WorldlyLabs
commited on
Commit
•
e584dab
1
Parent(s):
dbe3f9b
Update README.md
Browse files
README.md
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
---
|
4 |
|
5 |
# worldly-v1: Bias Mitigation Script for Image Generation
|
6 |
|
7 |
## Overview
|
8 |
|
9 |
-
**worldly
|
10 |
|
11 |
## Purpose
|
12 |
|
13 |
-
The goal of **worldly
|
14 |
|
15 |
## How It Works
|
16 |
|
@@ -32,7 +32,7 @@ pip install torch diffusers huggingface_hub Pillow
|
|
32 |
|
33 |
1. **Download the Script**
|
34 |
|
35 |
-
You can download and integrate the **worldly
|
36 |
|
37 |
```python
|
38 |
from huggingface_hub import hf_hub_download
|
@@ -50,7 +50,7 @@ spec.loader.exec_module(worldly_v1)
|
|
50 |
|
51 |
2. **Integrating into Image Generation**
|
52 |
|
53 |
-
Once downloaded, you can use **worldly
|
54 |
|
55 |
### Example Script
|
56 |
|
@@ -156,4 +156,4 @@ if __name__ == "__main__":
|
|
156 |
|
157 |
## License
|
158 |
|
159 |
-
The **worldly
|
|
|
1 |
---
|
2 |
+
license: mit
|
3 |
---
|
4 |
|
5 |
# worldly-v1: Bias Mitigation Script for Image Generation
|
6 |
|
7 |
## Overview
|
8 |
|
9 |
+
**worldly** is a bias mitigation script designed to modify prompts before sending them to an image generation model. It introduces diverse ethnicities and other demographic characteristics into prompts that contain vague references to "people," "person," or related terms, helping ensure more equitable representation in generated images. This version is specifically demonstrated with the **FluxPipeline** model, but it can be used with any image generation model that accepts text-based prompts.
|
10 |
|
11 |
## Purpose
|
12 |
|
13 |
+
The goal of **worldly** is to mitigate bias in AI-generated imagery by diversifying the representations of people in prompts. This script dynamically modifies prompts by injecting randomly selected ethnicities or demographic details, ensuring equal chances of different ethnicities being represented in the generated images.
|
14 |
|
15 |
## How It Works
|
16 |
|
|
|
32 |
|
33 |
1. **Download the Script**
|
34 |
|
35 |
+
You can download and integrate the **worldly** script into your image generation pipeline. Use the `huggingface_hub` library to fetch the script:
|
36 |
|
37 |
```python
|
38 |
from huggingface_hub import hf_hub_download
|
|
|
50 |
|
51 |
2. **Integrating into Image Generation**
|
52 |
|
53 |
+
Once downloaded, you can use **worldly** to modify prompts before image generation. Below is an example of how to integrate the script into an image generation pipeline using the **FluxPipeline** model from Diffusers.
|
54 |
|
55 |
### Example Script
|
56 |
|
|
|
156 |
|
157 |
## License
|
158 |
|
159 |
+
The **worldly** script is licensed under the MIT License. You are free to use, modify, and distribute this script, as long as the original copyright and permission notice is retained.
|