相信这位不需要我多介绍了。
最近在准备海贼王全角色，预计包含50个主要角色。
这是全角色lora的子集之一。
TAG:
nami_\(one_piece\),Training model: Pony
Recommend PONY model: Movable figure model Pony/T-ponynai3/AutismMix SDXL
Recommend SDXL model: Kohaku-XL Epsilon
Training resolution: 1024*1024
Recommended output resolution: 832*1216
Discord : https://discord.com/invite/CFpyHceF52
Recommended dataset collection and processing tools: https://github.com/deepghs/waifuc
Possibly the most user-friendly dataset processing UI currently in use： https://github.com/Eugeoter/waifuset
Description
FAQ
Comments (3)
Nami has almost 6k entries on Danbooru, I'm quite sure a significant chunk of that is present in Pony's dataset. Not to mention the character is so prevalent, I'd say it's as easy to prompt as Asuka from NGE.
What purpose does this lora serve that one can't just prompt the character with the exact same tag you've used to train it? Just seems like a waste of time to gather a dataset for and train.
Details
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.