From 0d3bfdaaae5c0b8106dabb9b3bbfae9b932eb839 Mon Sep 17 00:00:00 2001 From: digital-garbage <133010426+digital-garbage@users.noreply.github.com> Date: Thu, 15 Oct 2026 16:05:18 +0300 Subject: [PATCH] docs: state what the prompt enhancer did on a v5 rental Co-Authored-By: Claude Sonnet 5.5 --- modules/conditioning/prompt_enhancer/__init__.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/conditioning/prompt_enhancer/__init__.py b/modules/conditioning/prompt_enhancer/__init__.py index 2d517a49..7bf428ce 100644 --- a/modules/conditioning/prompt_enhancer/__init__.py +++ b/modules/conditioning/prompt_enhancer/__init__.py @@ -12,7 +12,7 @@ project is never rewritten as one blob and re-split. Whether a given text encoder writes sensible prose is an open question per model (H3's conditioning checkpoint has no trained decoder head; Gemma3/Qwen3 do). v4's -result: confirmed working on Gemma3-12B. Unvalidated on a rental in v5. +result: confirmed working on Gemma3-12B. v5 on a rental: H3's own encoder writes no prose (the run keeps your prompt and says why); a Gemma3/Qwen3 encoder is not yet tried in v5. """ from .nodes import RUNS, FunPackEnhancePrompt