Instructions to use Beinsezii/Krea-2-Turbo-Projector-Scale-LoRA-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Beinsezii/Krea-2-Turbo-Projector-Scale-LoRA-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Turbo", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Beinsezii/Krea-2-Turbo-Projector-Scale-LoRA-Diffusers") 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
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,8 @@ tags:
|
|
| 6 |
library_name: diffusers
|
| 7 |
---
|
| 8 |
|
|
|
|
|
|
|
| 9 |
```
|
| 10 |
- 0.01 weight = +1×
|
| 11 |
- 0.1 weight = +10×
|
|
|
|
| 6 |
library_name: diffusers
|
| 7 |
---
|
| 8 |
|
| 9 |
+
Effectively increases prompt adherence in a manner that's a bit different than CFG. Helps when the model isn't following instructions correctly.
|
| 10 |
+
|
| 11 |
```
|
| 12 |
- 0.01 weight = +1×
|
| 13 |
- 0.1 weight = +10×
|