lllyasviel / lllyasviel/ControlNet
different setup of input_hint_block compared to paper?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
Hi, i noticed that the implementation of the tiny work converting control images into feature space is different from the structure menioned in the paper: "In particular, we use a tiny network E(·) of four convolution layers with 4 × 4 kernels and 2 × 2 strides (activated by ReLU, using 16, 32, 64, 128, channels respectively". The corresponding implementation should be here right(correct me if i am wrong): https://github.com/lllyasviel/ControlNet/blob/ed85cd1e25a5ed592f7d8178495b4483de0331bf/cldm/cldm.py#L147-L163
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with cldm/cldm.py lines 147-163 and compare the input_hint_block implementation with the quoted paper description. Determine whether the code or paper is inconsistent, then document the confirmed resolution or required correction; the issue is done when the discrepancy is explained and, if needed, addressed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100