nodes/havvk-ComfyUI_AIIA
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,055 Commits 1 Branch 0 Tags
9f046e37d44ae6f502f98b51c1237bf2b4e27fbd
Commit Graph
42 Commits
Author SHA1 Message Date
Hawk Lee 579da6b3e4 fix: 启用所有节点模块导入 2026-02-19 12:08:47 +08:00
Hawk Lee 1cb441eaa9 fix: 修复 IndexTTS 导入导致 NeMo 分段节点卡死的问题 
- 根因: indextts 的 infer_v2.py 顶层导入 modelscope，会全局 monkey-patch
  transformers.PreTrainedModel.from_pretrained，导致 NeMo 模型加载卡死
- 修复: 在 aiia_indextts_nodes.py 中保存/恢复 from_pretrained 原始引用
- 清理 libs/ 目录：删除各依赖的文档、示例、测试等非运行时文件
- 新增 libs/index-tts (仅保留 indextts/ 核心包和 LICENSE)
 2026-02-19 12:05:07 +08:00
Hawk Lee 8b556e8435 v1.14.2: Fix NeMo diarization for PyTorch 2.10+, add JSON Extractor/Builder nodes, Qwen3-TTS voice presets & robustness fixes 2026-02-17 23:10:27 +08:00
Hawk Lee 40bc5627cb feat: add AIIA Text Splitter node (v1.13.0) 
New node that splits single-speaker text into dialogue_json format:
- 3 split modes: auto, by_sentence, by_line
- Short sentence merging (min_chars)
- Long sentence splitting at commas/semicolons (max_chars)
- Output compatible with Emotion Annotator and Dialogue TTS

Workflow: Text → Text Splitter → Emotion Annotator → TTS
 2026-02-16 11:03:31 +08:00
Hawk Lee a74a8b20bb feat: add AIIA Emotion Annotator node (LLM-driven) 
- New node: 🎭 AIIA Emotion Annotator (LLM)
- Supports Groq (free), Ollama, vLLM via OpenAI-compatible API
- API key from GROQ_API_KEY env var or node parameter
- Custom base URL for local LLM services
- skip_existing / overwrite_all modes
- Robust JSON parsing with markdown code block handling
- Proxy support from environment variables
 2026-02-16 01:24:36 +08:00
Hawk Lee c6c747b424 fix: restore overwritten remote files and add new ASR/Splitter/Stitcher nodes 
- Restore 12 files from 37cd909 that were accidentally overwritten
  by older local copies (includes BodySway, expanded subtitle/vibevoice nodes, etc.)
- Re-add ASR, Podcast Splitter, Podcast Stitcher registrations in __init__.py
- Keep new files: aiia_asr_nodes.py, aiia_podcast_splitter.py, aiia_podcast_stitcher.py
 2026-02-15 12:20:55 +08:00
Hawk Lee eff537d9dd feat: add ASR, Podcast Splitter, and Podcast Stitcher nodes for anti-leakage pipeline 
- Add AIIA_ASR node with FunASR (paraformer-zh + SenseVoiceSmall)
- Add AIIA_Podcast_Splitter for per-speaker text splitting
- Add AIIA_Podcast_Stitcher with 3-tier fuzzy alignment (exact, Levenshtein, fallback)
- Register 5 previously missing modules in __init__.py
- Update README with installation guide and node documentation
 2026-02-15 12:14:45 +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 b5c2c80e0c v1.10.12: Add Text Debug Splicer node 2026-02-02 13:54:19 +08:00
Hawk Lee dd911ed39e fix: Restore startup logging in __init__.py 2026-01-20 22:19:57 +08:00
Hawk Lee 3fe363537c fix: Register aiia_image_nodes via _load_nodes_from_module 2026-01-20 22:17:50 +08:00
Hawk Lee f2156a550f chore: Remove debug prints and update task status 2026-01-20 13:33:43 +08:00
Hawk Lee dce58dee12 feat: Add Ditto nodes and debug logs 2026-01-20 13:29:45 +08:00
Hawk Lee c9441f1b92 feat: add EchoMimic V3 nodes 2026-01-19 16:40:13 +08:00
Hawk Lee 8d933f0205 feat: Interactive Teaching Web Export (v1.8.0) 
- Add AIIA_Web_Export node for generating HTML player
- Update Script Parser to support (Visual: url) tags
- Update Dialogue TTS to propagate visual tags to segments
- Support relative paths for visual content
 2026-01-05 15:07:38 +08:00
