Ethanfel and Claude Sonnet 4.6
679a607a85
feat: wire prompt output from feature extractor to sampler in demo workflow
...
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-04 17:13:23 +02:00
Ethanfel and Claude Sonnet 4.6
c23d210ab2
feat: SelVA video-to-audio example workflow
...
LoadVideo → SelvaFeatureExtractor → SelvaSampler → PreviewAudio.
Defaults: medium_44k, bf16, 25 steps, cfg=4.5.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-04-04 15:31:53 +02:00
Ethanfel and Claude Sonnet 4.6
67be94c45c
chore: add updated V2A example workflow
...
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-28 11:13:06 +01:00
Ethanfel and Claude Sonnet 4.6
681d230b0c
chore: update T2A workflow to match V2A style and current defaults
...
Steps=100, cfg=7.0, randomize seed, consistent node format with
aux_id/ver/ue_properties.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-28 11:11:20 +01:00
Ethanfel and Claude Sonnet 4.6
f32456a142
feat: add fps input to PrismAudioFeatureExtractor
...
Exposes the video frame rate as an optional input (default 30).
Correct FPS ensures accurate temporal frame sampling in VideoPrism
and Synchformer feature extraction.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-27 20:08:10 +01:00
Ethanfel and Claude Sonnet 4.6
7671d296fa
fix: remove spurious caption_cot input entry from video_to_audio workflow
...
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-27 19:39:05 +01:00
Ethanfel and Claude Sonnet 4.6
3894fcc9b4
feat: add demo workflows for text-to-audio and video-to-audio
...
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-27 19:32:24 +01:00
EthanfelandClaude Sonnet 4.6