Update README.md
Browse files
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 |
|