docs: readme
Browse files
README.md
CHANGED
|
@@ -9,6 +9,13 @@ inference: false
|
|
| 9 |
**Original model**: [sd-turbo](https://huggingface.co/stabilityai/sd-turbo)<br/>
|
| 10 |
**GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# SD-Turbo Model Card
|
|
|
|
| 9 |
**Original model**: [sd-turbo](https://huggingface.co/stabilityai/sd-turbo)<br/>
|
| 10 |
**GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.
|
| 11 |
|
| 12 |
+
| Quantization | OpenCLIP ViT-H/14 Quantization | VAE Quantization |
|
| 13 |
+
| --- | --- | --- |
|
| 14 |
+
| FP16 | FP16 | FP16 |
|
| 15 |
+
| Q8_0 | FP16 | FP16 |
|
| 16 |
+
| Q4_1 | FP16 | FP16 |
|
| 17 |
+
| Q4_0 | FP16 | FP16 |
|
| 18 |
+
|
| 19 |
---
|
| 20 |
|
| 21 |
# SD-Turbo Model Card
|