Instructions to use Kagerage/wriggly-s-extra-gum-artstyle-ponydiffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Kagerage/wriggly-s-extra-gum-artstyle-ponydiffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Kagerage/wriggly-s-extra-gum-artstyle-ponydiffusion", 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 Settings
- Draw Things
- DiffusionBee
Forgot to mention recommended CFG
Browse files
README.md
CHANGED
|
@@ -22,6 +22,8 @@ anything else should be added at the end, so prompt would look like "gvgtgm trad
|
|
| 22 |
|
| 23 |
negative prompt "ugly, red, green, blue, clipped highlights, contrast", or for solo images, "ugly, multiple, red, green, blue, clipped highlights, contrast", or exclude "ugly" for a (Possibly) more true to training data image
|
| 24 |
|
|
|
|
|
|
|
| 25 |
Non-anthro ponies are seemingly very difficult to get, and I'm not sure how to make this model generate them.
|
| 26 |
|
| 27 |
Sample pictures of this concept:
|
|
|
|
| 22 |
|
| 23 |
negative prompt "ugly, red, green, blue, clipped highlights, contrast", or for solo images, "ugly, multiple, red, green, blue, clipped highlights, contrast", or exclude "ugly" for a (Possibly) more true to training data image
|
| 24 |
|
| 25 |
+
Recommended CFG is 7
|
| 26 |
+
|
| 27 |
Non-anthro ponies are seemingly very difficult to get, and I'm not sure how to make this model generate them.
|
| 28 |
|
| 29 |
Sample pictures of this concept:
|