EthanfelandClaude Opus 4.8
6e6232d4ab
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>
16 lines
627 B
Plaintext
16 lines
627 B
Plaintext
# Qwen3-VL needs transformers >= 4.57. The newer natively-multimodal Qwen3.5/3.6
|
|
# abliterated models need a recent transformers exposing AutoModelForMultimodalLM
|
|
# (upgrade transformers if a Qwen3.5/3.6 model fails to load).
|
|
transformers>=4.57.0
|
|
huggingface_hub # auto-download of models by repo id / alias
|
|
torch
|
|
pillow
|
|
numpy
|
|
# for precision=nf4 (4-bit) — needed to run the 30B-A3B abliterated judge on 32 GB:
|
|
bitsandbytes
|
|
# optional, for the Audio Prompt Guide node — adds tempo (BPM) + beat times
|
|
# (energy envelope + segments work without it):
|
|
# librosa
|
|
# optional, for faster attention on the RTX 5090:
|
|
# flash-attn
|