safetensors note
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ inference: true
|
|
| 16 |
|
| 17 |
A LoRA for SDXL 1.0 Base which improves output image quality after loading it and using `wrong` as a negative prompt during inference. You can demo image generation using this LoRA in [this Colab Notebook](https://colab.research.google.com/github/minimaxir/sdxl-experiments/blob/main/sdxl_image_generation.ipynb).
|
| 18 |
|
|
|
|
|
|
|
| 19 |
Benefits of using this LoRA:
|
| 20 |
|
| 21 |
- Higher detail in textures/fabrics, particularly at full 1024x1024 resolution.
|
|
|
|
| 16 |
|
| 17 |
A LoRA for SDXL 1.0 Base which improves output image quality after loading it and using `wrong` as a negative prompt during inference. You can demo image generation using this LoRA in [this Colab Notebook](https://colab.research.google.com/github/minimaxir/sdxl-experiments/blob/main/sdxl_image_generation.ipynb).
|
| 18 |
|
| 19 |
+
The LoRA is also available in a `safetensors` format for other UIs such as A1111; however this LoRA was created using `diffusers` and I cannot guarantee its efficacy outside of it.
|
| 20 |
+
|
| 21 |
Benefits of using this LoRA:
|
| 22 |
|
| 23 |
- Higher detail in textures/fabrics, particularly at full 1024x1024 resolution.
|