gpustack commited on
Commit
bec0440
·
verified ·
1 Parent(s): c21bba5

doc: readme

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -33,6 +33,13 @@ extra_gated_heading: Please read the LICENSE to access this model
33
  **Original model**: [stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4)<br/>
34
  **GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.
35
 
 
 
 
 
 
 
 
36
  ---
37
 
38
  # Stable Diffusion v1-4 Model Card
 
33
  **Original model**: [stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4)<br/>
34
  **GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.
35
 
36
+ | Quantization | CLIP_L Quantization | VAE Quantization |
37
+ | --- | --- | --- |
38
+ | FP16 | FP16 | FP16 |
39
+ | Q8_0 | FP16 | FP16 |
40
+ | Q4_1 | FP16 | FP16 |
41
+ | Q4_0 | FP16 | FP16 |
42
+
43
  ---
44
 
45
  # Stable Diffusion v1-4 Model Card