ussoewwin
8e3cc68f37
docs: add note that V1 node does not work properly with ComfyUI Nodes 2.0
2026-05-17 05:27:13 +09:00
ussoewwin
ef0f592818
Revert changelog/version changes (py node changes already in 698f995)
2026-05-17 05:27:13 +09:00
ussoewwin
9677bf1822
docs: v2.4.0 - document V4 to V1 rename (breaking change), update Basic Usage, bump version
2026-05-17 05:27:12 +09:00
ussoewwin
01137b68c9
feat: rename V4 to V1 (rgthree-style UI), add qiv1_stack.png to README
2026-05-17 05:27:11 +09:00
avan06
2737cafee0
feat(qwen_lora): add Nunchaku Qwen Image LoRA Stack V4 with rgthree-style UI ( #49 )
...
- Implement Nunchaku Qwen Image LoRA Stack V4 based on the V3 architecture.
- Redesign the UI to pay homage to rgthree-comfy's Power Lora Loader.
Special thanks to @rgthree for designing such a clean and elegant interface, which served as the inspiration for this version.
2026-05-17 05:27:11 +09:00
ussoewwin
9ed7287226
Docs: restore PEFT format note in Supported Formats
2026-05-17 05:27:10 +09:00
ussoewwin
f856b21b30
Docs: remove Issue #30 guidance troubleshooting section
2026-05-17 05:27:09 +09:00
ussoewwin
494369b094
Docs: note nunchaku_log enables detailed debug logs
2026-05-17 05:27:09 +09:00
ussoewwin
fcc61605f0
Update version to 2.3.9
2026-05-17 05:27:08 +09:00
ussoewwin
6a9fbd8d5c
Update v2.3.9 changelog: Add note about default log muting
2026-05-17 05:27:08 +09:00
ussoewwin
53b621f0a4
Update README for v2.3.9: Add Key Diffusion feature summary
2026-05-17 05:27:07 +09:00
ussoewwin
4c280dbcd4
Add temporary files to .gitignore
2026-05-17 05:27:07 +09:00
ussoewwin
75105eba1c
Key Diffusion implementation: Add key analysis logging to QI LoRA nodes
2026-05-17 05:27:06 +09:00
ussoewwin
f516fc0423
Translate Japanese MD files to English
2026-05-17 05:27:06 +09:00
ussoewwin
84761d1daa
Add PEFT format LoRA support to Supported Formats section
2026-05-17 05:27:05 +09:00
ussoewwin
a7cab10b24
Fix v2.3.8 release notes link to GitHub release
2026-05-17 05:27:05 +09:00
ussoewwin
3a9365be04
Update version to 2.3.8
2026-05-17 05:27:04 +09:00
ussoewwin
83210013f7
Translate pr48_peft_lora_format_fix.md to English
2026-05-17 05:27:04 +09:00
ussoewwin
a9aed6dcc9
Fix image path in v1.63 release notes
2026-05-17 05:27:03 +09:00
ussoewwin
1d95a0b6bd
Add v1.63 CPU Offload Setting text before image
2026-05-17 05:27:03 +09:00
ussoewwin
cb184d1435
Replace detailed changelog (v1.60-v2.2.8) with link to release notes
2026-05-17 05:27:02 +09:00
ussoewwin
0fd175943b
Add Previous Releases (v1.6.0 to v2.2.8) release notes
2026-05-17 05:27:02 +09:00
ussoewwin
3464db3a2d
Update v2.3.8 Issue #44 link to match v2.3.6 format
2026-05-17 05:27:01 +09:00
ussoewwin
daccd4de54
Update Issue #44 link in v2.3.6 changelog
2026-05-17 05:27:01 +09:00
ussoewwin
5477af0a21
Add PR #48 thanks message to Features section
2026-05-17 05:27:00 +09:00
ussoewwin
82291f4ec6
Add PR #48 merge info to v2.3.8 changelog
2026-05-17 05:27:00 +09:00
ussoewwin
dc1c46b880
Simplify v2.3.8 changelog entry
2026-05-17 05:26:59 +09:00
ussoewwin
86f59b6c45
Update README for v2.3.8: Add PEFT format LoRA detection fix
2026-05-17 05:26:59 +09:00
avan
7375cf98cb
feat(lora_qwen): improve format detection and add safety skip logs
...
