 Hawk Lee
|
a9126ab02f
|
fix: total structural recovery to fix canvas socket shifts
|
2026-02-04 15:41:01 +08:00 |
|
|
Hawk Lee
|
5345a2324d
|
fix: total structural restoration to fix canvas layout
|
2026-02-04 15:38:29 +08:00 |
|
|
Hawk Lee
|
0d65fea080
|
fix: total input order restoration to fix canvas sockets
|
2026-02-04 15:36:23 +08:00 |
|
|
Hawk Lee
|
1f9673781b
|
fix: complete metadata alignment for Qwen3-TTS nodes
|
2026-02-04 15:34:59 +08:00 |
|
|
Hawk Lee
|
9d6816ebc4
|
fix: restore node inputs to fix canvas corruption
|
2026-02-04 15:34:01 +08:00 |
|
|
Hawk Lee
|
5b43ddd45f
|
refactor: simplify Qwen3-TTS UI with Model Router and bundle support
|
2026-02-04 15:22:22 +08:00 |
|
|
Hawk Lee
|
c4aefcf541
|
feat: add UI and console warnings for Qwen3-TTS Base model instruction limitations
|
2026-02-04 14:52:16 +08:00 |
|
|
Hawk Lee
|
fc3720c723
|
docs: add Qwen3-TTS model-capability mapping table
|
2026-02-04 14:30:30 +08:00 |
|
|
Hawk Lee
|
94342c97ed
|
docs: add dialect compatibility tips and update README
|
2026-02-04 14:27:54 +08:00 |
|
|
Hawk Lee
|
3d2d014e23
|
docs: add 0.6B download info and ModelScope support for Qwen3-TTS
|
2026-02-04 14:05:19 +08:00 |
|
|
Hawk Lee
|
178883eb96
|
feat: add dialect selection support for Qwen3-TTS and dialogue nodes
|
2026-02-04 14:02:11 +08:00 |
|
|
Hawk Lee
|
4dfa7a3432
|
fix: resolve batch_mode signature mismatch and improve max_batch_char robustness
|
2026-02-04 11:46:16 +08:00 |
|
|
Hawk Lee
|
08bf36ab4f
|
docs: synchronize new parameters and emotion safeguards to README
|
2026-02-04 11:00:19 +08:00 |
|
|
Hawk Lee
|
eb8527e934
|
fix: disable emotion tags for VibeVoice to prevent them being read aloud
|
2026-02-04 10:58:21 +08:00 |
|
|
Hawk Lee
|
8e0ca9abda
|
feat: implement emotion compatibility check for non-expressive CosyVoice models
|
2026-02-04 10:57:07 +08:00 |
|
|
Hawk Lee
|
36514bd27d
|
feat: add verbose console logging for text and instructions in dialogue nodes
|
2026-02-04 10:54:46 +08:00 |
|
|
Hawk Lee
|
cda70248c0
|
feat: increase max_batch_char to 32768 for Qwen3-TTS long-context
|
2026-02-04 10:53:14 +08:00 |
|
|
Hawk Lee
|
0e49a1d850
|
feat: added specialized micro-expression controls for Qwen3-TTS Specialist node
|
2026-02-04 10:49:40 +08:00 |
|
|
Hawk Lee
|
481fa301c5
|
feat: expose max_batch_char to general Dialogue node and unify Qwen batching
|
2026-02-04 10:42:39 +08:00 |
|
|
Hawk Lee
|
4381966fe8
|
feat: implement batch maximization for Qwen3-TTS Dialogue node
|
2026-02-04 10:40:45 +08:00 |
|
|
Hawk Lee
|
6a8afb9b0d
|
feat: unified emotion dropdowns for Qwen and general Dialogue nodes
|
2026-02-04 10:04:05 +08:00 |
|
|
Hawk Lee
|
3340d63766
|
feat: add emotion and expression dropdowns for Qwen3-TTS nodes
|
2026-02-04 10:02:10 +08:00 |
|
|
Hawk Lee
|
9288adecdd
|
docs: add Qwen3-TTS instruction (emotion/style) control guide
|
2026-02-04 09:59:33 +08:00 |
|
|
Hawk Lee
|
51bd60c41f
|
ui: rename x_vector_only to zero_shot_mode and enforce auto-fallback
|
2026-02-04 09:56:26 +08:00 |
|
|
Hawk Lee
|
d27d6b6e5e
|
feat: add reference text support for each speaker in Qwen Dialogue node
|
2026-02-04 09:53:13 +08:00 |
