Update README.md

README.md

@@ -34,13 +34,15 @@ base_model: BackGwa/LUMIERE-Q
 instance_prompt: >-
   backgwa, solo, pale blue hair, cat ears, golden eyes, navy beret, white shirt,
   red ribbon, oversized sleeves, blue jacket
-license: creativeml-openrail-m
+license:
+- creativeml-openrail-m
+- mit
 ---
 
 # Overview
-This LoRA is an SDXL-based character LoRA created to reproduce the `BACKGWA` character.
+Character-LoRA is an SDXL-based character LoRA created to reproduce the `BACKGWA` character. This LoRA was trained on a copyright-conscious synthetic image dataset.
 
-This project was conducted for research purposes to protect the copyright, creative style, training rights, and intellectual property held by the original artist of this character.  
+This project was conducted for research purposes to protect the copyright, creative style, training rights, and intellectual property held by the original artist of this character.
 Instead of using images directly created by the artist as training data, this LoRA was trained only on an AI-generated synthetic image dataset.
 
 Through this approach, the project explores a way to build a character LoRA without directly using the original character images or the artist's work as training data.
@@ -55,13 +57,12 @@ Through this approach, the project explores a way to build a character LoRA with
 - Redistribution of this LoRA by third parties is prohibited in principle. However, it may be permitted if the original creator is clearly credited and proper attribution is provided.
 
 ## Trigger Word
-You can use the `BACKGWA` character by entering the trigger prompt below.  
-This prompt includes the key visual features and default outfit elements required to generate the character.
 
-If you want to change specific details such as the outfit, expression, pose, background, or composition, you can keep the base trigger prompt and add or adjust the desired elements as needed.
+Use the trigger word below to activate the `BACKGWA` character.
+You can add extra prompts for outfit, expression, pose, background, or composition as needed.
 
 ```text
-backgwa, solo, pale blue hair, cat ears, golden eyes, navy beret, white shirt, red ribbon, oversized sleeves, blue jacket
+backgwa
 ```
 
 ## Usage
@@ -75,28 +76,27 @@ For the most stable and consistent results, it is recommended to use it with the
 ---
 
 # Training
+
 This LoRA was trained without using any human-made artwork as training data.
 
-The dataset consists of 28 synthetic images generated with GPT Image 2.  
-These images were created specifically for this LoRA training process and were not collected from, derived from, or reused from artwork produced by human artists.
+The dataset consists of 48 synthetic images generated with GPT Image 2.  
+These images were created specifically for this LoRA training process, and were not collected from, derived from, or reused from artwork created by human artists.
 
-To prepare the initial image-generation prompts, the original character image was provided as an image input to the locally executed [`gemma-4-E4B-it`](https://huggingface.co/google/gemma-4-E4B-it) model.  
-Predefined prompts and instructions were used to guide the model in producing text prompts capable of reconstructing the character from the provided reference image.
+To prepare the initial image-generation prompts, the original character image was provided as a reference image to the locally executed [`gemma-4-E4B-it`](https://huggingface.co/google/gemma-4-E4B-it) model.  
+Predefined prompts and instructions were used to guide the model in generating text prompts capable of reconstructing the character from the provided reference image.
 
-Using those reconstructed prompts, synthetic character images were generated with GPT Image 2.  
-When suitable high-quality outputs were obtained, some of them were also used as additional references for further image generation.
+Using these reconstructed prompts, synthetic character images were generated with GPT Image 2.
 
-The generated images were then labeled using GPT-5.5.  
-These labels describe the visible character features, outfit elements, composition, and other relevant image details used during training.
+The generated images were then separately labeled using GPT-5.5.  
+These labels describe the visible visual features, outfit elements, composition, and other relevant details used during training.
 
-A total of 28 synthetic images were used for training.  
-The LoRA was trained on the SDXL-based [`LUMIERE-Q`](https://huggingface.co/BackGwa/LUMIERE-Q) model, with 10 repeats and 10 epochs at a resolution of `1024x1024`.
+A total of 48 synthetic images were used for training.  
+The LoRA was trained on the SDXL-based [`LUMIERE-Q`](https://huggingface.co/BackGwa/LUMIERE-Q) model at a resolution of `1024x1024`, with 10 repeats and 10 epochs.
 
 |Parameter|Setting|
 |---|---|
 |Base Model|[`LUMIERE-Q`](https://huggingface.co/BackGwa/LUMIERE-Q)|
-|Model Type|`SDXL-based`|
-|Dataset Size|`28 images`|
+|Dataset Size|`48 images`|
 |Epochs|`10`|
 |Repeats|`10`|
-|Resolution|`1024x1024`|
+|Resolution|`1024x1024`|