How is the t2i text processed?
Can the Dev put this question to rest? How is the text processed now for t2i? Is Automatic1111 still in use? Stepping and blending don't seem to work after the Model change or at least not predictably, but weights do work predictably. I can see where the properties are stripped, an DSL evaluation runs, and the word filter, but what is processing the weights now? A frontend or are the handled by the CLiP and T5?
Would be great to have an infobox in the sidebar that showed these generator details all the time. Current platform, version, and information about key settings that are both hard set and/or adjustable via prompt. Click through it to get a one-page rundown of current engine and known tendencies and prompt methods. Maybe just a pinned "The Engine" thread with admin/dev updates locked to the top?