Instructions to use lenML/DeepNegativeXL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lenML/DeepNegativeXL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lenML/DeepNegativeXL", dtype=torch.bfloat16, device_map="cuda") prompt = "vampire bride,film photography aesthetic,the delicate texture of lace veil gently obscuring her face,long blonde hair,looking at viewer,eye eye contact,sapphire red eyes,choker,devil smile,dynamic composition,skin texture,from above,close-up,sharp focus,horror \\(theme\\),dutch angle," image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -79,6 +79,15 @@ This is the XL version of `DeepNegative`. If you are using the 1.5 mod
|
|
| 79 |
# DeepNegative XL
|
| 80 |
Finally, it's released! try it and review~🤗
|
| 81 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
ps:
|
| 83 |
I apologize for not updating the Deep Negative XL model due to the excessive focus on text models... (god damn GPT model, it’s all commercial hype!)...
|
| 84 |
|
|
|
|
| 79 |
# DeepNegative XL
|
| 80 |
Finally, it's released! try it and review~🤗
|
| 81 |
|
| 82 |
+
## What does it do?
|
| 83 |
+
**DeepNegative** is a negative embedding. it contain unsightly compositions and color patterns, such as inaccurate human anatomy, distasteful color combinations, disoriented spatial structures, and more. By put it in negative prompt, we can significantly reduce the occurrence of these elements.
|
| 84 |
+
|
| 85 |
+
## Suggestion
|
| 86 |
+
Because this embedding is learning how to create disgusting concepts, it cannot improve the picture quality accurately, so it is best used with (worst quality, low quality, logo, text, watermark, username) these negative prompts.
|
| 87 |
+
|
| 88 |
+
Of course, it is completely fine to use with other similar negative embeddings.
|
| 89 |
+
|
| 90 |
+
----
|
| 91 |
ps:
|
| 92 |
I apologize for not updating the Deep Negative XL model due to the excessive focus on text models... (god damn GPT model, it’s all commercial hype!)...
|
| 93 |
|