Please don’t rely only on the LoRA title to understand what it does. The preview images are the real representation of the results you should expect.
My LoRAs are trained on small, focused datasets, so they naturally stay close to the original concept. If a dataset contains green bedrooms, livestream UI, or Smurf-style houses, the LoRA will strongly lean toward those elements. Trying to turn it into something completely unrelated usually will not work well.
Please use the preview images as your main reference and keep the dataset concept in mind while prompting.
If you like one of my LoRAs but want different colors, atmosphere, or no livestream UI, feel free to ask. I’m always happy to remake or adapt a concept into a different version.
Description
FAQ
Comments (3)
I just want say your backgrounds have really improved lately. I understand you aren't doing anima or krea that much, but damn does it make me wish it was for those to.
Okay, I'd love to as well. The problem is that backgrounds are extremely random. Sometimes I'll train a bunch of datasets and they turn out amazing, and other times they're pretty disappointing. It's really hard to predict the outcome—it honestly feels like rolling the dice.
And yes, I'd love to make krea2 and anima too. It's just that the training costs so much Buzz, and hardly anyone is helping anymore. If I receive around 1,000 Buzz in a day, that's only enough to train about two models. So it really depends. When someone donates Buzz and specifically requests a training, I'm happy to do it. Otherwise, I usually have to wait because the Buzz just isn't coming in anymore.Thank you so much. I really appreciate it. You write a lot of comments, and it's genuinely appreciated. It's rare to find people who take the time to say something at all.
@arrssenne Maybe in the future i'll donate some if I get around to purchasing any.