This LORA model is trained using the technique described in https://www.crosslabs.org//blog/diffusion-with-offset-noise
Use it to produce beautiful high-key images that SD just wasn't capable of creating until now.
Sample images were generated using Illuminati Diffusion v1.0
The LORA was trained using Kohya's LORA Dreambooth script, on SD2.1-768 and SD1.5 with a dataset of 53 high-key, high-quality photographs.
Model weights can be used to affect the 'blown-out' lighting.
SD 1.5 version coming soon.
Description
FAQ
Comments (8)
Haha, I'm sorry...Spider-House!
Nah mate, that's just a common House Spider :)
@theovercomer8 haha, you win this round. I like that.
They look great I only have 2 2.1 models, hoping for a 1.5 like the contrast one, this would pair really well with so many models.
It’s giving me grief. Not coming out quite right yet. Soon.
Please create a Lora for SD 1.5. Thx!
Working on it!
@theovercomer8 thanks for the update!! 👍, I'll try to post some pics