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!
Description
ICBINP XL v4 + Voight Kampff MBW custom then flat merged back into ICBINP XL v4, then added the Midjourney Mimic, Horde Aesthetics Improver, and Extremely Detailed loras in
FAQ
Comments (5)
why it's still 'cartoons' from such title of 'i can't believe it's not photography' !?.
it's absolutely cartoonish plastic render of human images.
Not sure tbh - there is a mix of cartoony and realistic ones in the first batch; the second batch with the different negative prompt and less Perturbed Attention Guidance went much better
Hey @amazingbeauty - have released a v5a version which gives a more photographic result :)
@residentchiefnz hi! I havent tested 5a yet, but I still have version 2 in my models list, it has the most natural/realistic photo look in my opinion. thanks for your work! :)
@mech4nimal V5a has v2 merged into it so might be worth a go :)