render-cinematic-music-video

Name: render-cinematic-music-video
Author: gooseworks-ai

1.0kstars193forks

How to install render-cinematic-music-video?

gooseworks-ai/goose-skills/render-cinematic-music-video

$npx -y skills add gooseworks-ai/goose-skills --skill render-cinematic-music-video

Installs into the current project.

Summary

Assemble a cinematic live-action-style music-video ad from a config — an original sung anthem carries the whole narrative while N 35mm-film-look i2v clips are each cut to their lyric window and hard-concatenated on the beat as a 3-act arc, the anthem muxed at loudnorm I=-14, cine

Files · 1

View on GitHub

SKILL.md

1	# render-cinematic-music-video
2
3	Assemble a cinematic music-video ad from a config: a live-action-STYLE short film where an
4	original sung anthem is the score and every visual beat is a shot-on-film tableau (Kodak Portra
5	grain, light leaks, golden hour, handheld imperfection) timed to the lyrics, arranged as a
6	3-act arc (morning → peak → twilight) with the hook line on the chorus drop. This capability is
7	the FREE, deterministic assembly — cut-to-window, hard-concat, anthem mux, caption burn,
8	and the brand end card.
9
10	`scripts/config.example.json` is the worked example (Hype and Vice "Game Day Girls", ~28s
11	1080×1920 9:16, 14 tableaux); `scripts/PIPELINE.md` maps every config block to its source step
12	and `scripts/README.md` documents the free assembly.
13
14	## Run
15
16	This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are
17	separate capabilities: the sung anthem (`create-music-elevenlabs`, `force_instrumental` false —
18	the lyrics ARE the script, returns mp3 + `words_timestamps`); one 35mm-film keyframe per beat
19	in one look pack (`create-image-fal`); and one Kling 3.0 i2v clip per beat (`create-video-fal`).
20	Given the delivered anthem + `words.json` + one clip per beat + the brand end-card asset,
21	`render-cinematic-music-video` cuts each clip to its lyric window, hard-concats on the beat,
22	muxes the anthem, burns the cinematic lower-third captions, and overlays the end card → the
23	master. Re-cuts reuse the existing anthem / keyframes / clips and cost $0.
24
25	## Contract (the free assembly)
26
27	- The sung anthem carries the story — no separate VO. The generated ElevenLabs track IS
28	the bed and the script (`force_instrumental` false); do not add a spoken voiceover or a
29	second bed.
30	- Plan the timeline AROUND the delivered anthem. The anthem is generated first and
31	reshapes/overshoots length; snap every tableau boundary to the lyric-phrase edges in the
32	returned word timings — never trim the anthem to a pre-planned grid.
33	- Captions from the anthem's OWN word timings, not Whisper. Derive `words.json` from the
34	music model's `words_timestamps`, chunk ~4 words at lyric boundaries, and burn cinematic
35	lower-third serif captions (`--placement low`) with the hook line accent-treated (bold-italic).
36	Whisper on sung audio returns "🎵 Music Playing 🎵".
37	- Land the hook on the chorus drop. The hero tableau (`is_hook`) is timed so the
38	load-bearing line sits on the chorus drop; accent that line in the captions.
39	- One cinematic look pack + hard cuts on the beat. The look pack (named film stock + grain +
40	flares + handheld) plus a continuity anchor holds every clip together; cut each clip to its
41	lyric window and hard-concat (one optional match-cut into the hero reveal) — no dissolves.
42	- End card from the real brand asset — never AI-render the wordmark as diffusion text.
43	Composite the lockup (PIL/ffmpeg) from the real asset or use a designed keyframe base;
44	diffusion garbles a wordmark.
45	- FFmpeg composite, deterministic, FREE. Normalize each clip to its beat-locked window,
46	hard-concat, mux the anthem (`afade` in/out + `loudnorm I=-14`), burn the caption ASS, overlay
47	the end card → a 1080×1920 h264+aac master. No paid calls, no keys.

People who liked this also viewed

6 picks

Type

render-cinematic-music-video

1.0kstars193forks

View on GitHub

How to install render-cinematic-music-video?

gooseworks-ai/goose-skills/render-cinematic-music-video

$npx -y skills add gooseworks-ai/goose-skills --skill render-cinematic-music-video

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# render-cinematic-music-video
2
3	Assemble a cinematic music-video ad from a config: a live-action-STYLE short film where an
4	original sung anthem is the score and every visual beat is a shot-on-film tableau (Kodak Portra
5	grain, light leaks, golden hour, handheld imperfection) timed to the lyrics, arranged as a
6	3-act arc (morning → peak → twilight) with the hook line on the chorus drop. This capability is
7	the FREE, deterministic assembly — cut-to-window, hard-concat, anthem mux, caption burn,
8	and the brand end card.
9
10	`scripts/config.example.json` is the worked example (Hype and Vice "Game Day Girls", ~28s
11	1080×1920 9:16, 14 tableaux); `scripts/PIPELINE.md` maps every config block to its source step
12	and `scripts/README.md` documents the free assembly.
13
14	## Run
15
16	This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are
17	separate capabilities: the sung anthem (`create-music-elevenlabs`, `force_instrumental` false —
18	the lyrics ARE the script, returns mp3 + `words_timestamps`); one 35mm-film keyframe per beat
19	in one look pack (`create-image-fal`); and one Kling 3.0 i2v clip per beat (`create-video-fal`).
20	Given the delivered anthem + `words.json` + one clip per beat + the brand end-card asset,
21	`render-cinematic-music-video` cuts each clip to its lyric window, hard-concats on the beat,
22	muxes the anthem, burns the cinematic lower-third captions, and overlays the end card → the
23	master. Re-cuts reuse the existing anthem / keyframes / clips and cost $0.
24
25	## Contract (the free assembly)
26
27	- The sung anthem carries the story — no separate VO. The generated ElevenLabs track IS
28	the bed and the script (`force_instrumental` false); do not add a spoken voiceover or a
29	second bed.
30	- Plan the timeline AROUND the delivered anthem. The anthem is generated first and
31	reshapes/overshoots length; snap every tableau boundary to the lyric-phrase edges in the
32	returned word timings — never trim the anthem to a pre-planned grid.
33	- Captions from the anthem's OWN word timings, not Whisper. Derive `words.json` from the
34	music model's `words_timestamps`, chunk ~4 words at lyric boundaries, and burn cinematic
35	lower-third serif captions (`--placement low`) with the hook line accent-treated (bold-italic).
36	Whisper on sung audio returns "🎵 Music Playing 🎵".
37	- Land the hook on the chorus drop. The hero tableau (`is_hook`) is timed so the
38	load-bearing line sits on the chorus drop; accent that line in the captions.
39	- One cinematic look pack + hard cuts on the beat. The look pack (named film stock + grain +
40	flares + handheld) plus a continuity anchor holds every clip together; cut each clip to its
41	lyric window and hard-concat (one optional match-cut into the hero reveal) — no dissolves.
42	- End card from the real brand asset — never AI-render the wordmark as diffusion text.
43	Composite the lockup (PIL/ffmpeg) from the real asset or use a designed keyframe base;
44	diffusion garbles a wordmark.
45	- FFmpeg composite, deterministic, FREE. Normalize each clip to its beat-locked window,
46	hard-concat, mux the anthem (`afade` in/out + `loudnorm I=-14`), burn the caption ASS, overlay
47	the end card → a 1080×1920 h264+aac master. No paid calls, no keys.

People who liked this also viewed

6 picks

Type