Please read the description for the models i put out. There is some good information that may increase the quality of your output when using my models.
Description
smaller dataset, trained with artists, blob and tubefeeding. All artists upscaled and dataset pruned heavily for high quality outoput. Trained at 640x640. Use clip skip 2 and hiresfix for best output.
FAQ
Comments (3)
Hi. Wouldn't it be possible to make some artist's LORAs out of the ones used in these models?
Or is it someplace you could share/upload your training data so we can try to do it?
Thanks.
Join the discord, there is a link to artist LoRAs there: https://discord.gg/67ZdksCT
@darkforces2 Thanks! I already joined.
There are some LoRA's in there, but not of the artist I'm currently looking for. I usually find myself using this model to generate skinny content using the tags.