Close-up of a split coconut with water splashing out, set on a sandy beach with palm leaves and turquoise ocean in the background under a bright sun flare.
Front view of a luxury emerald green SUV with illuminated aggressive headlights and large front grill, parked on wet ground with raindrops, forest background under cloudy sky.
Potted olive tree with green leaves in a simple round cream colored pot on a wooden surface against a plain light background
Smiling Asian teen girl wearing rectangle glasses and a striped prison jumpsuit with handcuffs and a belt, in a courtroom setting.
A lone figure walking on a wooden pathway through a dark, foggy landscape under a starry night sky with the Milky Way visible and an eerie atmosphere.
Young brunette woman dressed as a nun wearing black off-shoulder clothing and a cross necklace standing inside a church with stained-glass windows in the background.
Young woman in casual white long-sleeve shirt and denim shorts standing indoors leaning against a wooden door, hands in pockets, looking at the camera with natural expression.
土や岩、大きな緑の葉が茂る森林を特徴とするガラス球体のテラリウムで、柔らかな日光に美しく照らされている。
長い髭を持つ中世の魔法使いの服を着た老人が戦闘姿勢で炎の杖を持ち、火山の背景に立つ。
バットマンとジョーカーの邪悪なハイブリッドの肖像画。狂気の笑いと邪悪な笑み、鋭い牙、そして暗い雰囲気が特徴。

推奨プロンプト

simple explanation of the image

推奨ネガティブプロンプト

cartoon,painting,illustration,(worst quality, low quality, normal quality:2),asian,chinese

推奨パラメータ

samplers

SDE, DPM-Sampler, 2M Karras Sampler, Any Sampler, DPM++ 2M SDE Karras, DPM++ SDE, Restart, DPM++ 2M Karras, DPM++ SDE Karras

steps

20 - 30

cfg

2 - 7

resolution

512x768, 768x512, 512x768, 640x960, 768x512

vae

vae-ft-mse-840000-ema-pruned.safetensors (735e4c3a44)

other models

epiCRealism-naturalSin (84a88972f9)

推奨ハイレゾパラメータ

upscaler

4x_NMKD-Superscale-SP_178000_G

upscale

1.5 - 2

steps

10 - 15

denoising strength

0.3 - 0.35

ヒント

Use simple prompts without extra keywords for best results.

Avoid keywords like 'masterpiece, best quality, 8k, intricate, high detail' or '(extremely detailed face), (extremely detailed hands), (extremely detailed hair)' as they don't improve the output.

Use simple negatives or small negative embeddings for a more realistic look.

Add 'asian, chinese' to negative prompts to avoid Asian ethnicity when undesired.

Light, shadows, and details are excellent without extra keywords.

Avoid using 'cinematic' for a natural effect.

Avoid using '1girl' as it tends to push anime style rendering.

Too much face description often results in worse images.

For fantasy-like outputs, use the 2M Karras Sampler.

No extra noise-offset is needed but optional.

バージョンのハイライト

Since i'm low on time i still wanted to release the RC1 of an new aproach.

  • ordinary faces, natural look, more face diversity

  • hand fix

VAE included

Recommended simple Negative for average looking output, avoid "optimizer" Embeddings

cartoon, cgi, render, illustration, painting, drawing

seems to be a bit nsfw heavy and very lose on prompt guidance for now

クリエイタースポンサー

Natural Sin Final and last of epiCRealism

Since SDXL is right around the corner, let's say it is the final version for now since I put a lot effort into it and probably cannot do much more.

I tried to refine the understanding of the Prompts, Hands and of course the Realism.
Let's see what you guys can do with it.

Thanks to @drawaline for the in-depth review, so i'd like to give some advices to use this model.
[expand to see Advices]

Advices

  • use simple prompts

  • no need to use keywords like "masterpiece, best quality, 8k, intricate, high detail" or "(extremely detailed face), (extremely detailed hands), (extremely detailed hair)" since it doesn't produce appreciable change

  • use simple negatives or small negative embeddings. gives most realistic look (check samples to get an idea of negatives i used)

  • add "asian, chinese" to negative if you're looking for ethnicities other than Asian

  • Light, shadows, and details are excellent without extra keywords

  • If you're looking for a natural effect, avoid "cinematic"

  • avoid using "1girl" since it pushes things to render/anime style

  • to much description of the face will turn out bad mostly

  • for a more fantasy like output use 2M Karras Sampler

  • no extra noise-offset needed, but u can if you like to 😉

How to use?

Prompt: simple explanation of the image (try first without extra keywords)
Negative: "cartoon, painting, illustration, (worst quality, low quality, normal quality:2)"
Steps: >20 (if image has errors or artefacts use higher Steps)
CFG Scale: 5 (higher config scale can lose realism, depends on prompt, sampler and Steps)
Sampler: Any Sampler (SDE, DPM-Sampler will result in more realism)
Size: 512x768 or 768x512
Hires upscaler: 4x_NMKD-Superscale-SP_178000_G (Denoising: 0.35, Upscale: 2x)

Useful Extensions

!After Detailer | ControlNet | Agent Scheduler | Ultimate SD Upscale

⁉ No VAE needed but it is better to use one for more vibrant colors

⭐ Feel free to leave Reviews and Samples - and always have fun creating ❤

投稿者

前の画像
Creepy Cute Magical - v2.0 Flux ER
次の画像
Jibs - Dark Disturbing Dystopia - v1.0

モデル詳細

モデルタイプ

Checkpoint

ベースモデル

SD 1.5

モデルバージョン

Natural Sin RC1 VAE

モデルハッシュ

84d76a0328

作成者

ディスカッション

コメントを残すには log in してください。