models/ICBINP XL - v2.0

ICBINP XL - v2.0

|
12/3/2025
|
1:28:39 AM
| Discussion|
0
Highly detailed image of a samurai in traditional armor with a fierce Chinese dragon coiled in the background, lit with dramatic volumetric lighting.
Grandpa with gray hair and glasses in a light blue blazer and a young woman with gray hair in a deep pink dress, standing in a bright azure pool with a large white dog and a small kangaroo near a pastel pink wall.
A young woman in a white crop top and shorts walking with fear as a roaring Tyrannosaurus Rex chases her in a dense jungle.
Cinematic photo of a moving Dodge Charger Hellcat at night, driving on a city road with blurred city lights, captured with 35mm film style and bokeh effects.

Recommended Negative Prompts

nsfw, long neck, worst quality, bad quality, poor quality, zombie, blurry, cropped, ugly, out of frame, sketch, depth of field

Recommended Parameters

samplers

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

steps

30 - 35

cfg

2.5 - 7

resolution

832x1216, 1216x832, 832x1216

Recommended Hires (High-Resolution) Parameters

upscaler

Ultimate SD Upscaler, R-ESRGAN 4x+

upscale

1.5

steps

10

denoising strength

0.42

Tips

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

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

Sample images were created with no additional tooling for easier replication.

Version Highlights

Merged v1 with Juggernaut XL v8 using MBW, and added a custom lora I trained to improve realism

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
✨ LazyPositive LazyNegative for ALL illustrious NoobAI Pony SDXL model Lazy Embeddings (Positive and Negative plus more!) - lazynsfw
Next
Lava Gown - v1.0

Model Details

Model type

Checkpoint

Base model

SDXL 1.0

Model version

v2.0

Model hash

45754998aa

Discussion

Please log in to leave a comment.