LORA Captioning Help

doing alot of captioning for LORAs. Are there any captioners out there that work with pony stuff? Ive been used E621 tagger for a base but it still requires a lot of manual work. I work with illustrious and/or noob based models.
I was thinking about doing the LLM route but I have no idea where to begin with that.

Tagging a LoRA’s dataset effectively depends on the checkpoint type and the dataset(s) they were trained on.

IIRC, Illustrious was trained only on danbooru and NoobAI was trained on both danbooru and e621.

Given that e621 has far more pony-related content, it’s probably a safer bet to use NoobAI for your purposes.

A good e621 tag captioner (like the one I use: RedRocket/JointTaggerProject) can get a lot of the ‘pony-related’ tags.

In terms of decreasing the amount of work you need to put in, I find that when it comes to LoRAs, small good-quality datasets can give you good results. (For character LoRAs: at least 10, but preferably around 25 pics. For concept and style, I’m not sure yet)

(sorry, if this is confusing or anything, i’m a bit tired and felt the need to write down some of my knowledge on this subject once i saw an opportunity to do so)

@Bendy and Boney
Ya thats pretty much what im using right now. Really I’m just looking to automate the process enough so that I’m not missing important concepts per image. For a style Lora I’ve found that’s about 40-70 images. To get enough variation. Its stuff like “ears down” is what gets me because its a small thing to notice and easily becomes a constant if you don’t always caption it.