Instructions to use superdiff/superdiff-sd-v1-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use superdiff/superdiff-sd-v1-4 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-sd-v1-4", 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 +5 -5
pipeline.py
CHANGED
|
@@ -46,11 +46,11 @@ class SuperDiffPipeline(DiffusionPipeline, ConfigMixin):
|
|
| 46 |
self.text_encoder.to(device)
|
| 47 |
|
| 48 |
self.register_to_config(
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
device=device,
|
| 55 |
batch_size=None,
|
| 56 |
num_inference_steps=None,
|
|
|
|
| 46 |
self.text_encoder.to(device)
|
| 47 |
|
| 48 |
self.register_to_config(
|
| 49 |
+
vae=vae.__class__.__name__,
|
| 50 |
+
scheduler=scheduler.__class__.__name__,
|
| 51 |
+
tokenizer=tokenizer.__class__.__name__,
|
| 52 |
+
unet=unet.__class__.__name__,
|
| 53 |
+
text_encoder=text_encoder.__class__.__name__
|
| 54 |
device=device,
|
| 55 |
batch_size=None,
|
| 56 |
num_inference_steps=None,
|