LoRA of Sadie Sink
Welcome to my corner!
I'm creating Dreambooths, LyCORIS, and LORAs. (guide: https://civarchive.com/articles/7/dreambooth-lycoris-lora-guide). Here is my base model Serenity: https://civarchive.com/models/110426
I upload 2-3 times a week, however, I write down suggestions all the time. If you want to see someone made into a model just leave a comment :)
Suggestions left on my donation page ( https://www.buymeacoffee.com/malcolmrey ) are taken with the highest priority and you will be able to enjoy them way before they get released here. (I accept also custom requests)
The reason is that I can't keep up with uploading and the models are being made pretty much all the time :-)
As mentioned, via the donation page I accept custom requests, so feel free to engage with me there, I will answer all your questions :)
Description
FAQ
Comments (4)
1. I am still learning (for example, there were no regularization images)
2. You do not need 9 hours to train a decent LoRA
3. Seems like dreambooth won't be required so for SDXL it may just be lora (I will explore LyCORIS and check if those are better)
4. I am still tweaking the parameters so next LoRAs might be smaller (or larger?), etc and so on :-)
5. The training info is in the metadata of the LoRA
If you are curious about anything - just ask and I shall provide :-)
Is it me or does the face not look...clear...but noisy, or "wavy"
Looking great from the previews. Your 1.5 version was good but this looks better. Off to try it now.
Been testing the model in ComfyUI and connecting the Lora to the refiner definitely improves the likeness, but it also spits out tons of errors, like
ERROR diffusion_model.output_blocks.5.1.proj_out.weight shape '[1536, 1536]' is invalid for input of size 409600
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.