Instructions to use dg845/diffusers-cd_bedroom256_lpips with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dg845/diffusers-cd_bedroom256_lpips with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("dg845/diffusers-cd_bedroom256_lpips", 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
Update README.md
Browse filesFix typo in usage example
README.md
CHANGED
|
@@ -68,7 +68,7 @@ image.save("cd_bedroom256_lpips_onestep_sample.png")
|
|
| 68 |
# Multistep sampling
|
| 69 |
# Timesteps can be explicitly specified; the particular timesteps below are from the original Github repo:
|
| 70 |
# https://github.com/openai/consistency_models/blob/main/scripts/launch.sh#L83
|
| 71 |
-
image = pipe(num_inference_steps=None, timesteps=[
|
| 72 |
image.save("cd_bedroom256_lpips_multistep_sample.png")
|
| 73 |
```
|
| 74 |
|
|
|
|
| 68 |
# Multistep sampling
|
| 69 |
# Timesteps can be explicitly specified; the particular timesteps below are from the original Github repo:
|
| 70 |
# https://github.com/openai/consistency_models/blob/main/scripts/launch.sh#L83
|
| 71 |
+
image = pipe(num_inference_steps=None, timesteps=[17, 0]).images[0]
|
| 72 |
image.save("cd_bedroom256_lpips_multistep_sample.png")
|
| 73 |
```
|
| 74 |
|