BF95's Krea2 Dark Realism Update 3.0

Please share your results on this page, I'd love to see what you make.

Krea2-Dark-Realism merged model is Krea2 turbo, merged as written below with DarkBeast Krea2, updated with the latest version of Realism Engine Ideogram 4 + Krea 2

The LoRA is baked in at a strength of 1.0.

This is the baseline:

• CFG 1.0
  Steps 8

• Euler/Simple

However you can try other settings.
I've had success with:

• er_sde/simple

• dpm++ 2m sde/simple

and sometimes if the details are low, try turning up the steps and the cfg.
I've had good results with up to 12 steps at CFG 1.5

I'm happy with the results of this latest kitbash model, so I'm sharing with the community.

Acknowledgements:

Please also check out the creators who's work went into this model:
KREA 2 Turbo

Dark Beast Krea2 赤佬🐱‍👤黑兽 Aggressive Edition

Realism Engine Ideogram 4 + Krea 2

_________________________________________________________________________

Update 2.0: Renamed to be more realistic to its nature.
Krea2-Dark-Realism merged model is Krea2 turbo, merged as written below with DarkBeast Krea2, and now I've baked in a great LoRA from @razzz that brings some extra NSFW quality and overall skin texture improvements.

Again, not for everyone, but I thought I'd share it as it works for my own purposes.

Thank you to the original creators, please check them out and use their stuff if it suits you, but also give this a try and let me know what you think.

KREA 2 Turbo

Dark Beast Krea2 赤佬🐱‍👤黑兽 Aggressive Edition

Realism Engine Ideogram 4 + Krea 2

DarkBeast Krea 2 Turbo Merge

Or really, Krea 2 Turbo with a little DarkBeast on the side. This isn't meant to make DarkBeast better, but rather bring a little of their magic and edge into everyday Instagram like images.

All credit goes to the original authors of Krea and the wizards at @AiMetatron and their already perfect Dark Beast | 黑兽 INT8 Convrot 2倍速 | Krea2 Aggressive Edition

I wanted to try a model merge so I took the OG Krea 2 Turbo and blended in the Dark Beast. I am happy with the results so I will share here, but I encourage you to download the original Dark Beast and Krea 2 Turbo models for your creations as my merge may not be to everyone's liking.

The results?

A custom Krea 2 Turbo merge combining the speed, prompt adherence, and low-step performance of Krea 2 Turbo v1.0 with the darker, more dramatic visual character of DarkBeast Krea 2.

The goal of this merge was not to create a simple 50/50 blend. Instead, the model preserves most of Krea 2 Turbo’s core conditioning and early transformer structure, while gradually introducing more DarkBeast influence through the middle and later transformer blocks.

The result retains excellent performance at 8 steps, while adding richer contrast, moodier lighting, more detailed textures, and a stronger cinematic or dark-fantasy aesthetic.

Merge Structure

Model 1: Krea 2 Turbo v1.0
Model 2: DarkBeast Krea 2

The merge uses Krea 2 Turbo as the primary structural base.

Key timestep and projection layers remain approximately 90% Krea 2 Turbo to preserve distilled low-step behaviour. Text-conditioning layers remain mostly Turbo-biased for reliable prompt adherence.

DarkBeast influence increases gradually across the transformer stack:

• Blocks 0–6: 25% DarkBeast

• Blocks 7–13: 35% DarkBeast

• Blocks 14–20: 40% DarkBeast

• Blocks 21–27: 45% DarkBeast

The final output section returns to a stronger Krea 2 Turbo weighting for stability.

Merge Ratios

first.                                  0.80
tmlp.                                   0.90
txtmlp.                                 0.70
tproj.                                  0.90

txtfusion.layerwise_blocks.0.           0.70
txtfusion.layerwise_blocks.1.           0.70
txtfusion.projector.                    0.80
txtfusion.refiner_blocks.0.             0.65
txtfusion.refiner_blocks.1.             0.65

blocks.0 through blocks.6               0.75
blocks.7 through blocks.13              0.65
blocks.14 through blocks.20             0.60
blocks.21 through blocks.27             0.55

last.                                   0.70

Ratios represent the amount of Model 1, Krea 2 Turbo v1.0. The remaining percentage comes from DarkBeast Krea 2.

Recommended Settings

The model performs well using standard Krea 2 Turbo workflows.

Suggested starting point:

Steps: 8
CFG: 1.0
VAE: qwen_image_vae.safetensors
Text encoder: qwen3vl_4b_fp8_scaled.safetensors
Sampler: er_sde
Scheduler: sigmoid_offset
You can also use euler/simple

The model can also be tested at 9 or 10 steps for additional refinement, although 8 steps already produces strong results. Too high add unwanted noise.

Strengths

• Strong performance at low step counts

• Good prompt adherence

• Cinematic and dramatic lighting

• Rich contrast and atmospheric rendering

• Detailed faces, clothing, textures, and environments

• Excellent skin texture

• Works well for NSFW or SFW

• Particularly suitable for dark fantasy, gothic, cinematic, fashion, portrait, and dramatic photographic imagery

Notes

This is an experimental model merge and may behave differently from either parent model depending on the prompt and workflow.

It was created with ComfyUI’s native ModelMergeKrea2 node and saved as a standalone Krea 2 diffusion model.

Please do not share or re-merge this model without giving credit to @AiMetatron