
Made my own Sazer Visuel Lora because the previous one I uploaded (which was not made by me) could not depict the lower half of the costume accurately lol, hence why most of the showcase images are focused on said lower half hahaha
Would greatly appreciate it if you could read this before posting! https://civitai.com/articles/7060/look-both-ways-before-you-crosspost
Main prompts:
sazervisuel, orange bodysuit, brown leotard, belt, armor, gauntlets, black gloves
Add if doing "full body" or "feet out of frame" (training data set had "boots" as prompt, but from my own testing, "knee boots" seem to get you a more accurate depiction of her boots including her silver knee guards):
boots
For helmet with face covered:
helmet, visor, wearing helmet, covered face, covered mouth, covered eyes
For helmet with face visible:
helmet, wearing helmet, [eye color prompts], [facial expression prompts]
For helmet to be held and not worn (I forgot to actually test this but it should work since there was an example of this in the training data set ?):
helmet, visor, helmet removed, holding helmet
For her claw weapons (which AI seems to struggle to understand what claws are despite images with her wielding them being included in training data set, so your mileage may vary):
claw \(weapon\)
Notes:
-
When generating without helmet, the animal ears portion of the helmet may appear. Including "helmet, animal ears" in negative prompt mostly helps when this happens, but seems like not always
描述:
训练词语: sazervisuel, orange bodysuit, brown leotard, belt, armor, gauntlets, black gloves,boots,helmet, visor, wearing helmet, covered face, covered mouth, covered eyes,helmet, visor, helmet removed, holding helmet,claw \(weapon\)
名称: 939945_training_data.zip
大小 (KB): 8646
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: Sazer_Visuel.safetensors
大小 (KB): 445792
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success