adsd_pipeline / README.md
Bingsu's picture
Upload files: v0.1.1.dev0
79b8418
|
raw
history blame
519 Bytes
metadata
license: agpl-3.0
tags:
  - pytorch
  - diffusers

ADetailer Pipeline

import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "stablediffusionapi/counterfeit-v30",
    torch_dtype=torch.float16,
    custom_pipeline="Bingsu/adsd_pipeline"
)
pipe.safety_checker = None
pipe.to("cuda")

common = {"prompt": "masterpiece, best quality, 1girl", "num_inference_steps": 28}
result = pipe(common=common)

images = result[0]

github: https://github.com/Bing-su/asdff