Update README.md

README.md

@@ -11,25 +11,25 @@ library_name: diffusers
 
 
 ---
-# Anonymize Anyone: Toward Race Fairness in Text-to-Face Synthesis using Simple Preference Optimization in Diffusion Model
+# Ano-Face-Fair: Race-Fair Face Anonymization in Text-to-Image Synthesis using Simple Preference Optimization in Diffusion Model
 
 For detailed information, code, and documentation, please visit our GitHub repository:
-[Anonymize-Anyone](https://github.com/fh2c1/Anonymize-Anyone)
+[Ano-Face-Fair](https://github.com/i3n7g3/Ano-Face-Fair)
 
-## Anonymize Anyone
+## Ano-Face-Fair
 
-![anonymiza-anyone demo images](./assets/Fig1.png)
+![Ano-Face-Fair demo images](./assets/Fig1.png)
 
 ## Model
 
 ![overall_structure](./assets/Fig2.png)
 
-**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: **ℒ𝐹𝐹𝐸** (Focused Feature Enhancement Loss) to enhance performance with limited data, and **ℒ𝑫𝑰𝑭𝑭** (Difference Loss) to address catastrophic forgetting. Finally, we apply **Simple Preference Optimization** (SimPO) for refined and enhanced image generation.
+**Ano-Face-Fair** 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: **ℒ𝐹𝐹𝐸** (Focused Feature Enhancement Loss) to enhance performance with limited data, and **ℒ𝑫𝑰𝑭𝑭** (Difference Loss) to address catastrophic forgetting. Finally, we apply **Simple Preference Optimization** (SimPO) for refined and enhanced image generation.
 
 ## Model Checkpoints
 
-- [Anonymize-Anyone (Inpainting model with **ℒ𝐹𝐹𝐸** and **ℒ𝑫𝑰𝑭𝑭**)](https://huggingface.co/fh2c1/Anonymize-Anyone)
-- [SimPO-LoRA (Diffusion model with **Simple Preference Optimization**)](https://huggingface.co/fh2c1/SimPO-LoRA-1.2)
+- [Ano-Face-Fair (Inpainting model with **ℒ𝐹𝐹𝐸** and **ℒ𝑫𝑰𝑭𝑭**)](https://huggingface.co/i3n7g3/Ano-Face-Fair)
+- [SimPO-LoRA (Diffusion model with **Simple Preference Optimization**)](https://huggingface.co/i3n7g3/SimPO-LoRA-Diffusion)
 
 ### Using with Diffusers🧨
 
@@ -43,11 +43,11 @@ from diffusers import StableDiffusionInpaintPipeline
 
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 sd_pipe = StableDiffusionInpaintPipeline.from_pretrained(
-    "fh2c1/Anonymize-Anyone",
+    "i3n7g3/Ano-Face-Fair",
     torch_dtype=torch.float16,
     safety_checker=None,
 ).to(device)
-sd_pipe.load_lora_weights("fh2c1/SimPO-LoRA-1.2", adapter_name="SimPO")
+sd_pipe.load_lora_weights("i3n7g3/SimPO-LoRA-Diffusion", adapter_name="SimPO")
 sd_pipe.set_adapters(["SimPO"], adapter_weights=[0.5])
 
 def generate_image(image_path, mask_path, prompt, negative_prompt, pipe, seed):
@@ -62,8 +62,8 @@ def generate_image(image_path, mask_path, prompt, negative_prompt, pipe, seed):
                   negative_prompt=negative_prompt, generator=generator)
     return result.images[0]
 
-image = '/content/Anonymize-Anyone/data/2.png'
-mask = "/content/Anonymize-Anyone/data/2_mask.png"
+image = '/content/Ano-Face-Fair/data/2.png'
+mask = "/content/Ano-Face-Fair/data/2_mask.png"
 prompt = "he is an asian man."
 seed = 38189219984105
 negative_prompt = "low resolution, ugly, disfigured, ugly, bad, immature, cartoon, anime, 3d, painting, b&w, deformed eyes, low quailty, noise"
@@ -78,8 +78,8 @@ generated_image
 ```
 ![result](./assets/Fig3.png)
 
-For more detailed usage instructions, including how to prepare segmentation masks and run inference, please refer to our [GitHub repository](https://github.com/fh2c1/Anonymize-Anyone).
+For more detailed usage instructions, including how to prepare segmentation masks and run inference, please refer to our [GitHub repository](https://github.com/i3n7g3/Ano-Face-Fair).
 
 ## Training
 
-For information on how to train the model, including the use of **ℒ𝐹𝐹𝐸** (Focused Feature Enhancement Loss) and **ℒ𝑫𝑰𝑭𝑭** (Difference Loss), please see our GitHub repository's [training section](https://github.com/fh2c1/Anonymize-Anyone#running_man-train).
+For information on how to train the model, including the use of **ℒ𝐹𝐹𝐸** (Focused Feature Enhancement Loss) and **ℒ𝑫𝑰𝑭𝑭** (Difference Loss), please see our GitHub repository's [training section](https://github.com/i3n7g3/Ano-Face-Fair#running_man-train).