- Update _detect_lora_format to support LoRA keys with extra tags like .default.weight.
This ensures compatibility with LoRAs using naming conventions such as:
transformer_blocks.0.attn.add_k_proj.lora_A.default.weight
- Add detailed warning logs to identify which LoRA files had modulation layers (img_mod/txt_mod) skipped for Nunchaku safety.
2026-05-17 05:26:58 +09:00
ussoewwin
0810129da6
Update README for v2.6.6: Add mgpu_mm_log AttributeError fix
2026-05-17 05:26:57 +09:00
ussoewwin
958303d246
Update version to 2.3.7
2026-05-17 05:26:57 +09:00
ussoewwin
9256fb44cb
Remove unused temp files
2026-05-17 05:26:56 +09:00
ussoewwin
cf4320a7c5
Remove temp_release_notes_v2.2.7.txt
2026-05-17 05:26:56 +09:00
ussoewwin
3d881134f7
Remove Issue #44 reference from v2.3.7 release notes
2026-05-17 05:26:55 +09:00
ussoewwin
325c15510d
Add developer testing note to v2.3.7 release notes
2026-05-17 05:26:55 +09:00
ussoewwin
c54d1438bb
Add v2.3.7 release notes
2026-05-17 05:26:54 +09:00
ussoewwin
0f612aa580
Add note: V2 switch retained for backward compatibility
2026-05-17 05:26:54 +09:00
ussoewwin
34e3930af0
Add reason for v2.3.7: No noise issues reported after v2.3.6
2026-05-17 05:26:53 +09:00
ussoewwin
94f5bbee97
Update README for v2.3.7: V3 nodes always enable AWQ modulation layer LoRA
2026-05-17 05:26:53 +09:00
ussoewwin
7eaa203aab
V3: Always enable AWQ modulation layer LoRA (no switch needed)
2026-05-17 05:26:52 +09:00
ussoewwin
84db2a8abf
Update README.md: Add note about V1/V3 application in v2.3.6 changelog
2026-05-17 05:26:51 +09:00
ussoewwin
4f5a72ad2a
docs: Remove 'test thoroughly before using in production workflows' from README usage section
2026-05-17 05:26:51 +09:00
ussoewwin
8b8fe90479
chore: Update version to 2.3.6 in pyproject.toml
2026-05-17 05:26:50 +09:00
ussoewwin
ecb063d9d1
docs: Add detailed Z-Image-Turbo module resolution fix to v2.3.6 release notes
...
- Document NextDiT fallback mappings added to _resolve_module_name
- Explain root cause: module naming differences between Qwen Image and NextDiT
- Detail all code changes with line numbers and code blocks
- Document impact: 120 skipped keys -> all 150 keys applied
- Add reference to Issue #44
2026-05-17 05:26:50 +09:00
ussoewwin
3497713d52
Fix: Add Z-Image-Turbo (NextDiT) module resolution fallback paths
...
- Add fallback mappings for NextDiT module naming conventions:
- layers.N.attention.to_qkv -> layers.N.attention.qkv
- layers.N.attention.to_out.0 -> layers.N.attention.out
- layers.N.feed_forward.net.0.proj -> layers.N.feed_forward.w13/w1
- layers.N.feed_forward.net.2 -> layers.N.feed_forward.w2
- Change module resolution failure log level from debug to warning
- Fixes issue where 120 out of 150 LoRA keys were skipped for Z-Image-Turbo models
- Issue was exposed by qwen v2 AWQ fix's stricter module None checks
2026-05-17 05:26:49 +09:00
ussoewwin
dd5969165c
Fix V2 node isolation and zimageturbo_v4 compatibility: Use V2-specific wrapper, add compose_loras_v2_v2 function, fix apply_awq_mod handling, add comfy import
2026-05-17 05:26:49 +09:00
ussoewwin
ed1ec39d55
Add Issue #44 link to v2.3.6 changelog
2026-05-17 05:26:48 +09:00
ussoewwin
8bceac985c
Remove unnecessary test warning from v2.3.6 changelog
2026-05-17 05:26:48 +09:00
ussoewwin
9a19a6e80d
Remove LATEST UPDATE v2.3.6 section from README
2026-05-17 05:26:47 +09:00
ussoewwin
169d0960a8
Fix README: Move v2.3.6 impact and warning to Changelog section
2026-05-17 05:26:47 +09:00
ussoewwin