From 4f2003a897bc53217eeec113f60b6d8a30f40d13 Mon Sep 17 00:00:00 2001 From: Your Name Date: Thu, 8 Jan 2026 03:45:44 +0900 Subject: [PATCH] Update LoKR section with development history and add Issue #44 link --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 17cea50..6be5ece 100644 --- a/README.md +++ b/README.md @@ -203,6 +203,7 @@ ComfyUI\python_embeded\python.exe -m pip install --upgrade diffusers - **Status**: ❌ **Not Supported** - **Issue**: LoRAs in LoKR format (created by Lycoris) are **not supported**. - **Important Note**: This limitation applies specifically to **Nunchaku quantization models**. LoKR format LoRAs may work with standard (non-quantized) Qwen Image models, but this node is designed for Nunchaku models only. + - ⚠️ **Development History**: **We have spent considerable time analyzing the internal structure of LoKR format and performing extensive mapping tests. Despite these efforts, we have not been able to find a successful way to apply LoKR weights to Nunchaku quantization models.** The experimental conversion code has been tested but ultimately disabled due to incompatibility issues. - LoKR weights are automatically skipped when detected (experimental conversion code is disabled). - Converting to Standard LoRA using SVD approximation (via external tools or scripts) has also been tested and **found to result in noise/artifacts** when applied to Nunchaku quantization models. - **Conclusion**: At this time, we have not found a way to successfully apply LoKR weights to Nunchaku models. Please use Standard LoRA formats. @@ -219,6 +220,7 @@ ComfyUI\python_embeded\python.exe -m pip install --upgrade diffusers - ❌ **IA3**: Not supported - **Related Issues**: - [Issue #29](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/issues/29) - LyCORIS / LoKr Qwen Image LoRA not recognized by ComfyUI + - [Issue #44](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/issues/44) - [MISS] Module found but unsupported/missing proj_down/proj_up (freeze issue fixed in v2.2.8) ### context_refiner and noise_refiner Layer Support - **Status**: ❌ **Not Currently Supported**