Don't use it to post naughty pictures online please.
LCM does work. But sacrifices overall detail and promp coherence.
No special tricks where used to generated the images, no control net, no multi step process with img2img, no ADetailer, nothing just the basic models in SD WEBUI.
Recommendations
This can be used to generate images of 512/768, 768/512, 512/512 and anything in between, in all my testing no duplicate faces were generated.
Best CFG 7 - 9, i would not go any higher unless you wanna pump up the steps too.
Any checkpoint works but you may have to adjust the weight in order to get it to look right, the max usable weight is 1.3.
I recommend Restart/DPM++ 2M for the first pass and Restart/DPM++ 3M SDE for the Hires.fix pass, this will give you the best results.
Don't go above 2.0 times the first pass resolution, is better to pass it to img2img or use some other tricks to obtain more detail.
Extra notes.
The max resolution i tested is 960, it looks good, but expect duplicated subjects and faces.
If you want better face closeups i suggest you to use ControlNet, sd 1.5 is notorious for generating bad face closeups.
Description
Initial release. Trained checkpoint then converted to Lyco.
FAQ
Comments (2)
hmmm not there yet, features are too soft, head to small I think
Just like your other models, this only bears a passing resemblence to the intended subject. If you are training your models against anything other than the SD default checkpoint, that may be why. Given that all your models have virtually the same jawline and overall face shape, it almost appears that they were all trained against a 2.5D model instead of the SD default.
If that's not the case, then your source material may need to be reconsidered. Adding images with more diverse angles would help SD better learn the details and shapes of the faces of your intended subjects.
You also mentioned a max suggested weight of 1.5. Lycoris, and even regular Loras should never need weights that high to obtain/maintain resemblence. If they do, I would seriously reconsider my kohya or Dreambooth training parameters as well.
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.