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

Add PEFT format LoRA support to Supported Formats section

Browse Source
This commit is contained in:
Your Name
2026-01-26 12:25:32 +09:00
parent 592efd1432
commit cc1fa7c10f
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6
View File
@@ -177,6 +177,12 @@ ComfyUI\python_embeded\python.exe -m pip install --upgrade diffusers
- `lora_A.weight` / `lora_B.weight`
- `lora.A.weight` / `lora.B.weight`
- These are the standard formats produced by Kohya-ss, Diffusers, and most training scripts.
- ✅ **PEFT Format LoRA** (v2.3.8+):
- Supported weight keys:
- `lora_A.default.weight` / `lora_B.default.weight`
- `lora.up.default.weight` / `lora.down.default.weight`
- Other PEFT format variations with additional tags (e.g., `.default`, `.base`, etc.)
- These formats are produced by Hugging Face PEFT library. PEFT format support was added in v2.3.8 (PR #48).
- ❌ **LoKR (Lycoris)**: Not supported (Keys like `lokr_w1`, `lokr_w2`)
- ❌ **LoHa**: Not supported (Keys like `hada_w1`, `hada_w2`)
- ❌ **IA3**: Not supported