今回はdiffusersで選択できるsamplerごとに生成される画像の比較を行ってみました

この記事でわかること

diffusersのsampler変更時に生成画像がどう変化するか

1.実行環境

Google Colab
Diffusers transformers==4.26.0
model : yayoi_mix
sampler：ddpm / ddim / pndm / lms / euler_anc / euler / dpm

2.生成結果

positive = best quality 8k 32k masterpiece photo of pretty japanese women ultra_highres (detailed beautiful skin face focus)

negative=distorted face, badhandv4:0.6, extra fingers, fewer fingers, extra digit, bad hands, bad finger, head cut off, Easy Negative, disfigured, ugly, mutation, deformed, deformed face, long face, cross-eyed, long neck, cross-eyed, mutated hands, polar lowres, bad proportions, gross proportions, abdominal stretch, glans, fused fingers, bad body, malnourished,