Update README.md
Browse files
README.md
CHANGED
|
@@ -36,6 +36,8 @@ license: cc-by-nc-nd-4.0
|
|
| 36 |
|
| 37 |
# Constructive Deconstruction: Domain-Agnostic Debiasing of Diffusion Models
|
| 38 |
|
|
|
|
|
|
|
| 39 |
## Introduction
|
| 40 |
|
| 41 |
Constructive Deconstruction is a novel approach to debiasing diffusion models used in generative tasks like image synthesis. This method enhances the quality and fidelity of generated images across various domains by removing biases inherited from the training data. Our technique involves overtraining the model to a controlled noisy state, applying nightshading, and using bucketing techniques to realign the model's internal representations.
|
|
|
|
| 36 |
|
| 37 |
# Constructive Deconstruction: Domain-Agnostic Debiasing of Diffusion Models
|
| 38 |
|
| 39 |
+
A paper is currently in the works. We believe the breakthrough and said release of the weights should come BEFORE any paper or wait period.
|
| 40 |
+
|
| 41 |
## Introduction
|
| 42 |
|
| 43 |
Constructive Deconstruction is a novel approach to debiasing diffusion models used in generative tasks like image synthesis. This method enhances the quality and fidelity of generated images across various domains by removing biases inherited from the training data. Our technique involves overtraining the model to a controlled noisy state, applying nightshading, and using bucketing techniques to realign the model's internal representations.
|