lllyasviel / lllyasviel/ControlNet
Pre-trained encoder as input_hint_block
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 34.1k
- Forks
- 3k
- PR merge metrics
- No merged PRs in 30d
Description
I was wondering if any experiments using pre-trained encoder as input_hint_block, for example directly use vae auto-encoder, rather than train this part from scratch? It would be beneficial for limited data?
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 by locating the input_hint_block entry point and reviewing how its encoder is currently trained. Compare that path with using a pre-trained VAE auto-encoder, and define experiments on limited data that measure whether the pre-trained approach is beneficial.
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