A combined styler / detailer Lora for SDXL trained on 1000 hand-selected Flux gens, all recaptioned with both Florence-2 Large "more detailed mode" natural language descriptions and also Booru tags from wd-eva02-large-tagger-v3. No particular trigger word. Recommended strength is around 0.7ish, but feel free to adjust as you see fit.
Read the "About This Version" section of the page for more detailed info on any given specific version of the Lora.
For a Pony "style" lora trained on the same dataset as this lora, check out Best Of Flux instead.
Note that you CAN combine this Lora with my Zoot Detailer XL Lora if you wish, as both Loras were trained on completely different datasets.
Description
Retrained with a larger dataset (1000 images on the dot, now). Same captioning approach used as before. All showcase images were generated with Base SDXL + this Lora.
FAQ
Comments (2)
I recently used your LoRA, and I am absolutely thrilled with the results. The images generated are simply stunning, with a captivating atmosphere that draws you in. Every detail is vibrant and meticulously crafted, which significantly enhances the quality of the output. This LoRA model delivers outstanding results and far exceeded my expectations. I highly recommend it to anyone.👍
Thanks for the kind words, I'm glad you like it!