The new version, trained for SDXL is up.
For this version, I recommend to use weight between 0.8 and 1.5.
It also seems to work with Pony if you use a very high weight, like 3 or 4.
A style LoRA to reproduce classical sketch and drawing study
It's a merge of multiples LoRA trained with the same dataset on SD 1.5 but with different training parameters.
You can use monochrome in your prompt if you dont want colors.
Use a weight of 1.
The training data is also available to download, all the images are in the public domain.
Description
FAQ
Comments (3)
I would LOVE a SDXL version of this, looks stunning! If you don't have the means, I can take the dataset and train one for you, or I'll just give you a lot of Buzz so you can do it yourself. Either way, great job!! <3
I added the training data, feel free to use them however you want, I'm not really interested in SDXL for now. If you make a lora with it, dont hesitate to tell me, I would love to see the result.
@Oofas Nice, thanks! I'll share it here if I have time this week!