Train ControlNet - custom resolution? about editanything HOT 4 OPEN

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.

from editanything.

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.

from editanything.

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

from editanything.

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

from editanything.