
I wanted to test out training character LORAs which aren't present in the dataset using my normal methodology with Illustrious-XL, so here's an Ellen LORA.
There are three versions:
001 uses only screenshots of asset ports to MMD and Koikatsu. Trained to see how well this method works on Illustrious.
002 replaces many of the Koikatsu screenshots with a few images of the most on model fan art I could find. Trained to see how bad the first one is.
010 is trained using a workaround for base_weights. Around 90% of the training images are screenshots.
Both models were trained using a style LORA and SD-Script's base_weights functionality, but my attempts at training one that works well for this purpose haven't been going very well. As a result I think that 001 has a lot of style burn in. Using both LORAs in conjunction at lowered weights might produce results that are relatively style agnostic while still remaining accurate.
As it turns out base_weights doesn't work correctly in the versions of SD-Scripts that I've been using to train Illustrious LORAs. As a result versions 001 and 002 were actually trained against the base model instead of one merged with a style LORA.
描述:
训练词语: ellen joe, red eyes, short hair, black hair, tail, tail print, sharp teeth, red nails, mole/s under eye, earclip,maid, black dress, argyle thighband pantyhose, maid apron, high heels, headdress, wrist cuffs, metal collar, metal tassel, puffy sleeves, back bow,school uniform, brown pantyhose, grey shirt, pleated skirt, school shoes, belt, pendant choker/choker
名称: ellen joe illustrious 002.safetensors
大小 (KB): 201607
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success