模型介绍: I don't speak English so I'm translating at ChatGPT. Let me know if the English is weird. It is a 2D model with flat coloring and no other particular features. It was born as a counterpart to the Featureless JRPG 3D Mix during the adjustment process of the 3D Slider LoRA. Comparing this, you'll realize just how much 3D component was actually in the Featureless Mix. 塗りがフラットな、それ以外の特徴が特にない2Dモデルとなります。 3DスライダーLoRAの調整の過程でFeatureless JRPG 3D Mixの対として誕生しました。 これと比較するとFeatureless Mixなんてすごく3D成分入ってたんだなと気づきますね。 Merging Method / マージ方法 All of the following models are merged so that they are all in the same proportion 以下のモデルをすべて同じ割合になるようマージしています AAM - AnyLoRA Anime Mix - Anime Screencap Style Model v1 https://civitai.com/models/84586?modelVersionId=89927 Flat-2D Animerge v3.0 https://civitai.com/models/35960?modelVersionId=103436 KevaMixFlat v1.0 https://civitai.com/models/146380?modelVersionId=162999 JitQ v2.0 NOTJit https://civitai.com/models/132246?modelVersionId=154039 ClearVAE v2.3 has been merged. / ClearVAE v2.3をマージ済みです。 ~~~~~~~~~~~~~~~~~~~~~~~o(* ̄︶ ̄*)o~~~~~~~~~~~~~~~~~~~~~~~ 示例提示词和参数: Prompt: masterpiece,best quality,1girl,solo,fantasy,serious,smile,motion,simple background,destruction Negative prompt: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, rough sketch,nsfw Steps: 20, CFG scale: 11, Sampler: DPM++ 2M Karras, Seed: 274069949, Size: 512x768, Version: v1.5.2, Model hash: 76ebd0a9d4, Hires upscale: 1.875, Hires upscaler: Latent, Denoising strength: 0.55, Clip skip: 2 |
1人表示很赞