Open arnage74 opened 2 weeks ago
Sure, I suggest running via the API to do that
You could also try editing predict.py
def predict
From
disable_safety_checker: bool = Input(
description="Disable safety checker for generated images.", default=False
),
To
disable_safety_checker: bool = Input(
description="Disable safety checker for generated images.", default=True
),
def update_workflow
From
negative_prompt["text"] = (
f"(nsfw:2), nipple, nude, naked, {kwargs['negative_prompt']}, lowres, two people, child, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, multiple view, reference sheet, mutated, poorly drawn, mutation, deformed, ugly, bad proportions, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, amateur drawing, odd eyes, uneven eyes, unnatural face, uneven nostrils, crooked mouth, bad teeth, crooked teeth, gross, ugly, very long body, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn eyes"
)
To
negative_prompt["text"] = (
f"{kwargs['negative_prompt']}, lowres, two people, child, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, multiple view, reference sheet, mutated, poorly drawn, mutation, deformed, ugly, bad proportions, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, amateur drawing, odd eyes, uneven eyes, unnatural face, uneven nostrils, crooked mouth, bad teeth, crooked teeth, gross, ugly, very long body, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn eyes"
)
Untested. There may be something easier or other checks in place.
I want to run this model for NSFW content. Is it possible to run it locally without this check?