If you do like this work, consider buying me a coffee :)
Updated - Mid Year: Updated with a lora created from a frest dataset merged with ICBINP Final. Should give decent results, but does have the standard AI issues (cleft chin bias etc..)
Recommended settings: DPM++ 3M SDE Karras or DPM++ 2M Karras, 20-30 steps, 2.5-5 CFG (or use Dynamic Thresholding), happiest at 640x960 with a hires fix on top, but if you are happy to hunt through seeds to avoid head duplicates, 768x1152 works quite well also.
Following on from Gorilla With A Brick, I've merged in 10 more photorealistic models at various weights, and some more noise offset to create something that when prompted for photorealism will make you go "I Can't Believe It's Not Photography". It will happily create CGI characters and awesome landscapes as well.
As always, pruned to fp16, the VAE is baked in (SD-v2 840000 - ignore the VAE requirement above as the system is borked!), and the man in the suit can be used as the calibration prompt on any UI!
Description
ICBINP Final + LCM_Lora at 0.5a, 0.25b
FAQ
Comments (6)
Hello, I left you a publication, please review it.
I have tried in every possible way to configure the Final LCM so that it gives me a smoother and more realistic texture of the generated images, but I have not been able to do so. Maybe it's because of the LCM model itself, or because I need to configure something.
I so tired.
I cant find your publication??
It could be the LCM model. My initial thought is are you able to recreate the sample shots? If not, that would be the place to start (the LCM sampler is probably not optional on it, and in a1111 requires the sd-webui-animatediff extension to enable that sampler). If you were able to recreate them then yeah, it's likely just a limitation of the LCM model :(
@residentchiefnz https://civitai.com/posts/994306 This is.
Seco or afterburn which to use?
I reckon SECO gives a better image but Afterburn plays nicer with LoRAs.
@Malessar New Year is live now :)