【無料】Waifu Diffusion の使い方【AIイラスト作成】

GドライブにGoogle Colabアプリをインストール

編集 → ノートブックの設定 → ハードウェアアクセラレータを「GPU」に設定変更し保存

!pip install diffusers==0.3.0 transformers scipy ftfy

import torch

from torch import autocast

from diffusers import StableDiffusionPipeline, DDIMScheduler

# StableDiffusionパイプラインの準備

pipe = StableDiffusionPipeline.from_pretrained(

“hakurei/waifu-diffusion“,

torch_dtype=torch.float16,

revision=”fp16″,

scheduler=DDIMScheduler(

beta_start=0.00085,

beta_end=0.012,

beta_schedule=”scaled_linear”,

clip_sample=False,

set_alpha_to_one=False,

).to(“cuda”)

prompt = “ここに呪文（プロンプト）を入力“

with autocast(“cuda”):

images = pipe(prompt, guidance_scale=7.5).images

images[0].save(“output.png”)

“A princess with silver hair and black gothic lolita dress, fairy tale style background, a beautiful half body illustration, top lighting, perfect shadow, soft painting, reduce saturation, leaning towards watercolor, art by hidari and krenz cushart and wenjun lin and akihiko yoshida,highly detailed, elaborate, digital painting hyper quality, 8k”
“cute girl with silver hair and black dress, fairy tale style background, a beautiful half body illustration, top lighting, perfect shadow, soft painting, reduce saturation, leaning towards watercolor, art by hidari and krenz cushart and wenjun lin and akihiko yoshida,highly detailed, elaborate, digital painting hyper quality, 8k”