These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with canny conditioning. You can find some example images in the following.

prompt: a couple watching a romantic sunset, 4k photo

prompt: ultrarealistic shot of a furry blue bird

prompt: a woman, close up, detailed, beautiful, street photography, photorealistic, detailed, Kodak ektar 100, natural, candid shot

prompt: Cinematic, neoclassical table in the living room, cinematic, contour, lighting, highly detailed, winter, golden hour

prompt: a tornado hitting grass field, 1980's film grain. overcast, muted colors.

Make sure to first install the libraries:

And then we're ready to go:

To more details, check out the official documentation of StableDiffusionXLControlNetPipeline.

Our training script was built on top of the official training script that we provide here.

This checkpoint was first trained for 20,000 steps on laion 6a resized to a max minimum dimension of 384. It was then further trained for 20,000 steps on laion 6a resized to a max minimum dimension of 1024 and then filtered to contain only minimum 1024 images. We found the further high resolution finetuning was necessary for image quality.

one 8xA100 machine

Data parallel with a single gpu batch size of 8 for a total batch size of 64.

Constant learning rate of 1e-4 scaled by batch size for total learning rate of 64e-4

fp16