Arcane Style LoRA XL
Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
First LoRA I make for SDXL0.9, but works perfectly on XL1.0.
This should be used with Anime Art Diffusion XL (that's neutral enough) at around 0.65-0.9 weight. Trigger is arcane.
Allow me to remind this is not a character LoRA (I didn't tag characters in the dataset). Still, as you can see, it can get pretty close to the original characters with accurate prompting. Comfy workflows are embedded in the images.
Please enjoy.
Description
FAQ
Comments (9)
wow XL loras also XL sized lol,
I'll give it a try
yeah it's all pretty heavy unfortunately.
Very good lora, are you training it with kohya_ss?
yes
is it compatible with SDXL1.0?
yep, tested on Anime Art Diffusion XL1.0
That looks very convincing, great work.
Do you have any resource to share to help with training models/loras by any chance?
Why are so many of your model names different in the generation data ? And then it does not give the same results.... artDiffusionXL09-alpha_half_00001_ where is that? I download what that supposedly is, bad result with generation data. a lot of the time.
Thank you, that's what I needed.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.