Instructions to use Metal079/SonicDiffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Metal079/SonicDiffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Metal079/SonicDiffusion", 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
|
@@ -5,6 +5,6 @@ mobianstrimmed6000 was trained on 100 images for 6000 steps, use keyword 'mobian
|
|
| 5 |
mobianstrimmed12000 was trained on 100 images for 12000 steps, use keyword 'mobian person' when prompting
|
| 6 |
|
| 7 |
Current testing shows that mobianstrimmed6000 and evan5400 produce the best quality images, I would recommend starting with one of those two and compare results.
|
| 8 |
-
Apologies for using different keywords between models, I wanted to fully switch over to 'mobian person' but unfortunetaly im not fully conviced even though I used
|
| 9 |
-
double the training images, that it is better so I included both models. 6000 seemed like the sweet spot as I have noticed mobianstrimmed12000
|
| 10 |
-
good images as the other two.
|
|
|
|
| 5 |
mobianstrimmed12000 was trained on 100 images for 12000 steps, use keyword 'mobian person' when prompting
|
| 6 |
|
| 7 |
Current testing shows that mobianstrimmed6000 and evan5400 produce the best quality images, I would recommend starting with one of those two and compare results.
|
| 8 |
+
Apologies for using different keywords between models, I wanted to fully switch over to 'mobian person' but unfortunetaly im not fully conviced even though I used
|
| 9 |
+
more than double the training images, that it is better so I included both models. 6000 seemed like the sweet spot as I have noticed mobianstrimmed12000
|
| 10 |
+
doesnt give as consistantly good images as the other two.
|