gpustack commited on
Commit
632cbcd
1 Parent(s): c16c0c1

docs: readme

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -15,6 +15,15 @@ license_link: https://huggingface.co/stabilityai/sdxl-turbo/blob/main/LICENSE.md
15
  **GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.<br/>
16
  **VAE From**: [madebyollin/sdxl-vae-fp16-fix](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/blob/main/sdxl_vae.safetensors).
17
 
 
 
 
 
 
 
 
 
 
18
  # SDXL-Turbo Model Card
19
 
20
  <!-- Provide a quick summary of what the model is/does. -->
 
15
  **GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.<br/>
16
  **VAE From**: [madebyollin/sdxl-vae-fp16-fix](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/blob/main/sdxl_vae.safetensors).
17
 
18
+ | Quantization | OpenAI CLIP ViT-L/14 Quantization | OpenCLIP ViT-G/14 Quantization | VAE Quantization |
19
+ | --- | --- | --- | --- |
20
+ | FP16 | FP16 | FP16 | FP16 |
21
+ | Q8_0 | FP16 | FP16 | FP16 |
22
+ | Q4_1 | FP16 | FP16 | FP16 |
23
+ | Q4_0 | FP16 | FP16 | FP16 |
24
+
25
+ ---
26
+
27
  # SDXL-Turbo Model Card
28
 
29
  <!-- Provide a quick summary of what the model is/does. -->