Labels Milestones

Search syntax

assignee:<username>	Filter by assigned user
author:<username>	Filter by the author
is:all	All
is:closed	Closed
is:open	Open
mentions:<username>	Filter by mentioned user
modified:[>|<]<date>	Filter by last modified date
review:<username>	Filter by user who reviewed
sort:<by>:[asc|desc]	Sort by: created|comments|updated|deadline

Cancel

New issue

21 Open 2 Closed 23 All

Label

Show archived labels

All labels No label

pull-request

Milestone

All milestones No milestones

Project

All projects No project

Author

All authors

Assignee

All assignees No assignee

bsakaguchi

Sort

Relevance Newest Oldest Recently updated Least recently updated Most commented Least commented Nearest due date Farthest due date

21 Open 2 Closed 23 All

Close

Label

Clear labels

pull-request

Milestone

No milestone

Projects

Clear projects

Assignee

Clear assignees

No assignee

bsakaguchi

[PR #14] transformers 版本有误

pull-request

#23 opened 2026-10-30 21:03:38 +00:00 by bsakaguchi

[PR #21] Add compatibility for Transformers 5.x

pull-request

#22 opened 2026-10-30 21:03:38 +00:00 by bsakaguchi

[GH-ISSUE #23] Bug: Create Voice does not recompute when audio input changes (text unchanged) — likely broken IS_CHANGED; also always overwrites output file with no versioning

#21 opened 2026-10-30 21:03:35 +00:00 by bsakaguchi

[GH-ISSUE #22] Bug: save_path on Create Voice silently fails when target folder doesn't exist (no error, no log, no file saved)

#20 opened 2026-10-30 21:03:35 +00:00 by bsakaguchi

[GH-ISSUE #24] Feedback: Load Voice tooltip doesn't clearly state the folder it reads from, and its input/output model differs from ComfyUI convention without being flagged

#19 opened 2026-10-30 21:03:35 +00:00 by bsakaguchi

[GH-ISSUE #20] Not so good configuration with memory bugs

#18 opened 2026-10-30 21:03:34 +00:00 by bsakaguchi

[GH-ISSUE #18] Ability to process text in batches?

#17 opened 2026-10-30 21:03:34 +00:00 by bsakaguchi

[GH-ISSUE #16] Fails to load on Python 3.13 / ComfyUI v0.14.0 — transformers 5.x and 4.57.x both break

#15 opened 2026-10-30 21:03:32 +00:00 by bsakaguchi

[GH-ISSUE #17] The generated voice tone is too flat

#14 opened 2026-10-30 21:03:32 +00:00 by bsakaguchi

[GH-ISSUE #15] Node in Chinese

#13 opened 2026-10-30 21:03:32 +00:00 by bsakaguchi

[GH-ISSUE #13] pt克隆KeyError: 'ref_spk_embedding'

#12 opened 2026-10-30 21:03:27 +00:00 by bsakaguchi

[GH-ISSUE #11] This workflow uses custom nodes you haven't installed yet. AILab_Qwen3TTSLoadVoice AILab_Qwen3TTSWhisperSTT

11

#11 opened 2026-10-30 21:03:27 +00:00 by bsakaguchi

[GH-ISSUE #12] qwen_tts is not available.

2

#10 opened 2026-10-30 21:03:27 +00:00 by bsakaguchi

[GH-ISSUE #10] 'Qwen3TTSTalkerConfig' object has no attribute 'pad_token_id'

4

#9 opened 2026-10-30 21:03:22 +00:00 by bsakaguchi

[GH-ISSUE #8] why its not realtime and low latency as advertised by qwen tts? i am using 4090

1

#8 opened 2026-10-30 21:03:22 +00:00 by bsakaguchi

[GH-ISSUE #9] 'Qwen3TTSTalkerConfig' object has no attribute 'pad_token_id'

#7 opened 2026-10-30 21:03:22 +00:00 by bsakaguchi

[GH-ISSUE #5] Failed to import

1

#6 opened 2026-10-30 21:03:20 +00:00 by bsakaguchi

[GH-ISSUE #6] where is the advance workflows? when i use voice clone, it keep generate audio 2 minutes and 43 second.

3

#5 opened 2026-10-30 21:03:20 +00:00 by bsakaguchi

[GH-ISSUE #4] Torch OOM when loading large text sample

1

#4 opened 2026-10-30 21:03:20 +00:00 by bsakaguchi

[GH-ISSUE #1] sugerence add whisper node

1

#3 opened 2026-10-30 21:03:18 +00:00 by bsakaguchi