lllyasviel / lllyasviel/ControlNet

how to use DDIM inversion during inference?

Open
#359 6 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

Hi, thanks for releasing this amazing project. From my best understanding, current demo code does not use DDIM inversion during inference as the x_T variable is None in the following line? If so, could you please provide some suggestions on how to implement DDIM inversion to better use some input images as prior? Thanks!

https://github.com/lllyasviel/ControlNet/blob/3d25e488c7e6c2efdfe94f1673f2de261c662902/cldm/ddim_hacked.py#L132-L133

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 cldm/ddim_hacked.py at lines 132-133 and trace how the demo handles x_T during inference. Compare that path with the requested DDIM inversion workflow for using input images as a prior. Done means the inference behavior or implementation guidance clearly addresses whether and how inversion is supported.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.