Close-up portrait of a woman with pink hair wearing round black glasses, a black and white beanie, and a black turtleneck, showing natural skin texture and pores.
View of Norway's coastline featuring rocky cliffs, turquoise foamy waves crashing on shore under a stormy sky with a luminous sunset breaking through clouds.
A young woman posing stylishly in a pale translucent satin dress with a messy bun hairstyle, softly lit against a muted background.
A realistic, front-view portrait of a smiling young catholic nun signing documents inside a church with a large cross in the background.
Stable Diffusionを使用して生成された、編み込みの髪をした女の子がコージーなセーターを着ているポートレート画像。
編み込みの髪を持つ若い女性が、高い襟のドレスを着て横を見ているポートレート。自然光を使用し、Stable DiffusionでAI生成。
安らかな微笑みを浮かべる若い女性が、クリーム色の居心地の良いタートルネックセーターを着ている、Stable Diffusion AIで作成された。
高級ホテルの部屋でエレガントな装いの女の子がベルベットソファに寛いでいる姿。劇的な照明と緻密なディテール。

推奨ネガティブプロンプト

few tokens or single embeddings,style negatives like colorful Photo, soft Photo

推奨パラメータ

samplers

DPM++ 2M, Restart

steps

10 - 22

cfg

1 - 6

resolution

600x800, 640x960

推奨ハイレゾパラメータ

upscaler

4x_NMKD-Siax_200k, 4x_NMKD-Superscale-SP_178000_G, 4x_UniversalUpscalerV2-Sharp_101000_G

upscale

2

steps

10 - 11

denoising strength

0.2 - 0.3

ヒント

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

Don't use a ton of negative embeddings; focus on few tokens or single embeddings.

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

Start sampling at 20 steps.

No extra noise-offset is needed.

バージョンのハイライト

have to rush, but belive me - it's insane :D

Samples will follow next week if i have the time for that.

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
Flux_White_SaMay - v1.0
次の画像
Purple Grace | Style Lora - 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

Ultimate Fidelity

モデルハッシュ

e44c7b30c6

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。