DoRA is trained on stickers from various artists from the VK website.
Trigger words: There were no trigger words in the dataset, but I recommend using tags on image composition such as close-up, portrait, upper body, cowboy shot, etc. in the prompt. I also recommend using the white background tag.
Example prompt: very aesthetic, newest, best quality, masterpiece, absurdres, 1girl, ganyu (genshin impact), smile, upper body, white background
DoRA weight: I recommend using the DoRA weight between 0.7 and 0.85. I personally use 0.85.
Recommended model: DoRA was trained on the AnimagineXLV31 model, so I recommend using it.
Clip skip: The clip skip of the DoRA is 2, just as specified for the AnimagineXLV31 model.
When writing a prompt, I recommend following the guidelines that are specified for AnimagineXLV31.
I also recommend using Adetailer.
This DoRA doesn't do well with eyes because of the dataset.