Instructions to use naclbit/trinart_stable_diffusion_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use naclbit/trinart_stable_diffusion_v2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("naclbit/trinart_stable_diffusion_v2", 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
|
@@ -27,7 +27,7 @@ V2 checkpoint uses dropouts, 10,000 more images and a new tagging strategy and t
|
|
| 27 |
|
| 28 |
## Three flavors
|
| 29 |
|
| 30 |
-
Step 115000/95000
|
| 31 |
|
| 32 |
ステップ115000/95000のチェックポイントでスタイルが変わりすぎると感じる場合は、ステップ60000のチェックポイントを使用してみてください。
|
| 33 |
|
|
|
|
| 27 |
|
| 28 |
## Three flavors
|
| 29 |
|
| 30 |
+
Step 115000/95000 checkpoints were trained further, but you may use step 60000 checkpoint instead if style nudging is too much.
|
| 31 |
|
| 32 |
ステップ115000/95000のチェックポイントでスタイルが変わりすぎると感じる場合は、ステップ60000のチェックポイントを使用してみてください。
|
| 33 |
|