Instructions to use lambda/sd-naruto-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lambda/sd-naruto-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lambda/sd-naruto-diffusers", 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
|
@@ -26,7 +26,9 @@ If you want to find out how to train your own Stable Diffusion variants, see thi
|
|
| 26 |
## Prompt engineering matters
|
| 27 |
|
| 28 |
We find that prompt engineering does help produce compelling and consistent Naruto style portraits.
|
| 29 |
-
For example, writing prompts such as '
|
|
|
|
|
|
|
| 30 |
|
| 31 |
Here are a few examples of prompts with and without prompt engineering that will illustrate that point.
|
| 32 |
|
|
|
|
| 26 |
## Prompt engineering matters
|
| 27 |
|
| 28 |
We find that prompt engineering does help produce compelling and consistent Naruto style portraits.
|
| 29 |
+
For example, writing prompts such as '<person_name> ninja portrait' or '<person_name> in the style of Naruto tends to produce results that are closer to the style of Naruto character with the characteristic headband and other elements of costume.
|
| 30 |
+
|
| 31 |
+
If you are curious to see the effect of prompt engineering in action, try our [text-to-naruto demo](https://huggingface.co/spaces/lambdalabs/text-to-naruto)!
|
| 32 |
|
| 33 |
Here are a few examples of prompts with and without prompt engineering that will illustrate that point.
|
| 34 |
|