models/ICBINP XL - v4

ICBINP XL - v4

12/4/2025

11:25:12 AM

Related Keywords & Tags

base model,checkpoint,icbinp v6,icbinp xl,photo,photorealistic,realistic images,sdxl,sdxl 1.0,stable diffusion,unidentified_author,v4

Anime style superhero woman with flowing blonde hair wearing a blue and red armored suit with a gold emblem, surrounded by vibrant red and white flowers under cinematic lighting.

Recommended Negative Prompts

nsfw, nude, naked, long neck, worst quality, blurry, zombie, ugly, cropped, out of frame, cartoon, pixar, disney, 3d render, cgi, illustration, anime, unreal, blender, sketch, watercolor, crayon, impressionist

Recommended Parameters

samplers

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

steps

30 - 35

cfg

3 - 7

clip skip

resolution

832x1216, 832x1216, 1664x2432, 1216x832

vae

fixFP16ErrorsSDXLLowerMemoryUse_v10.safetensors

Recommended Hires (High-Resolution) Parameters

upscaler

Ultimate SD Upscaler, R-ESRGAN 4x+

upscale

steps

denoising strength

0.2 - 0.25

Tips

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

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

Version Highlights

Went back to v2, auto-MBW merge with DPO, merge in a couple of my photo loras (unreleased)

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!