From 2e57726d39d70818d7cb06202be428769aaea7ae Mon Sep 17 00:00:00 2001 From: ussoewwin <136552381+ussoewwin@users.noreply.github.com> Date: Thu, 1 Jan 2026 15:34:14 +0900 Subject: [PATCH] Add testing limitation explanation for context_refiner and noise_refiner layers --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index be532d8..39002f7 100644 --- a/README.md +++ b/README.md @@ -223,7 +223,9 @@ ComfyUI\python_embeded\python.exe -m pip install --upgrade diffusers ### context_refiner and noise_refiner Layer Support - **Status**: ❌ **Not Currently Supported** - **Issue**: LoRA keys for `context_refiner` and `noise_refiner` layers are **not currently supported**. These are specialized layers used in Z-Image-Turbo models for refiner functionality. -- **Details**: We have not tested LoRAs that contain `context_refiner` and `noise_refiner` layers with actual models. Without testing, we cannot determine if correct key mappings are possible for these layers. The current key mapping system does not include mappings for these layers, and they **will not work** at this time. +- **Details**: + - ⚠️ **Testing Limitation**: We have not tested LoRAs that contain `context_refiner` and `noise_refiner` layers with actual models. The reason we cannot test them is that **we do not know which LoRAs are in this format**. If we can identify specific LoRAs that contain these layers, we can proceed with testing. + - Without testing, we cannot determine if correct key mappings are possible for these layers. The current key mapping system does not include mappings for these layers, and they **will not work** at this time. - **Conclusion**: Support for `context_refiner` and `noise_refiner` layers is not implemented because we have not been able to test LoRAs containing these layers. Even if we test them, it is unknown whether correct key mappings can be determined. Please use LoRAs that target the standard transformer layers only. - **Related Issues**: - [#41](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/issues/41) - 无法加载context_refiner和noise_refiner层的参数