Instructions to use ItsMeBell/LarosBell-XL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ItsMeBell/LarosBell-XL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ItsMeBell/LarosBell-XL", 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 Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -229,6 +229,7 @@ tags:
|
|
| 229 |
<details>
|
| 230 |
<summary><strong>Recommended settings</strong></summary>
|
| 231 |
<br>
|
|
|
|
| 232 |
<p>Prompting is a bit different in this model, for optimal results, it's recommended to follow the structured prompt template:</p>
|
| 233 |
<pre>1girl/1boy, character name, from what series, everything else in any order.</pre>
|
| 234 |
<p>To guide the model towards generating high-aesthetic images, use negative prompts like:</p>
|
|
|
|
| 229 |
<details>
|
| 230 |
<summary><strong>Recommended settings</strong></summary>
|
| 231 |
<br>
|
| 232 |
+
<p>USE SDXL VAE For More Natural Color</p>
|
| 233 |
<p>Prompting is a bit different in this model, for optimal results, it's recommended to follow the structured prompt template:</p>
|
| 234 |
<pre>1girl/1boy, character name, from what series, everything else in any order.</pre>
|
| 235 |
<p>To guide the model towards generating high-aesthetic images, use negative prompts like:</p>
|