Update README.md

README.md

@@ -73,34 +73,37 @@ Total steps is: (4+8)x(164x10+94x16)=37,728
 ![sample](https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/37f81f5e-ae3d-44c1-9bf1-daf31fcff800/width=800/185488)
 
 # Charater from Honkai impact
-## Elysia/爱莉希雅
+## Elysia/爱莉希雅-V2
 ### Brief intro
-LORA of Elysia, with 4 costumes in game. civitAI page [Download](https://civitai.com/models/14616)
+LORA of Elysia, with 5 costumes in game. civitAI page [Download](https://civitai.com/models/14616)
 ### Training dataset
 #### Default costume/Miss Pink Elf
-70 images in total, in folder "14_Elysia (miss pink elf) 1girl"
-* 40 normal illustrations, non-nude
+75 images in total, in folder "14_Elysia (miss pink elf) 1girl"
+* 45 normal illustrations, non-nude
 * 30 normal 360 3D model snapshots
 #### Default herrscher costume/herrscher of human:ego
-93 images in total, in folder "11_elysia (herrscher of humanego) 1girl"
-* 33 normal illustrations, included few NSFW, not completely nude though
-* 60 normal 360 3D model snapshots
+129 images in total, in folder "11_elysia (herrscher of humanego) 1girl"
+* 39 normal illustrations, included few NSFW, not completely nude though
+* 90 normal 360 3D model snapshots
 #### Miad costume
-62 images in total, in folder “16_Elysia-maid 1girl”
-* 33 normal illustrations, non-nude
+75 images in total, in folder “16_Elysia-maid 1girl”
+* 45 normal illustrations, non-nude
 * 30 normal 360 3D model snapshots
 #### swimsuit
-74 images in total, in folder “14_elysia-swimsuit 1girl”
-* 14 normal illustrations, non-nude
+80 images in total, in folder “14_elysia-swimsuit 1girl”
+* 20 normal illustrations, non-nude
 * 60 normal 360 3D model snapshots
-In addition, I have also included 12 images with non-official costumes in a new folder "10_Elysia 1girl"
+In addition, I have also included 52 images with non-official costumes in a new folder "10_Elysia 1girl"
+
 ### Captioning
-WD14 captioning instead of the deepdanbooru caption was used, since the former one will not crop/resize the images. Threshold are usually set to 0.75-0.8. since I don't like to have a very long and sometimes inaccurate caption for my training data. After captionin is done, I added "elysia \ \(miss pink elf\ \) \ \(honkai impact\ \)", "elysia \ \(herrscher of human:ego\ \) \ \(honkai impact\ \)", "Elysia-maid", "Elysia-swimsuit" and "1girl, elysia \ \(honkai impact\ \)" to the captioning respectively as identifiers.
+Captioning with WD1.4, with threshold 0.7.
+After the auto captionin is done, I added "elysia \ \(miss pink elf\ \) \ \(honkai impact\ \)", "elysia \ \(herrscher of human:ego\ \) \ \(honkai impact\ \)", "Elysia-maid", "Elysia-swimsuit" and "1girl, elysia \ \(honkai impact\ \)" to the captioning respectively as identifiers. In addition, I also manually editted the captioning to make sure that there was no overlap of prompts between each concepts.
 ### Training setup
 Trained with Kohya_SS stable diffusion trainer Base model was [Anything V3.0 full](https://huggingface.co/Linaqruf/anything-v3.0/blob/main/anything-v3-fp32-pruned.safetensors) Trainig process consist of two phases. The first one with default parameters of:
-* learning_rate: 0.0001
-* text_encoder_lr: 5e-5
-* unet_lr: 0.0001 and 4 epoch,
-After phase 1, choose the one with the best result (a little bit underfitting, no over fitting, and the two costume are seperated), which is the 6th one. Then trained with 1/10 of the original LR for another 8 epochs.
+* Lion, Cosine with restarts
+* learning_rate: 0.00003
+* text_encoder_lr: 15e-6
+* unet_lr: 0.00003
+Trained for 10 epochs with upper parameters, feel underfit, thus trained another 2 epoch with 1/3 the initial LR.
 ### Result
-![sample1](https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9a699f92-b026-4efb-9714-6d6e2675f400/width=800/174757)
+![sample1](https://imagecache.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bfe9c4fd-4966-4322-284f-4424e4a12800/width=800,anim=true/Elysia-V2-examples.jpeg)