//=time() ?>
I'm training dreambooth model with SD-768.
Results seems to overcooked too fast.
75 refs images
1000 regs
3000 steps
Prompt: "portrait of santa claus, arcane style"
QingShe (Green Skake) in White Snake 2. Dreambooth (left) vs original(right). #StableDiffusion #Dreambooth #NovelAI #1girl
仰向けデアリングタクト #女の子 #AIイラスト #ウマ娘プリティーダービー #デアリングタクト(ウマ娘) #AnythingV3 #Dreambooth #浴衣 https://t.co/q0VBnhvcUR
some more game characters
I should test on some point reusing them in dreambooth to further finetune them eg for faces
Could be a nice and nearly fully automatic pipeline for #stablediffusion in #gamedev
アルダンさんとお出かけ #女の子 #AIイラスト #ウマ娘プリティーダービー #メジロアルダン(ウマ娘) #AnythingV3 #Dreambooth https://t.co/PpHthHUQVB
new grid who dis
prompt is just "[trained tokens] portrait" 🤯 that's almost dreambooth quality
8528diffusion のv0.2を作る過程で、別モデル学習の検証。WDへの学習データには自分が描いた絵(二次創作含む)を利用。#8528d より学習データ枚数が足りないのでめちゃくちゃ傾向が偏るのと制御難易度跳ね上がり。 "自分の絵で簡易追加学習する"ならdreamboothの方がいいかもな……
#dreambooth #stablediffusion experiments. The training set was a bunch of random SD images I made and liked.
#dreambooth #stablediffusion experiments. The training set was a bunch of random SD images I made and liked.
Another #dreambooth #stablediffusion experiment. I guess I shouldn't say "sexy female android" if I don't want nudity.
A quick #dreambooth #stablediffusion experiment. I didn't ask for the nudity but that's fine.