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
|
@@ -91,6 +91,9 @@ tags:
|
|
| 91 |
possibly, if your models are combined with FP16 and FP32, there could be a round-off error when converting data between these two formats. The main reason why it happens may
|
| 92 |
mainly due to the internal codes, and because of this, you'd better RESTART the interface to reload models from your disk every 200 times, for example, to maintain precise weights and eusure best image quality.
|
| 93 |
|
|
|
|
|
|
|
|
|
|
| 94 |
- This is not the final version of this repo. I will frequently update demos for further applications and advanced functions, so if you are interested, please like it.
|
| 95 |
|
| 96 |
- Need to be updated...
|
|
|
|
| 91 |
possibly, if your models are combined with FP16 and FP32, there could be a round-off error when converting data between these two formats. The main reason why it happens may
|
| 92 |
mainly due to the internal codes, and because of this, you'd better RESTART the interface to reload models from your disk every 200 times, for example, to maintain precise weights and eusure best image quality.
|
| 93 |
|
| 94 |
+
- Different from previous diffusion models, this stable-diffusion-xl-0.9 is naturally designed for high resolution image generation, so
|
| 95 |
+
in order to achieve a decent quality, please use a relatively higher resolution, for recommendation, 1024 * 1024.
|
| 96 |
+
|
| 97 |
- This is not the final version of this repo. I will frequently update demos for further applications and advanced functions, so if you are interested, please like it.
|
| 98 |
|
| 99 |
- Need to be updated...
|