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

docs: add v2.4.0 to Changelog, update Latest release

Browse Source
This commit is contained in:
Your Name
2026-02-07 21:48:51 +09:00
parent fc880e42a4
commit fdc9f8bd8f
1 changed files with 6 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6 -8
View File
@@ -9,13 +9,6 @@ A ComfyUI custom node for loading and applying LoRA (Low-Rank Adaptation) to Nun
> Latest release: [v2.4.0 on GitHub Releases](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/releases/tag/v2.4.0)
>
## v2.4.0 - Nunchaku Qwen Image LoRA Stack V1 (rgthree-style UI)
Added **Nunchaku Qwen Image LoRA Stack V1** with a clean, minimalist interface inspired by Power Lora Loader (rgthree-comfy). Toggle, LoRA name, and strength per row.
- **PR**: [PR #49 - feat(qwen_lora): add Nunchaku Qwen Image LoRA Stack V4 with rgthree-style UI](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/pull/49)
- **Note**: Does not work properly with ComfyUI Nodes 2.0. Use the standard (LiteGraph) canvas.
## Source
This LoRA loader was extracted and modified from GavChap's fork:
@@ -216,6 +209,11 @@ ComfyUI\python_embeded\python.exe -m pip install --upgrade diffusers
## Changelog
### v2.4.0 (latest)
- **Added**: Nunchaku Qwen Image LoRA Stack V1 with rgthree-style UI - Clean, minimalist interface inspired by Power Lora Loader (rgthree-comfy). Toggle, LoRA name, and strength per row.
- **Merged**: [PR #49](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/pull/49) - feat(qwen_lora): add Nunchaku Qwen Image LoRA Stack V4 with rgthree-style UI (proposed by [avan06](https://github.com/avan06))
- **Note**: Does not work properly with ComfyUI Nodes 2.0. Use the standard (LiteGraph) canvas.
### v2.3.9
- **Added**: Key Diffusion (key analysis logging) - Added detailed key analysis logging to all Qwen Image LoRA nodes (Loader, Legacy Stack, V2 Stack, V3 Stack). When enabled via `nunchaku_log=1` environment variable, displays key mapping information (`Key: <original key> -> Mapped to: <mapped target> (Group: <group>)`) for debugging and verification purposes. This feature matches the functionality already available in Z-Image Turbo LoRA nodes. **Note**: Logs are muted by default and only displayed when `nunchaku_log=1` is set.
- **Technical Details**: See [v2.3.9 Release Notes](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/releases/tag/v2.3.9) for complete explanation
@@ -246,7 +244,7 @@ ComfyUI\python_embeded\python.exe -m pip install --upgrade diffusers
- ⚠️ **Important**: This node is **only compatible with the unofficial Nunchaku Z-Image-Turbo DiT Loader** provided by [ComfyUI-nunchaku-unofficial-loader](https://github.com/ussoewwin/ComfyUI-nunchaku-unofficial-loader)
- ⚠️ **Not Compatible**: This node is **not compatible** with the official Nunchaku Z-Image-Turbo DiT Loader from ComfyUI-Nunchaku
### v2.3.1 (latest)
### v2.3.1
- **Fixed**: Resolved [Issue #46](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/issues/46) – Fixed `NameError: name 'ZIMAGETURBO_V4_NAMES' is not defined` error that occurred when `zimageturbo_v4` module import failed. Initialized `ZIMAGETURBO_V4_NAMES`, `ZIMAGETURBO_V4_NODES`, `QWEN_V3_NAMES`, and `QWEN_V3_NODES` before the import block to prevent NameError on import failure.
- **Fixed**: Resolved [Issue #47](https://github.com/ussoewwin/ComfyUI-QwenImageLoraLoader/issues/47) – Added missing v4 files to Git repository (`nodes/lora/zimageturbo_v4.py`, `js/zimageturbo_lora_dynamic_v4.js`). These files were created but not committed to Git, causing `ModuleNotFoundError` in previous releases. The files are now included in the repository.