nodes/ussoewwin-ComfyUI-QwenImageLoraLoader
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add Chinese acknowledgment to v2.2.7

Browse Source
This commit is contained in:
Your Name
2026-01-08 00:15:12 +09:00
parent 4c8f489b67
commit b787af2fad
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1
View File
@@ -244,6 +244,7 @@ ComfyUI\python_embeded\python.exe -m pip install --upgrade diffusers
### v2.2.7 (latest)
- **Performance**: LoRA loading speed improvement - Implemented optimization by eliminating duplicate file reads. The first LoRA file loaded for debug logging is now cached and reused in actual processing, eliminating duplicate file I/O and deserialization operations
- **Technical Details**: See [v2.2.7 Release Notes](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/releases/tag/2.2.7) for complete explanation
- **Acknowledgments**: 本次改进参考了zhihu.com上Jimmy先生发表的文章《【closerAI ComfyUI】nunchakuV1.1支持z-image+支持zimage-LORA的修复方案，短板一次性补全，nunchaku zimage全面高速生图解决方案！》。在此谨向Jimmy先生致以诚挚谢意。
### v2.2.6
- **Fixed**: Resolved [Issue #43](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/issues/43) – Fixed `TypeError: QwenTimestepProjEmbeddings.forward() takes 3 positional arguments but 4 were given` error by forcing `guidance=None` after converting to `additional_t_cond` to prevent ComfyUI-nunchaku's buggy code path from executing