|
|
Hawk Lee
|
7f454d95f9
|
fix: auto-switch to zero-shot when ref_text is missing in VoiceClone mode
|
2026-02-04 09:51:33 +08:00 |
|
|
Hawk Lee
|
5d1f3fa371
|
fix: restore missing FUNCTION attribute in Qwen Specialist Dialogue node
|
2026-02-04 09:49:40 +08:00 |
|
|
Hawk Lee
|
76944fd165
|
fix: resolve qwen models from local folder_paths and log discovery
|
2026-02-04 09:48:29 +08:00 |
|
|
Hawk Lee
|
64217b1518
|
fix: resolve transformers 5.0.0 conflict and qwen-tts decorator bug
|
2026-02-04 09:42:52 +08:00 |
|
|
Hawk Lee
|
b2acebdc4a
|
feat: support high-quality fallback seeds in Qwen Specialist Dialogue node
|
2026-02-04 09:29:56 +08:00 |
|
|
Hawk Lee
|
a76e46854e
|
ui: implement automatic multi-line wrapping for static labels
|
2026-02-04 09:26:34 +08:00 |
|
|
Hawk Lee
|
8a60897c63
|
ui: implement elegant static labels for Qwen-TTS speaker guide using is_label
|
2026-02-04 09:25:03 +08:00 |
|
|
Hawk Lee
|
34fcb61a11
|
feat: support cfg_scale, temperature, top_k, top_p for Qwen3-TTS in all nodes
|
2026-02-04 09:22:33 +08:00 |
|
|
Hawk Lee
|
25f1bc7a73
|
ui: improved Qwen-TTS speaker selection with official list and UI notes
|
2026-02-04 09:20:00 +08:00 |
|
|
Hawk Lee
|
032f48aaa3
|
docs: add official speaker list to code comments
|
2026-02-04 09:14:12 +08:00 |
|
|
Hawk Lee
|
0ed49dbb1b
|
docs: correct Qwen3-TTS preset speaker names
|
2026-02-04 09:13:52 +08:00 |
|
|
Hawk Lee
|
52d6e63042
|
feat: implement specialized AIIA_Qwen_Dialogue_TTS node for deep Qwen3 integration
|
2026-02-04 09:11:47 +08:00 |
|
|
Hawk Lee
|
98f615c603
|
feat: support multi-model routing for Qwen3-TTS in podcast nodes & clarify terminology
|
2026-02-04 09:07:33 +08:00 |
|
|
Hawk Lee
|
1d43237813
|
docs: complete manual download guide for all Qwen3-TTS model variants
|
2026-02-04 08:59:48 +08:00 |
|
|
Hawk Lee
|
c8949e3b10
|
docs: add manual download guide for Qwen3-TTS
|
2026-02-04 08:57:28 +08:00 |
|
|
Hawk Lee
|
167edf8d20
|
feat: integrate Qwen3-TTS support into podcast nodes (v1.11.0)
|
2026-02-04 08:54:08 +08:00 |
|
|
Hawk Lee
|
9d069fc0ea
|
v1.10.20: Enhanced subtitle calibration with Turn Protection (0.5s threshold)
|
2026-02-04 00:22:29 +08:00 |
|
|
Hawk Lee
|
f264f140b7
|
v1.10.19: Fix subtitle timing with sequential priority logic
|
2026-02-03 23:17:32 +08:00 |
|
|
Hawk Lee
|
633ed75661
|
v1.10.17: Implement Speaker ID Mapping for subtitle calibration
|
2026-02-03 01:29:00 +08:00 |
|
|
Hawk Lee
|
9224e6c9f6
|
v1.10.16: Implement greedy speaker turn collection for subtitles
|
2026-02-02 22:44:28 +08:00 |
|
|
Hawk Lee
|
d84ea55914
|
v1.10.15: Fix subtitle timing truncation bug
|
2026-02-02 20:24:43 +08:00 |
|
|
Hawk Lee
|
72391958b1
|
v1.10.14: Fix AttributeError 'should_stop' and improve cross-version compatibility
|
2026-02-02 14:25:07 +08:00 |
|
|
Hawk Lee
|
de9eefcd64
|
v1.10.13: Fix Ditto Sampler interruption issue
|
2026-02-02 14:20:52 +08:00 |
|
|
Hawk Lee
|
b5c2c80e0c
|
v1.10.12: Add Text Debug Splicer node
|
2026-02-02 13:54:19 +08:00 |
|
|
Hawk Lee
|
81d7b23776
|
fix(subtitle): disable default bold style to make markdown emphasis visible (v1.10.11)
|
2026-02-01 20:16:26 +08:00 |
|