lllyasviel / lllyasviel/ControlNet

Custom resolution dataset, ex 1024 x 768?

Open
#334 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
34.1k
Forks
3k
PR merge metrics
No merged PRs in 30d

Description

Is it possible to train with a custom resolution dataset, ex 1024 x 768?
I tried something like this, 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

thanks!

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with train_controlnet.py and inspect how the --resolution argument is parsed and applied to the fusing/fill50k dataset and validation images. Determine whether non-square dimensions such as 1024x768 are supported throughout training, and consider the work complete when that command accepts the custom resolution and training proceeds successfully.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.