GB | |
| stable-diffusion-v1-4-Q5_0.gguf | Q5_0 | 3 | 1.62 GB | |
| stable-diffusion-v1-4-Q5_1.gguf | Q5_1 | 3 | 1.64 GB | |
| stable-diffusion-v1-4-Q8_0.gguf | Q8_0 | 4 | 1.76 GB | |
| stable-diffusion-v1-4-f16.gguf | f16 | 4 | 2.13 GB | |
| stable-diffusion-v1-4-f32.gguf | f32 | 4 | 4.27 GB |