EthanfelandClaude Opus 4.8 6e6232d4ab Add SxCP Audio Prompt Guide node (audio -> waveform image + timing summary) ...

New node for audio-guided video prompts (LTX): takes a ComfyUI AUDIO clip + free-text
motion notes and outputs (1) a rendered energy-envelope IMAGE with beat/segment markers
so the vision model can see the audio shape, and (2) an audio_summary STRING with
duration, tempo/beats (librosa optional), per-segment energy + 8n+1-snapped frame counts
+ stage hints + the notes. Wire waveform_image -> Judge.reference_image and audio_summary
-> Judge.user_prompt (chat mode, json_output) for beat-aligned LTX JSON. librosa optional
(energy envelope + segments work without it). Registered in __init__; README workflow added.

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

2026-07-04 22:02:12 +02:00

..

__init__.py

Initial commit: VLM-as-judge prompt calibration loop

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

audio_guide.py

Add SxCP Audio Prompt Guide node (audio -> waveform image + timing summary)

2026-07-04 22:02:12 +02:00

qwen_judge.py

chat mode: json_output toggle to return clean extracted JSON

2026-07-02 02:09:36 +02:00

receptor.py

Fix: render text inputs as editable fields, not input sockets

2026-06-27 10:18:12 +02:00