Type | |
Stats | 1,203 |
Reviews | (84) |
Published | Oct 23, 2024 |
Base Model | |
Usage Tips | Clip Skip: 2 |
Hash | AutoV2 EB04E13338 |
This model is a merger of PonyDiffusion, PonyDiffusion derivative models, and other photorealistic models. It features straightforward prompt responses, rich expressive power, and outstanding realism.
このモデルは、PonyDiffusion およびPonyDiffusion派生モデル、その他フォトリアル系モデルをマージしたモデルです。
素直なプロンプト反応とバリエーション豊かな表現力、そして群を抜くリアリティさを特徴としています。
Generation settings
Conforms to pony generation. Particularly for quality tags, please check the official pony explanation. If you understand Japanese, please refer to my note article.
ponyの生成に準拠します。
特にクオリティタグについてはpony公式の解説を確認してください。
日本語がわかる方は私のnote記事を参照してください。
My Settings
quality prompt:
score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,
realistic eye,(realistic:1.2),(real:1.2),(photorealistic:1.1), ultra photo-realistic, 8k uhd, highres, extremely detailed,
negative prompt:
worst quality, low quality, normal quality, lowres, bad anatomy, bad hands, source_pony, comic, 3d,middle age,adult,mother,mature female, milf,Muscles,censor, bar censor, mosaic censorship, text, signature
Sampling method: Euler a
Sampling steps: 30-40
Upscaler: ESRGAN_4x
Hires steps: 10
Denoising strength: 0.35
CFG Scale: 6-8
Extensions: ADetailer
License
This model is licensed under a modified Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/) license.
The following modifications have been added to Fair AI Public License:
You are not permitted to run inference of this model on websites or applications allowing any form of monetization (paid inference, faster tiers, etc.). This applies to any derivative models or model merges.