This model can handle 2D, 2.5D, and 3D tasks. Although it's not perfect and might take a few tries to get the desired result, just keep experimenting with your prompts, and eventually, you will achieve what you want.
Best settings:
Sampling Method: Euler A, DPM++ 3M SDE Karras - you can mess around with this
Sampling Steps: 20 ~ 60 depending on your sampling method
Hires. fix: Enabled
Hires Steps: 15 ~ 30
Upscaler: 4x-AnimeSharp - You can test others since this is the only one I ever use.
Denoise Strength: 0.4
Upscale by: Preferably x2
CFG Scale: 6 ~ 9.5
Clip Skip: 2
Important:
Positive prompt must contain: score_9,score_8_up,score_7_up,
Negative prompt can be empty but preferably contain the default pony negatives.
Use "3d" in Negative prompt to generate 2d images.
I use Forge as my main UI because it has so many optimizations for running XL/Pony models on lower end GPU's despite me having a RTX 4090, generations are alot smoother. I'm not sure how this model performs on other UI's.
I haven't done much testing. If there is anything amiss, please let me know. Feedback is always appreciated :). This model excels at portraits.
Post results and, most importantly, have fun!
Description
More consistant 3D/2.5D.
FAQ
Comments (2)
One question please: Beta version is the same as Alpha but "better"? im new and i always see a lot of previous versions uploaded. Thanks for this model is amazin :)
Tyvm!, at the very base yes, but "Beta" can also mean it's better in other places where the "Alpha" was not and vice versa. For some models the creator needs to make compromises to get a "better" result.