Train ControlNet - custom resolution?

[alelordelo]

Hi, thanks for sharing this amazing repo! I was thinking of doing something similar, super impressive you related this just a couple days after SAM! 🚀

My dataset is 1024 x 768. Is it possible to train with a a custom?

Thanks!

[gasvn]

Currently, we are using SD 2.1 as the base model, so we are using 512x512 for training. Do you mean to train a model with resolution 1024 x 768? I think that's achievable.

[alelordelo]

Yup, train the model with 1024 x 768, instead of 512x512. Do you think that is possible?

I tried something like this in ControlNet original repo, but didn't work:

accelerate launch train_controlnet.py --pretrained_model_name_or_path=$MODEL_DIR --output_dir=$OUTPUT_DIR --dataset_name=fusing/fill50k *--resolution=1024x768 * --learning_rate=1e-5 --validation_image "./conditioning_image_1.png" "./conditioning_image_2.png" --validation_prompt "red circle with blue background" "cyan circle with brown floral background" --train_batch_size=4

[gasvn]

It should be able to work with 1024x768. Maybe there are some settings that make this resolution not working. I will check it and let you know.

[alelordelo]

Thanks @gasvn , if we can have custom aspect ratio that would open a lot of possibilities!