Pink and plastic is indeed fantastic!
Usage
Use the trigger word: "BarbieCore" along with the LoRA to activate it.
Example prompt: BarbieCore gundam mech <lora:BarbieCorePony:1>
I've found that most settings work well with this model. No special samplers or CFG-scale.
Note:
I may be using the following extensions in the reference images: FreeU or ADetailer / Face Editor. I may also be using a specific Hires Checkpoint (swaps to another model when doing the hires steps). If your results don't match mine exactly, this may explain why.
Tips and tricks
Here's a list of keywords you can use to enhance the different effects of the model.
For a more 60s toy-like aesthetic, try:
pink
plastic
(toy:0.4)Training Data attached.
Like it?
Description
FAQ
Comments (4)
Hi mate, question over here. I was told to train on Pony XL some weeks ago. How is the style adherence difference from your POV?
Hey there!
I would have to say that I get MUCH weaker result with Pony.
At least for the way that my training works.
I suspect it may be due to the way my style datasets are captioned. They are captioned with a lazy style of tagging, which means I only tag the TriggerWord and the Subject. No other descriptions.
This has worked great for 1.5 and SDXL, but I feel like my styles are MUCH weaker in Pony.
It may be that I need to prompt differently to get good results in Pony. I just don't know yet.
This is awesome, thanks!
Thank you!
Hmm, I'm not sure I like the Pony version much. I think it's a bit less expressive than the SDXL or 1.5 actually. But I also suck at Pony prompting. I just don't know how to get anything good out of it!
If you managed to make something nice, please share a few pictures, I'd really appreciate it and could certainly use a few pointers.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.