A general purpose detailer, trained on images captioned both with Florence 2 Large rich captions and also WD-EVA02-Large-Tagger-V3 Booru tags. No particular trigger word. Recommended strength is around 0.6 to 0.8 or so, but feel free to adjust the strength as you see fit for any particular image.Note that you CAN combine this Lora with my <a rel="ugc" href="https://civarchive.com/models/633453">Zoot Fluxxer XL Lora</a> if you wish, as both Loras were trained on completely different datasets.

Zoot Detailer XL

Overhauled and completely recaptioned the dataset. This is definitely the best version of this Lora, by like a lot. All primary / initial sample images were made with just this Lora at between 0.7 - 0.75 and my "Zoot's Tweaked Base SDXL For Finetuning Or Lora Training" checkpoint.

Files with SHA256: ff6102145d687adc0ecbe55343c200958b7e981b1948dfbc6a95c6f0fb1e9f0f