Instructions to use MidnightRunner/Pear with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use MidnightRunner/Pear with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("MidnightRunner/Pear") prompt = "(a beautiful woman:1.5), (looking straight at the camera:1.3), hazel eye color, sweat, trembling, blush, a woman with black hair, black manicure, (goosebumps:1.2), skin pores, sweat, raytracing, specular lighting, shallow depth of field, 1girl, smiling, dimples, long voluminous hair, beautiful, from below, (looking at the viewer), (in frame), bare shoulders" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -60,9 +60,7 @@ Embarking my first LoRa research
|
|
| 60 |
|
| 61 |
As my research purposes to build base model, creating a model using a 3D sculpting approach similar to retrain the model versioning, with a distinctive emphasis on realism, like the contours of a hourglass body and face features. It does not depict anyone real person.
|
| 62 |
|
| 63 |
-
When using for ADetailer or anything with facial improvements, recommend to mention:
|
| 64 |
-
|
| 65 |
-
`a woman with black hair`
|
| 66 |
|
| 67 |
Sampling method
|
| 68 |
DPM++ 2M Karras
|
|
|
|
| 60 |
|
| 61 |
As my research purposes to build base model, creating a model using a 3D sculpting approach similar to retrain the model versioning, with a distinctive emphasis on realism, like the contours of a hourglass body and face features. It does not depict anyone real person.
|
| 62 |
|
| 63 |
+
When using for ADetailer or anything with facial improvements, recommend to mention: `a woman with black hair`
|
|
|
|
|
|
|
| 64 |
|
| 65 |
Sampling method
|
| 66 |
DPM++ 2M Karras
|