|
--- |
|
license: creativeml-openrail-m |
|
task_categories: |
|
- text-to-image |
|
tags: |
|
- stable diffusion |
|
- style |
|
- hypernetwork |
|
pretty_name: lowpoly |
|
base_model: runwayml/stable-diffusion-v1-5 |
|
--- |
|
|
|
 |
|
|
|
# Lowpoly |
|
|
|
Lowpoly is a model trained on a stylized lowpoly dataset that captures a unique style (base model [SD 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5)). It's not meant to be used stand-alone but with other checkpoints. |
|
|
|
## Auto1111 Quick Start |
|
|
|
Instructions for use with Stable Diffusion Web UI. |
|
|
|
### Hypernetwork |
|
|
|
1. Download the [`lowpoly.hypernet.pt`](https://huggingface.co/n6ai/lowpoly-hypernetwork/resolve/main/lowpoly.hypernet.pt) file. |
|
2. Place the downloaded `lowpoly.hypernet.pt` file inside `stable-diffusion-webui/models/hypernetworks` directory. If the `hypernetworks` directory doesn't exist simply create it. |
|
3. Add `<hypernet:lowpoly.hypernet:0.25>` to your prompt and adjust the blend to your liking. |
|
|
|
**Example** |
|
|
|
```xml |
|
Your Prompt <hypernet:lowpoly.hypernet:0.25> |
|
``` |
|
|
|
## Best Practices |
|
|
|
> ⚠️ The model is quite aggressive and more unpredictable at higher blend values. |
|
|
|
- Use a blend between `0.1` and `0.3`. |
|
- Generate multiple images at once, minimum `4`. |
|
- Use `Lowpoly` with other artistic checkpoints. |
|
|