Hawk Lee 57285ec603 feat: Add Subtitle Generation support (v1.7.0) 
- Add AIIA_Subtitle_Gen node for SRT/ASS generation
- Update AIIA_Dialogue_TTS to output precise timestamps (segments_info)
- Implement Smart Batch Interpolation for VibeVoice timestamps
- Update README and Walkthrough
 2026-01-05 13:33:57 +08:00
Hawk Lee 174cc81609 feat(podcast): Add VibeVoice Batch Modes and Fixes 
- Add Batch Mode (Natural, Strict, Whole) to Dialogue TTS
- Fix VibeVoice trailing noise with auto-trim
- Fix built-in audio clipping by attenuating volume
- Add comment support to Script Parser
- Update README with new features
 2026-01-04 20:27:06 +08:00
Hawk Lee d0d652446b Feat: Add VoxCPM 1.5 Node Skeleton 2026-01-04 15:34:42 +08:00
Hawk Lee 9d7f4a6071 chore: disable debug and initialization logs 2025-12-31 11:25:46 +08:00
Hawk Lee 6614ac07cf Refactor: Separate VibeVoice Realtime TTS and Preset Maker into modular files and enable direct connection 2025-12-30 16:32:30 +08:00
Hawk Lee 1f3c9b3134 feat: add Microsoft VibeVoice 1.5B support (v1.4.85) 2025-12-28 23:15:42 +08:00
Hawk Lee 8a26498f67 feat: add Audio Info node for metadata inspection (v1.4.83) 2025-12-28 23:03:11 +08:00
Hawk Lee 90d95db4fe fix: correctly indent node loading logic to prevent execution on duplicate load (v1.4.26) 2025-12-28 13:13:19 +08:00
Hawk Lee ee7b66c3c8 fix: implement smart duplicate detection in __init__ (v1.4.25) 2025-12-28 13:11:34 +08:00
Hawk Lee 2a0d2d6c2e chore: cleanup debug logs and finalize release (v1.4.24) 2025-12-28 13:10:00 +08:00
Hawk Lee 871e248813 fix: revert broken import guards, restore functionality (v1.4.23) 2025-12-28 13:08:29 +08:00
Hawk Lee f7ae303569 fix: stricter duplicate import check blocking paths with separators (v1.4.22) 2025-12-28 13:05:27 +08:00
Hawk Lee b81aba46fc fix: prevent double loading by ignoring absolute path imports (v1.4.21) 2025-12-28 13:04:10 +08:00
Hawk Lee 1e5d3db32f chore: add debug logging for module name and update version to 1.4.20 2025-12-28 13:02:25 +08:00
Hawk Lee d93e224473 feat: add AIIA_Audio_Enhance (Resemble Enhance) node (v1.4.15) 2025-12-28 12:13:34 +08:00
Hawk Lee f8e3b0057b feat: add ai audio denoise node using voicefixer (v1.4.0) 2025-12-28 01:12:04 +08:00
Hawk Lee 94585337c2 feat: improve cosyvoice stitching with sacrificial context and add splice debugging tool 2025-12-27 21:07:23 +08:00
Hawk Lee 633aaf44db feat: Introduce Audio Smart Chunker for optimized long audio splitting and CosyVoice integration 2025-12-26 22:59:05 +08:00
Hawk Lee 08bc6dd047 feat: Add AIIA Unlimited Voice Conversion for CosyVoice3 2025-12-26 22:31:36 +08:00
Hawk Lee cb8681fade feat: Add Audio Speaker Merger node with flexible duration alignment 2025-12-26 22:13:16 +08:00
Hawk Lee 842aaf7075 feat: Add Audio Speaker Isolator node for seamless speaker extraction 2025-12-26 21:22:46 +08:00
Hawk Lee fce3cab082 style: Clean up startup logs across all modules for a professional look 2025-12-26 20:53:21 +08:00
Hawk Lee 5cf70746ba feat: Restore PersonaLive nodes from history (without environment updates) 2025-12-26 18:27:13 +08:00
Hawk Lee be6738589a revert: ROLLBACK EVERYTHING TO PRE-DEC-26 STATE to fix static frame issue 2025-12-26 18:09:48 +08:00
Hawk Lee 6595332481 feat: Integrated PersonaLive nodes with OOM protection (In-Memory & To-Disk) 2025-12-26 00:54:11 +08:00
JaQuan cdbff9a6e9 确保HTTP路由被注册 2025-06-15 22:08:28 +08:00
l.y@live.cn b7ff46713a 20250607 2025-06-07 17:17:51 +08:00