docs: readme
Browse files
README.md
CHANGED
|
@@ -36,6 +36,13 @@ pipeline_tag: text-to-image
|
|
| 36 |
**Original model**: [stable-diffusion-3-medium](https://huggingface.co/stabilityai/stable-diffusion-3-medium)<br/>
|
| 37 |
**GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
---
|
| 40 |
|
| 41 |
# Stable Diffusion 3 Medium
|
|
|
|
| 36 |
**Original model**: [stable-diffusion-3-medium](https://huggingface.co/stabilityai/stable-diffusion-3-medium)<br/>
|
| 37 |
**GGUF quantization**: based on stable-diffusion.cpp [ac54e](https://github.com/leejet/stable-diffusion.cpp/commit/ac54e0076052a196b7df961eb1f792c9ff4d7f22) that patched by llama-box.
|
| 38 |
|
| 39 |
+
| Quantization | OpenAI CLIP ViT-L/14 Quantization | OpenCLIP ViT-G/14 Quantization | Google T5-xxl Quantization | VAE Quantization |
|
| 40 |
+
| --- | --- | --- | --- | --- |
|
| 41 |
+
| FP16 | FP16 | FP16 | FP16 | FP16 |
|
| 42 |
+
| Q8_0 | FP16 | FP16 | Q8_0 | FP16 |
|
| 43 |
+
| Q4_1 | FP16 | FP16 | Q8_0 | FP16 |
|
| 44 |
+
| Q4_0 | FP16 | FP16 | Q8_0 | FP16 |
|
| 45 |
+
|
| 46 |
---
|
| 47 |
|
| 48 |
# Stable Diffusion 3 Medium
|