沙村広明作品4千枚ほどでFine tuningを施したautismmixSDXL_autismmixPony出来は良くないが死蔵するのも惜しいので公開<a target="_blank" rel="ugc" href="https://github.com/NEXTAltair/Lorayougazouwoiroirosurusukuriputo">Lorayougazouwoiroirosurusukuriputo</a>1.画像を最大1024x1024の近似で32の倍数になるように縮小2.GPT-4-Turboでタグとキャプションの作成 話は変わるがエグい絵が多い画集ひとでなしの恋の画像はプロンプトを拒否されるかと思ったが拒否されたのは4､5枚で済んだ｡エグすぎて何やってるのか理解してない可能性がある3.VAST.AIでH100を借りて10epochThis model, named "autismmixSDXL_autismmixPony," was fine-tuned using approximately 4,000 images from works by Hiroyuki Samura. Although the quality may not be perfect, it was deemed too valuable to remain unused and hence has been made public.Lorayougazouwoiroirosurusukuriputo Script Overview:<ol><li>Image Resizing: Images were resized to the nearest multiple of 32, with a maximum dimension of 1024x1024 pixels.</li><li>Tag and Caption Generation: Tags and captions were generated using GPT-4-Turbo. It's noteworthy that while most images from the intense and graphic collection "Hitodenashi no Koi" were accepted, only four or five were rejected, possibly due to the AI not fully understanding the extreme content.</li><li>Training Details: The model was trained using <a target="_blank" rel="ugc" href="http://VAST.AI">VAST.AI</a>'s H100 instance for 10 epochs, facilitating the computation-intensive process.</li></ol>

Files with SHA256: 7d38215ed0c7c1eba61b8ee407345ea613c9e86a8421bacb0edfe63ca63d1f8a