Instructions to use schrum2/MarioDiffusion-MLM-absence0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use schrum2/MarioDiffusion-MLM-absence0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("schrum2/MarioDiffusion-MLM-absence0", 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 files
README.md
CHANGED
|
@@ -11,4 +11,6 @@ There is also an interactive GUI for constructing complete levels out of model-g
|
|
| 11 |
|
| 12 |
This model had good performance in our experiments, but it challenging to use because it was trained with
|
| 13 |
lengthy "absence" captions that list various elements that are absent in each game scene. When that information
|
| 14 |
-
is not supplied, the results can be counterintuitive.
|
|
|
|
|
|
|
|
|
| 11 |
|
| 12 |
This model had good performance in our experiments, but it challenging to use because it was trained with
|
| 13 |
lengthy "absence" captions that list various elements that are absent in each game scene. When that information
|
| 14 |
+
is not supplied, the results can be counterintuitive. We recommend
|
| 15 |
+
https://huggingface.co/schrum2/MarioDiffusion-MLM-regular0
|
| 16 |
+
as a simpler starter model for generating Mario levels.
|