Only for SDXL
Give me your feedback. I'm testing different parameters. And I'm not sure of the final result.
Do you too feel like the pictures have become too perfect?
Let's go a little wild and do some mirror distortion. Just put "specular distortion" in the prompt and "man" or "woman".
Description
FAQ
Comments (10)
Hmmm... Looks very interesting ! There are many people interested by glitch effects and it could be very handy in a img2img mode. I have to try :)
May I know how you did train it ?
I'm tweaking the training parameters now, but it definitely doesn't work the same way as in 2.1
Loving it....giving exactly the look I try to prompt for...if this is your thing then I highly recommend grabbing this Lora...
Thank you! I'm glad to hear that.
These are cool but both of your specular distortion LoRAs have the same name and trigger word when you try and use them which I think might cause problems.
Thanks for the feedback! They are trained on the same dataset with different parameters. I want to understand how Lora changes. Which variant do you like better?
Can you name your LoRA so they say the effect and not just your name? Impossible to figure these out without renaming them all and uploading images..
Fantastic
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.