Update README.md

README.md

@@ -29,13 +29,14 @@ This repository is a test project comparing different loss weighting schemes for
 
 ## Test Cases
 
-This repository includes test models using four different weighting schemes:
+This repository includes test models using different weighting schemes:
 
 1. **test_normal_weight**
    - Baseline model using standard weighting
 
 2. **test_edm2_weighting**
    - New loss weighting scheme
+   - implementation by A
 
 3. **test_min_snr_1(incomplete)**
    - Baseline model with `--min_snr_gamma = 1`
@@ -45,9 +46,14 @@ This repository includes test models using four different weighting schemes:
      - `--debiased_estimation_loss`
      - `--scale_v_pred_loss_like_noise_pred`
 
+5. **test_edm2_weight_new(incomplete)**
+   - New loss weighting scheme
+   - Implementation by madman404
+
 ## Training Parameters
 For detailed parameters, please refer to the `.toml` files in each model directory.
-Each model directory uses sdxl_train.py (and sdxl_train.py and t.py for edm2).
+Each model uses sdxl_train.py in each model directory
+(and sdxl_train.py and t.py for test_edm2_weighting, sdxl_train.py andlossweightMLP.py for test_edm2_weight_new)
 
 Common parameters:
 - Samples: 57,373
@@ -57,4 +63,38 @@ Common parameters:
 - Batch size: 8
 - Gradient accumulation steps: 4
 - Optimizer: Adafactor (stochastic rounding)
-- Training time: 13.5 GPU hours (RTX4090) per trial
+- Training time: 13.5 GPU hours (RTX4090) per trial
+
+## Dataset Information
+The dataset used for testing consists of:
+- ~53,000 images extracted from danbooru2023 based on specific artist styles (approximately 300 artists)
+- ~4,000 carefully selected danbooru images for standardization
+
+**Note**: As this dataset is a subset of my regular training data focused on specific artists, the model's generalization might be limited. A wildcard file (wildcard_style.txt) containing the list of included artists is provided for reference.
+
+### Tag Format
+The training follows the tag format from [Kohaku-XL-Epsilon](https://huggingface.co/KBlueLeaf/Kohaku-XL-Epsilon):
+`<1girl/1boy/1other/...>, <character>, <series>, <artists>, <general tags>, <quality tags>, <year tags>, <meta tags>, <rating tags>`
+
+### Style Prompts
+The following style prompts from Kohaku-XL-Epsilon might be compatible (untested):
+```
+ask \(askzy\), torino aqua, migolu, (jiu ye sang:1.1), (rumoon:0.9), (mizumi zumi:1.1)
+```
+```
+ciloranko, maccha \(mochancc\), lobelia \(saclia\), migolu, 
+ask \(askzy\), wanke, (jiu ye sang:1.1), (rumoon:0.9), (mizumi zumi:1.1)
+```
+```
+shiro9jira, ciloranko, ask \(askzy\), (tianliang duohe fangdongye:0.8)
+```
+```
+(azuuru:1.1), (torino aqua:1.2), (azuuru:1.1), kedama milk, 
+fuzichoco, ask \(askzy\), chen bin, atdan, hito, mignon
+```
+```
+ask \(askzy\), torino aqua, migolu
+```
+
+
+*This model card was written with the assistance of Claude 3.5 Sonnet.*