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.
A girl with braids wearing a cozy sweater in a portrait image generated using Stable Diffusion.
Portrait of a young woman with braided hair in a high-collared dress looking to the side, using natural light, AI generated with Stable Diffusion.
A young woman with a serene smile, wearing a cozy cream-colored turtleneck sweater, created using Stable Diffusion AI.
Portrait of a beautiful woman with dark hair, wearing a red vintage lace dress and an ornate choker necklace. AI generated image using stable diffusion.

Prompts négatifs recommandés

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

Paramètres recommandés

samplers

DPM++ 2M, Restart

steps

10 - 22

cfg

1 - 6

resolution

600x800, 640x960

Paramètres haute résolution recommandés

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

Conseils

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.

Points forts de la version

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 ❤

Contributeur

Précédent
Flux_White_SaMay - v1.0
Suivant
Purple Grace | Style Lora - v1.0

Détails du modèle

Type de modèle

Checkpoint

Modèle de base

SD 1.5

Version du modèle

Ultimate Fidelity

Hash du modèle

e44c7b30c6

Créateur

Discussion

Veuillez vous log in pour laisser un commentaire.