Update README.md

README.md

@@ -15,7 +15,7 @@ Captioning the images properly and put them into different folders respectively,
 ## captioning tips
 I`m trying to find a way to optimize the captioning of identifiers. I`ll write down some of my findings here as a record.
 * It looks like that the more different the trigger prompts are, the better. The exception are my first multi-id Lora "ningguang"
-* The format of promt are different in SD webUI and the captioning file, e.g. the " "and "_". Currently I`m using the webUI format in captioning, and so far so good.
+* ~~The format of promt are different in SD webUI and the captioning file, e.g. the " "and "_"~~, Tried with Barbara model, little difference, but it seems the original format(using"_" instead of " " is better).
 
 
 # Charater from Genshin
@@ -62,7 +62,7 @@ LORA of Elysia, with 4 costumes in game. civitAI page [Download](https://civitai
 ### Training dataset
 #### Default costume/Miss Pink Elf
 70 images in total, in folder "14_Elysia (miss pink elf) 1girl"
-* 20 normal illustrations, non-nude
+* 40 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"