lllyasviel / lllyasviel/ControlNet

Inpainting Controlnet

Open
#611 1 comment 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

I've trained controlnet for sd2 inpainting model by concatenating control image, masked image and the mask itself.
What do I need to change in inference code to use this model?

size mismatch for input_blocks.0.0.weight: copying a param with shape torch.Size([320, 9, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 4, 3, 3])

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 by inspecting the inference code and the checkpoint error for input_blocks.0.0.weight, comparing the trained 9-channel input with the current model's 4-channel input. Done means the trained inpainting ControlNet loads successfully and its inference path accepts the concatenated control image, masked image, and mask.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.