Instructions to use ECarbenia/grimoiresigils with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ECarbenia/grimoiresigils with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ECarbenia/grimoiresigils", 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,7 @@ tags:
|
|
| 7 |
|
| 8 |
This model was trained with 300 sigils from classic grimoires and a few modern grimoires.
|
| 9 |
Some of the sources include Heptameron, Verum, Goetia, Ars Almadel, Ars Paulina, Honorius, Hygromanteia, The works of Dr. John Dee, A.E. Waite's Turba Philosophorum, etc.
|
| 10 |
-
Veve from various spirits within the tradition of Vodun were included, as well as examples from modern practitioners
|
| 11 |
|
| 12 |
Skews the results towards the style of classic sigils, and often results in somewhat familiar forms. Type in the name of a desired spirit/effect, and run some tests with them.
|
| 13 |
Results are generally black and white, unlike models which are not trained on this dataset.
|
|
|
|
| 7 |
|
| 8 |
This model was trained with 300 sigils from classic grimoires and a few modern grimoires.
|
| 9 |
Some of the sources include Heptameron, Verum, Goetia, Ars Almadel, Ars Paulina, Honorius, Hygromanteia, The works of Dr. John Dee, A.E. Waite's Turba Philosophorum, etc.
|
| 10 |
+
Veve from various spirits within the tradition of Vodun were included, as well as examples from modern practitioners.
|
| 11 |
|
| 12 |
Skews the results towards the style of classic sigils, and often results in somewhat familiar forms. Type in the name of a desired spirit/effect, and run some tests with them.
|
| 13 |
Results are generally black and white, unlike models which are not trained on this dataset.
|