Clarification of some details from article

Nobody has claimed this yet.

Hello. I am trying to train and infer a model according to your article. However, some things are not clear from article:
1) "In the training process, we randomly replace 50% text prompts ct with empty strings". Ok, you replace 50 % of the input text to ControlNet with empty strings, but do you so also for base model (for same elements in the batch)?
2) In section "Classifier-free guidance resolution weighting" you state that you are reweighting ControlNet residuals by wi = (64 / {resolution of residual}). Am I right, that lowest resolution residual (middle block) gets a multiplier of 8? In my case it completely breaks the generation (diffusers case of using np.linspace(-1, 0, 13) works slightly better).

Start with the article's training-process paragraph and the section titled "Classifier-free guidance resolution weighting." Verify how the 50% empty-prompt replacement applies to the base model and ControlNet, and whether the stated residual weighting matches the described resolutions. Done means the article clearly answers both questions.

Written by the indexing model from the issue text.