Sign In

Real1

0
51
104
0
Updated: Mar 14, 2025
styleanimesemireal
Verified:
SafeTensor
Type
LoRA
Stats
51
104
60
Reviews
No reviews yet
Published
Mar 14, 2025
Base Model
SD 1.5
Hash
AutoV2
DC2F69B663

I am admittedly kind of a noob at this, but if you enjoy my humble work, any donations are greatly appreciated: https://ko-fi.com/insult_to_ninjary

Your generosity helps me stay motivated to keep improving and to keep trying new things!

At a Glance:

  • Base model: Chilloutmix (others will work, but won't give quite the right effect)

  • Use a VAE?: Yes (baked or your choice)

  • Clip skip: 1 or 2 (experiment with both!)

  • LoRA weight: 1 - 0.7 (go lower if your images appear too noisy/busy/garbled)

  • Hires. fix: use non-default upscaler; denoising strength 0.5 - 0.4

Description:

Way back in the day, the site Pixai had a handful of anime models you could use to generate images online, but then they decided to try their hand with a realistic model. The first version of their realistic model wasn't really photorealistic, it kind of just looked like a sort of really realistic anime. Still, it had kind of a charm to it, and I really liked it. However, it was relatively quickly replaced with a second version that produced much more normal photorealism. Sadly, the original first version was never archived in their model marketplace, so it's now completely lost to time. This model is my attempt to give that concept a second life, even if it's not exactly the same as its inspiration.

In the end, I think the model does do a decent job of capturing the intended style, though you may have to specifically use Chilloutmix as the base model in order to achieve it. It will have an effect on other base models, but in the ones I tested, it won't really look like that original Pixai model. Most likely, not many of you even know or care about that model though, so just use whatever you think looks good!

Troubleshooting:

  • The biggest issue you're going to come across is problems with anatomy - hands, fingers, etc. Sometimes even entire limbs. I actually made this model over a year ago, and it shows its age in its occasional instability. If you run into problems, just try your best with all the usual fixes - different prompting, try a different base model, use a VAE, try different clip skip values, lower the LoRA weight, use adetailer, etc.

  • If you're wondering why your images don't look quite like my example images, as I mentioned above, try using Chilloutmix as the base model. It seems to make a big difference!

  • For some reason, this model is pretty horny, lol. I didn't intend for it to be like that, but it just kind of happened somehow! Anyway, if nsfw is not your bag, it should hopefully be easy enough to prompt away from it.

Outro:

If you make anything awesome, please consider posting them to the gallery! That goes for all of my LoRAs! I really like seeing what kind of stuff you all are able to make!

If you have any questions, feel free to ask! I will try my best to help! Also, if you have any ideas for future LoRAs, please don't hesitate to share them with me!