Close-up analog portrait of a young woman with pink hair wearing round black glasses, a black beanie, and a black turtleneck against a plain white background.
View of a stormy ocean with foamy waves crashing on a rocky desolate shore under a thunder sky and luminous sunset in Norway.
Young fashion model with messy bun hair wearing a translucent satin dress, posing stylishly with warm Rembrandt lighting highlighting her glossy lips and soft features.
A smiling catholic nun in a church outfit signing documents while sitting in a pew with a large cross visible behind her.
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.

Recommended Negative Prompts

colorful Photo,soft Photo

Recommended Parameters

samplers

DPM++ 2M, Restart

steps

10 - 22

cfg

1 - 6

resolution

600x800, 640x960

Recommended Hires (High-Resolution) Parameters

upscaler

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

upscale

2

steps

10 - 11

denoising strength

0.2 - 0.3

Tips

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.

Atmospheric enhancers like 'cinematic, dark, moody light' are still useful.

Start sampling at 20 steps.

No extra noise-offset needed.

Version Highlights

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

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

Creator Sponsors

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 ❤

Contributor

Previous
Wacky Artsy Paint - v1.0 Flux
Next
fl4t / flat color illustrious - V0.1

Model Details

Model type

Checkpoint

Base model

SD 1.5

Model version

Ultimate Fidelity

Model hash

e44c7b30c6

Creator

Discussion

Please log in to leave a comment.