https://github.com/deepghs/waifuc/tree/main
The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently crawl and process over 3000 training images within a span of 2 hours. Training the character "Lora" on this extensive dataset yields significant performance advantages compared to situations with limited data availability.
Trigger Words in page,other tag in lora metainfo.
recommand use model: Kohaku_XL https://civarchive.com/models/162577/kohaku-xl-beta
weight: 0.8~1
Description
FAQ
Comments (11)
hey bro if possible can you make a Lora of tsubakura enraku to XL?
ok,please wait a few day. other project is wip, i have none time in few day.
@Supermachoman
@kitarz Thanks
Greetings, I love yours models, love to have much toho stuff, I was wondering if there was a way to make a request for character named katt rinpoo from breath of fire?, I would love to have a lora working so well as the ones you has been posting of her
I am currently spend all my time try the parameters about train lora based on the "Animagine XL V3" model, which is incredibly powerful. I need some time to figure out the parameters before I can train the new Lora model. However, if you prefer to use the old version of Lora, I can allocate some time for that as well.
@kitarz I did the leap to XL thanks to that one, I would not mind waiting for a XL 3 version, that model is amazing, I thanks you for your time and consideration.
@momijifw I grabbed all the images from several booru sites and tried many different parameter, but all results were poor on A3. It's possible that there aren't many furry pictures in the 1.2m images on A3. I suggest waiting for the base model update.
@momijifw https://civitai.com/models/265863 here
@kitarz Thanks you so much, I check it out, but wait for the update as you say, have a nice day
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.