Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ For detailed information, code, and documentation, please visit our GitHub repos
|
|
| 21 |
**Anonymize Anyone** presents a novel approach to text-to-face synthesis using a Diffusion Model that considers Race Fairness. Our method uses facial segmentation masks to edit specific facial regions, and employs a Stable Diffusion v2 Inpainting model trained on a curated Asian dataset. We introduce two key losses: **βπΉπΉπΈ** (Focused Feature Enhancement Loss) to enhance performance with limited data, and **βπ«π°ππ** (Difference Loss) to address catastrophic forgetting. Finally, we apply **Simple Preference Optimization** (SimPO) for refined and enhanced image generation.
|
| 22 |
|
| 23 |
## Model Checkpoints
|
| 24 |
-
|
| 25 |
- [Anonymize-Anyone (Inpainting model with **βπΉπΉπΈ** and **βπ«π°ππ**)](https://huggingface.co/fh2c1/Anonymize-Anyone)
|
| 26 |
- [SimPO-LoRA (Diffusion model with **Simple Preference Optimization**)](https://huggingface.co/fh2c1/SimPO-LoRA-1.2)
|
| 27 |
|
|
|
|
| 21 |
**Anonymize Anyone** presents a novel approach to text-to-face synthesis using a Diffusion Model that considers Race Fairness. Our method uses facial segmentation masks to edit specific facial regions, and employs a Stable Diffusion v2 Inpainting model trained on a curated Asian dataset. We introduce two key losses: **βπΉπΉπΈ** (Focused Feature Enhancement Loss) to enhance performance with limited data, and **βπ«π°ππ** (Difference Loss) to address catastrophic forgetting. Finally, we apply **Simple Preference Optimization** (SimPO) for refined and enhanced image generation.
|
| 22 |
|
| 23 |
## Model Checkpoints
|
| 24 |
+
|
| 25 |
- [Anonymize-Anyone (Inpainting model with **βπΉπΉπΈ** and **βπ«π°ππ**)](https://huggingface.co/fh2c1/Anonymize-Anyone)
|
| 26 |
- [SimPO-LoRA (Diffusion model with **Simple Preference Optimization**)](https://huggingface.co/fh2c1/SimPO-LoRA-1.2)
|
| 27 |
|