EthanfelandClaude Opus 4.8 4003dbb6e8 Judge: add seed (reproducible output) + interrupt support ...

New 'seed' input seeds sampling (torch.manual_seed before generation) so a fixed seed
reproduces the same output — no reroll when re-queueing while tweaking downstream nodes;
bump it to reroll (named 'seed' so the frontend adds control_after_generate). Generation
now honors ComfyUI cancel: a StoppingCriteria halts model.generate() promptly and
_check_interrupt() raises between passes. Workflows updated with the seed widget.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-07-05 00:15:05 +02:00

..

__init__.py

Initial commit: VLM-as-judge prompt calibration loop

2026-06-26 22:15:56 +02:00

audio_guide.py

Audio Wave: skip overlapping segment labels (readable when splits are close)

2026-07-04 23:56:51 +02:00

audio_wave_segments.py

Audio Wave: segments = user splits only (721 groups are markers, not segments)

2026-07-04 23:49:46 +02:00

qwen_judge.py

Judge: add seed (reproducible output) + interrupt support

2026-07-05 00:15:05 +02:00

receptor.py

Drop the SxCP prefix from this pack's node names

2026-07-04 22:36:50 +02:00

text.py

Add LTX audio workflow + Text (Prompt) node

2026-07-04 22:40:52 +02:00