Instructions to use superdiff/superdiff-sdxl-v1-0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use superdiff/superdiff-sdxl-v1-0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("superdiff/superdiff-sdxl-v1-0", 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 pipeline.py
Browse files- pipeline.py +1 -1
pipeline.py
CHANGED
|
@@ -443,7 +443,7 @@ class SuperDiffSDXLPipeline(DiffusionPipeline, ConfigMixin):
|
|
| 443 |
* (noise_pred_text_o - noise_pred_text_b)
|
| 444 |
)
|
| 445 |
|
| 446 |
-
if i < self.num_inference_steps -
|
| 447 |
latents += 2 * dsigma * noise_pred + noise
|
| 448 |
else:
|
| 449 |
latents += dsigma * noise_pred
|
|
|
|
| 443 |
* (noise_pred_text_o - noise_pred_text_b)
|
| 444 |
)
|
| 445 |
|
| 446 |
+
if i < self.num_inference_steps - 3:
|
| 447 |
latents += 2 * dsigma * noise_pred + noise
|
| 448 |
else:
|
| 449 |
latents += dsigma * noise_pred
|