HDR photo of a muddy World War 1 battlefield featuring tanks moving through deep mud, soldiers advancing beside trenches, and barbed wire in the foreground under dramatic cloudy skies.
Stone cottage with blue shutters surrounded by green fields and flowering garden under a clear blue sky in the French countryside

Recommended Negative Prompts

nsfw, nude, naked, long neck, worst quality, bad quality, poor quality, blurry, zombie, ugly, cropped, out of frame, cartoon, animation, 3d render, illustration, anime, unreal, blender, sketch, watercolor, crayon, impressionist, noisy, soft, depth of field, out of focus, blur, lens blur, bokeh

Recommended Parameters

samplers

DPM++ 2M Karras, DPM++ SDE 3M Exponential

steps

30 - 35

cfg

3 - 7

resolution

832x1216, 1024x1024, 1216x832, 832x1216

other models

ICBINP_XL_V3 (f59b41fc72)

Recommended Hires (High-Resolution) Parameters

upscaler

Ultimate SD Upscaler, 4xUltrasharp

upscale

1.25 - 1.5

steps

15

denoising strength

0.5

Tips

For best realism, avoid additional hi-res fix and use the Ultimate SD Upscaler instead.

To create anime style images, change sampler to DPM++ SDE 3M Exponential and increase CFG to 6-7.

Experimentation and better workflows can lead to amazing results.

Version Highlights

Merged v2 with Fully Real XL, my own trained lora from a larger dataset than the first one, and the DPO lora, then merged back into v2, then more DPO lora and the Add Details lora to finish

More goodness for all :)

Creator Sponsors

If you do like this work, consider buying me a coffee :)

Use v6 of this model for free on Stable Horde

Use this model for free on Shakker.ai

If you do like this work, consider buying me a coffee :)

Use v6 of this model for free on Stable Horde

Use this model for free on Shakker.ai


The long awaited followup to ICBINP, this model is merged to try and get the most realistic images possible. It's the ICBINP you all know and love, but now with all of the benefits of SDXL (recommended 832x1216)


Update: v6
More mixing to try and get something even better than v2, and I think I've found a much nicer balance

The sample images are made in Forge with the DPM++ 2M Karras, 35 steps, 832x1216, cfg 3 - 4, clip skip 2, (some hi-res fix, but the best realism is without it IMO - use the Ultimate SD Upscaler instead) and no additional tooling so should be reasonably easy to replicate.

If you want to push this to make anime, change the sampler to DPM++ SDE 3M Exponential and crank the CFG up to 6-7.

I'm sure that some more experimentation and better workflows you will be able to achieve amazing results!

Previous
Abstract Art - V1
Next
Atomix Flux NF4 - v1.0

Model Details

Model type

Checkpoint

Base model

SDXL 1.0

Model version

v3

Model hash

c9cda74ad1

Discussion

Please log in to leave a comment.