diodiogod fab00263fb Version 5.8.7 ...

Run VibeVoice and KugelAudio natively on Transformers 5

Technical details:
- Add compatibility shims for Transformers 5 tokenizer, registration, generation, cache, dtype, and weight-tying APIs
- Materialize VibeVoice and KugelAudio diffusion scheduler state on CPU during meta-device model construction
- Remove the VibeVoice runtime selector and force legacy workflow values onto the main environment
- Update engine metadata and documentation to reflect native Transformers 5 support
- Suppress expected VibeVoice tied-weight and compatibility warnings

2026-08-28 15:06:49 -03:00

..

refactoring summary

update files

2025-07-12 23:42:45 -03:00

CACHE_ANALYSIS.md

TIER 3: Complete architecture standardization for model loading

2025-11-14 10:10:52 -03:00

CACHE_ISSUES_SUMMARY.md

TIER 3: Complete architecture standardization for model loading

2025-11-14 10:10:52 -03:00

COMFYUI_MESSAGING_GUIDE.md

Rename Audio Analyzer to Audio Wave Analyzer and fix F5-TTS nfe_step bug

2025-07-13 01:02:08 -03:00

COMFYUI_REGRESSION_FINDINGS.md

Move COMFYUI_REGRESSION_FINDINGS.md to proper docs location

2025-09-26 15:44:43 -03:00

DEPENDENCY_MANAGEMENT_GUIDE.md

docs: reorganize docs folder structure

2026-03-01 01:46:34 -03:00

DRAMABOX_CHATTERBOX_V3_CAPABILITY_SCOPE.md

Add DramaBox and ChatterBox V3 support

2026-07-25 11:38:52 -03:00

Echo_TTS_PR_250_Code_Review.md

Add comprehensive code review for Echo-TTS PR #250

2026-02-06 01:51:30 -03:00

f5tts_integration_guide.py

update files

2025-07-12 23:42:45 -03:00

F5TTS_EDIT_IMPROVEMENTS_PLAN.md

Version 3.0.4: Fix ChatterBox import detection to find bundled packages

2025-07-14 22:11:41 -03:00

F5TTS_IMPLEMENTATION_COMPLETE_REPORT.md

Release v3.0.0: Complete F5-TTS and Audio Analyzer implementation

2025-07-13 11:32:26 -03:00

F5TTS_IMPLEMENTATION_SUMMARY.md

update files

2025-07-12 23:42:45 -03:00

F5TTS_INTEGRATION_SPECIFICATION.md

update files

2025-07-12 23:42:45 -03:00

F5TTS_STREAMING_INTEGRATION_PLAN.md

Implement universal streaming system architecture

2025-08-10 11:30:44 -03:00

HIGGS_AUDIO_2_INTEGRATION_SPECIFICATION.md

Fix Higgs Audio 2 engine integration issues

2025-08-18 18:37:59 -03:00

HIGGS_AUDIO_STATELESS_WRAPPER_IMPLEMENTATION.md

Version 4.5.27

2025-08-28 17:41:42 -03:00

INDEXTTS_IMPLEMENTATION_PLAN.md

docs: reorganize docs folder structure

2026-03-01 01:46:34 -03:00

ISOLATED_RUNTIMES_PLAN.md

Add isolated runtimes implementation plan

2026-06-06 15:12:07 -03:00

MODEL_LOADING_ANALYSIS.md

docs: Add model loading architecture analysis and refactor recommendations

2025-11-13 20:47:00 -03:00

MODEL_LOADING_REFACTOR_REPORT.md

docs: Add model loading architecture analysis and refactor recommendations

2025-11-13 20:47:00 -03:00

MULTILANGUAGE_MODULARIZATION_PLAN.md

Reorganize documentation files into Dev reports folder

2025-08-08 14:54:50 -03:00

PARAMETER_MIGRATION_CHECKLIST.md

Version 3.0.7

2025-07-15 13:52:13 -03:00

PAUSE_TAGS_IMPLEMENTATION_REPORT.md

Reorganize documentation files into Dev reports folder

2025-08-08 14:54:50 -03:00

POST_V4.2.3_DEVELOPMENT_REVIEW.md

Clean up unused code and update PROJECT_INDEX.md with accurate architecture documentation

2025-08-12 22:42:34 -03:00

POST_V4.4.0_DEVELOPMENT_REVIEW.md

docs: reorganize docs folder structure

2026-03-01 01:46:34 -03:00

pytest_implementation_report.md

implemented a comprehensive pytest testing infrastructure for the TTS-Audio-Suite custom node. The infrastructure supports both **unit tests** (fast, no ComfyUI needed) and **integration tests** (requires running ComfyUI server).

2025-12-18 21:51:42 +01:00

REFACTORING_PLAN.md

Clean up README condensed engine table

2026-01-28 11:10:29 -03:00

SRT_Edit_Tag_Batch_Processing_Pattern.md

Add inline edit tag support for Higgs Audio and fix CUDA graph unloading crash

2025-12-06 19:04:27 -03:00

SRT_IMPLEMENTATION_OLD.md

Complete restructure of SRT_IMPLEMENTATION.md documentation

2025-07-14 12:04:30 -03:00

SRT_IMPLEMENTATION.md

Fix Advanced Usage Examples in SRT_IMPLEMENTATION.md

2025-07-14 12:18:37 -03:00

STATELESS_WRAPPER_IMPLEMENTATION_PLAN.md

Implement stateless ChatterBox wrapper for thread-safe parallel processing

2025-08-11 22:52:15 -03:00

Step_Audio_EditX_Implementation_Plan.md

Add Step Audio EditX segment parameter support and fix tooltips

2025-12-04 13:59:49 -03:00

Step_Audio_EditX_Inline_Tags_Plan.md

Implement inline edit tags for Step Audio EditX post-processing

2025-12-05 21:20:21 -03:00

STREAMING_ARCHITECTURE.md

Remove unused dynamic_worker_manager.py and update streaming architecture docs

2025-08-10 02:40:29 -03:00

test_cases.txt

Reorganize documentation files into Dev reports folder

2025-08-08 14:54:50 -03:00

TIER2-3_REFACTOR_PLAN.md

Fix: Move TIER2-3_REFACTOR_PLAN.md to correct directory

2025-11-14 23:02:11 -03:00

TODO.md

Document new engine validation rules

2026-07-10 00:21:17 -03:00

TRANSFORMERS_5_HIGGS_AUDIO_REPORT.md

Document Higgs Audio transformers 5 investigation

2026-06-08 17:40:15 -03:00

TRANSFORMERS_5_QWEN3_TTS_REPORT.md

Version 5.8.7

2026-08-28 15:06:49 -03:00

tts_audio_suite_aux_models.yaml

Add OmniVoice engine with native SRT duration targeting

2026-06-18 22:23:32 -03:00

tts_audio_suite_engines.yaml

Version 5.8.7

2026-08-28 15:06:49 -03:00

VERSION_3.1_RELEASE_GUIDE.md

docs: reorganize docs folder structure

2026-03-01 01:46:34 -03:00

VERSION_UPDATE_GUIDE.md

Major README.md redesign and version management automation

2025-07-14 11:09:33 -03:00

VIBEVOICE_INTEGRATION_PLAN.md

docs: split model sources and layouts from README

2026-02-20 13:46:00 -03:00