ベースモデルはバージョン名参照
約9000枚の画像を解像度2172で追加学習(ver3.1以降)
推奨設定はサンプル画像内蔵のワークフロー参照
base1.0-v3.1
解像度2172で学習やり直し
構図崩れはだいぶ減った・・と思う 多分
変換しただけのINT8ConvRot版はこちら
(botan_animabase1_INT8ConvRot_V3_1.safetensors)
https://huggingface.co/KKTT8823/botan_anima/tree/main/Base1_0
sample画像情報
positive prompt : masterpiece, detailed background, highres, absurdres,
negative prompt : score_1, score_2, score_3, blurry, worst quality, low quality, censored, bar censored, mosaic censoring , jpeg artifacts, signature, watermark, username, normal quality, source cartoon, makeup, simple background,monochrome ,
cfg : 4
Sampling method : Euler_ancestral
scheduler : normal
Description
背景強化
高解像度出力で細部が溶けるのを少し改善
FAQ
Comments (5)
Was there any issue with 2.10?
I accidentally uploaded a prototype that I had previously rejected because something about the expression felt slightly off. It seems I made a mistake when renaming the file for upload.
Neutral style that works well with LoRAs, generates cleanly at 2MP and can create some really great backgrounds.
ありがとうございます！
最新モデルの背景は非常に素晴らしい出来栄えです。その一方で、手や腕には不自然な箇所がより多く見受けられます。
Amazing model!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.