lllyasviel / lllyasviel/ControlNet

How to increase effect of text prompt?

Open
#117 3 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 there anyway we can increase the relative weight of the SD text conditioning? The reason for this is sometimes the additional condition is too strong and what we are trying to bring out using text is unfulfilled.

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

No files, tests, or entry points are named. Start by locating how text conditioning and the additional condition are combined, then determine whether the requested relative weighting has an existing control or requires a design decision; done would mean an agreed, reproducible way to increase text-conditioning influence.

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.