Download
1 variant available
fp8 SafeTensor
BF95_Krea_Dark_Realism_v4.safetensors
8-bit, smaller file • 12.24 GB
Verified: 4 days ago
Version Changes — v4
Updated the core merge from Dark Beast 2.0 to Dark Beast 3.0.
Refined the layer weighting to preserve more of Krea 2 Turbo's prompt handling and flexibility while bringing in Dark Beast 3.0's stronger realism and cinematic character.
Realism Engine Ideogram 4 + Krea 2 remains baked into the final model for additional photographic realism and detail.
Early testing suggests v4 may also be somewhat faster than v3.25 on my setup. With no LoRAs, 2.0MP images are currently running around 3.06 s/it in KSampler, with complete renders finishing in under 40 seconds. Performance will of course vary by hardware, workflow, resolution, and settings.
Overall, v4 is intended as an evolution of the existing Dark Realism look rather than a complete change in direction.
Show more


6220 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2290 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9

License:
BF95 Krea2 Dark Realism v4
BF95 Krea2 Dark Realism v4 is my latest evolution of this merge, built to push cinematic realism, mood, texture, and stronger photographic character while keeping the excellent flexibility and style range of Krea 2.
Try it with my latest Krea2 ComfyUI Workflow here: BF95 Krea 2 Workflows for ComfyUI
What to Expect
This version aims for:
strong realism and photographic detail
richer skin, texture, and materials
moodier contrast and more cinematic rendering
a dark, polished visual character while still remaining versatile
Compared to my earlier versions, v4 updates the merge with Dark Beast 3.0, then finishes the result with Realism Engine Ideogram 4 + Krea 2 for additional realism and refinement.
Suggested Sampler / Scheduler Combos
These are the combinations I currently suggest testing first:
euler / simple (baseline)
euler_a / beta
euler_a / bong_tangent
er_sde / bong_tangent
er_sde / beta
er_sde / sigmoid_offset
DPM++ 2M SDE / simple
EXP Huen 2 x0 SDE / bong_tangent (ht to @belember)
Notes
As always, results can vary depending on:
prompt style
resolution
guidance settings
LoRAs
sampler / scheduler choice
If you try the model, feel free to share your results and let me know which sampler/scheduler combinations work best for you.
Merge Components
This version is built from:
Krea 2 Turbo
https://civitai.com/models/2732656/krea-2-turboDark Beast 3.0 by AiMetatron
https://civitai.com/user/AiMetatronRealism Engine Ideogram 4 + Krea 2 by razzz
https://civitai.red/user/razzz
Content and Responsible Use Notice
This is a general-purpose merge, but it may generate mature, nude, or sexually explicit content.
Users are responsible for complying with Civitai’s Terms of Service, the applicable model licences, and all relevant laws. Do not use this model to create illegal, exploitative, non-consensual, or otherwise prohibited content.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-==-=-=-=-=-=-=-=-=-=-=
BF95's Krea2 Dark Realism Update 3.25
Please share your results on this page, I'd love to see what you make.
So many creative ideas coming in. Keep them coming! Please post your best images to help this model grow.
Try my simple and fast BF95 KREA 2 Diffusion Workflow for ComfyUI with this model.
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 0.25 in this version as I was finding v3 with the lora at 1.0 strength too aggressive at undressing people and other excessive nsfw content when not wanted.
This is the baseline:
CFG 1.0
Steps 8Euler/Simple
However you can try other settings.
I've had success with:
euler_a/bong_tangent (download RES4LYF node pack in Comfy Manager for Bong_Tangent scheduler)
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
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-==-=-=-=-=-=-=-=-=-=-=
BF95's Krea2 Dark Realism Update 3.0
Please share your results on this page, I'd love to see what you make.
So many creative ideas coming in. Keep them coming! Please post your best images to help this model grow.
Try my simple and fast BF95 KREA 2 Diffusion Workflow for ComfyUI with this model.
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 8Euler/Simple
However you can try other settings.
I've had success with:
euler_a/bong_tangent
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.
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. 0.70Ratios 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/simpleThe 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

