Text-to-Image
Diffusers
English
stable-diffusion
stable-diffusion-xl
sdxl
SD-XL 0.9
tutorial
NathMath
Instructions to use NathMath/sdxl-0.9-usage with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use NathMath/sdxl-0.9-usage with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("NathMath/sdxl-0.9-usage", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -79,9 +79,6 @@ tags:
|
|
| 79 |
### Tips
|
| 80 |
|
| 81 |
|
| 82 |
-
- The original weights by Stability AI are designed for high-end GPUs to use. However, here is a light, pruned version for base model with fp16 that are suitable for GPUs that do not have a suffcient VRAM to run the original one.
|
| 83 |
-
Link: https://huggingface.co/NathMath/sdxl-base-0.9-pruned-fp16
|
| 84 |
-
|
| 85 |
- Positive prompts and Negative prompts in both input box are ought to be identical, but you can freely try whatever you want.
|
| 86 |
|
| 87 |
- The output quality of the stable-diffusion-xl-0.9 models highly depends on your prompts and parameter settings, so try to adjust them to achieve a better quality.
|
|
|
|
| 79 |
### Tips
|
| 80 |
|
| 81 |
|
|
|
|
|
|
|
|
|
|
| 82 |
- Positive prompts and Negative prompts in both input box are ought to be identical, but you can freely try whatever you want.
|
| 83 |
|
| 84 |
- The output quality of the stable-diffusion-xl-0.9 models highly depends on your prompts and parameter settings, so try to adjust them to achieve a better quality.
|