GGUF
stable-diffusion
gpustack commited on
Commit
c79ee0c
·
verified ·
1 Parent(s): 4a063de

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -0
README.md CHANGED
@@ -5,6 +5,22 @@ tags:
5
  inference: false
6
  ---
7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  # Stable Diffusion v2 Model Card
9
  This model card focuses on the model associated with the Stable Diffusion v2, available [here](https://github.com/Stability-AI/stablediffusion).
10
 
 
5
  inference: false
6
  ---
7
 
8
+ # stable-diffusion-v2-inpainting-GGUF
9
+
10
+ !!! Experimental supported by gpustack/llama-box v0.0.98+ only !!!
11
+
12
+ **Model creator**: [StabilityAI](https://huggingface.co/stabilityai)<br/>
13
+ **Original model**: [stable-diffusion-2-inpainting](https://huggingface.co/stabilityai/stable-diffusion-2-inpainting)<br/>
14
+ **GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.
15
+
16
+ | Quantization | OpenAI CLIP ViT-L/14 Quantization | VAE Quantization |
17
+ | --- | --- | --- |
18
+ | FP16 | FP16 | FP16 |
19
+ | Q8_0 | FP16 | FP16 |
20
+ | Q4_1 | FP16 | FP16 |
21
+ | Q4_0 | FP16 | FP16 |
22
+
23
+
24
  # Stable Diffusion v2 Model Card
25
  This model card focuses on the model associated with the Stable Diffusion v2, available [here](https://github.com/Stability-AI/stablediffusion).
26