A Stable Diffusion LoRA profile.
More available on my site: https://ko-fi.com/diffusionbox
Place it in "stable-diffusion-webui\extensions\sd-webui-additional-networks\models\lora" folder in Automatic1111 WebUI root folder.
Made using kohya-ss so make sure to have that extension installed!
In txt2img, under "Additional Networks", select "Enable" and under Model 1 select "" and assign a weight between 0.3-0.7 (feel free to experiment!). In the promt text window use "" within your promt to generate images.
Embed has been trained on Stable Diffusion 1.5 model.
I Recommend the model https://civarchive.com/models/4922/grapelikedreamfruit - Gives amazing realistic renders.
Your output will vary depending upon your prompt, negative prompt, model, VAE, and Hypernetworks used.
More available on my site: https://ko-fi.com/diffusionbox
Description
FAQ
Comments (1)
It was working well when I first started using it. I went back to recreate a previous image to use it as a base for another image and the result is horrible. The generated image isn't even close to the original image and has, for lack of a better term, random cracks in the body. All the models are exactly the same as are the parameters. I think Automatic1111 updated and screwed everything up.