Portrait of a Mexican woman in a dark setting, softly illuminated with detailed gold embroidery on her dress, captured in a photographic style.
Black supercar driving fast on a snow-covered road in the Austrian Alps after a rainstorm, with cinematic sunlight and volumetric clouds overhead, viewed from the front left.
Black and white portrait of an Irish woman with strange hair blowing a bubble gum bubble, featuring Rembrandt lighting and a grainy, analog texture reminiscent of daguerreotype photography.
Blonde female police officer wearing a black uniform and matching black facemask standing on New York streets at night.
Close-up portrait of a pensive young brunette woman with detailed skin and sparkling eyes, half of her face concealed in shadow with side lighting on a dark background.
Fashion portrait of a young woman in a red turtleneck standing amidst a large installation of white balloons of various sizes.
Portrait of a girl with brown curly hair and brown eyes, wearing a white polka dot dress and a necklace, lit with cinematic studio lighting.

推奨ネガティブプロンプト

colorful Photo,soft Photo

推奨パラメータ

samplers

DPM++ 2M, DPM++ SDE, DPM++ SDE Karras, DPM++ 2M Karras

steps

20 - 35

cfg

4 - 7

resolution

512x768, 640x960, 960x720, 720x960

推奨ハイレゾパラメータ

upscaler

4x_NMKD-Superscale-SP_178000_G

upscale

2

steps

10 - 15

denoising strength

0.2 - 0.35

ヒント

Use simple prompts without 'masterpiece, photorealistic, 4k, 8k, super realistic, realism' to let the model shine.

Avoid using a ton of negative embeddings; focus on few tokens or single embeddings.

You can still use atmospheric enhancers like 'cinematic, dark, moody light'.

No extra noise-offset needed during sampling.

バージョンのハイライト

get that crappy look of reallife Photos somehow into 1.5, understanding and variety is very low

クリエイタースポンサー

Welcome to epiCPhotoGasm

This Model is highly tuned for Photorealism with the tiniest amount of exessive prompting needed to shine.
All Showcase images are generated without Negatives (V1) to show what is possible on the bare prompt.

Whats special?

The model has highly knowledge of what a photo is, so if u promt u can avoid using photo. If the prompt tends to be fantasy like the model will turn away from photo and u have to tweak by prompting and/or negatives.

The model can do various ethnicities well, so try them out.

Age is also well trained and known by the model, so try them out too.

How to use

  • use simple prompts without "fake" enhancers like "masterpiece, photorealistic, 4k, 8k, super realistic, realism" etc.

  • don't use a ton of negative embeddings, focus on few tokens or single embeddings

  • you can still use atmospheric enhances like "cinematic, dark, moody light" etc.

  • start sampling at 20 Steps

  • no extra noise-offset needed

Additional Ressources

Style Negatives: colorful Photo | soft Photo

Useful Extensions

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

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

投稿者

前の画像
96yottea | Style LoRa - 96yottea
次の画像
Nevolution SDXL - v2-anim

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

AmateurRealLife

モデルハッシュ

163b8d0c3d

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。