render-cartoon-music-video

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

1.0kstars193forks

How to install render-cartoon-music-video?

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

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

Installs into the current project.

Summary

Assemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one recurring animated character, one look pack) are each cut to their BAR window from librosa beat-tracking and hard-concatenated on the

Files · 1

View on GitHub

SKILL.md

1	# render-cartoon-music-video
2
3	Assemble a cartoon music-video ad from a config: an animated / illustrated / hand-crafted
4	story (stop-motion felt-and-foam, claymation, 2D toon, cut-out) where a sung song is the entire
5	script and one recurring animated character carries every shot, cut to the bar with the climax
6	line on the drop. This capability is the FREE, deterministic assembly — cut-to-bar,
7	hard-concat, the logo bug + captions burn, and the solid-color end card.
8
9	`scripts/config.example.json` is the worked example (Coinbase "Bet on anything", ~55s 1080×1920
10	9:16, 16 body bars + a 3s end card); `scripts/PIPELINE.md` maps every config block to its source
11	step and `scripts/README.md` documents the free assembly.
12
13	## Run
14
15	This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are
16	separate capabilities: the sung song (`create-music-elevenlabs`, or a user-supplied mp3 + Whisper
17	word timings) beat-tracked with librosa so the BAR GRID sets the timeline; one locked recurring
18	character + one keyframe per bar in one look pack (`create-image-fal`, Nano Banana); and one
19	Seedance i2v clip per bar (`create-video-fal`). Given the song + `word-timestamps.json` +
20	`bars.json` + one clip per bar + the brand wordmark SVG, `render-cartoon-music-video` cuts each
21	clip to its bar window, hard-concats on the bar, burns the logo bug + captions, appends the
22	solid-color end card, and muxes the song under it → the master. Re-cuts reuse the existing song /
23	keyframes / clips and cost $0.
24
25	## Contract (the free assembly)
26
27	- The sung song carries the narrative — no separate VO. The generated/supplied track IS the
28	bed (no VO to duck under); do not add a spoken voiceover or a second bed.
29	- Plan the timeline AROUND the delivered song's BAR GRID. Beat-track the song with librosa
30	(assume 4/4); one bar = one shot (default). Snap every tableau window to the bar boundaries —
31	never trim the song to a pre-planned grid.
32	- Captions from the song's word timings, re-spelled against the locked lyrics. Whisper
33	mishears shouted accents ("BETS" → "Hearts"); re-spell the timed tokens against the locked
34	lyric file (never edit lyrics to match Whisper). VEED-whisper white bold sans in the
35	BOTTOM third (Alignment 2, `margin_v` above the bottom-left logo bug), ~4–5 words per cue,
36	NO background pill; captions STOP at the end-card boundary. Never mid-frame — it covers the
37	character (fixed 2026-07). If the host ffmpeg lacks libass, render the cues as timed PIL PNG
38	overlays (ffmpeg `overlay=…:enable='between(t,st,en)'`) at the same bottom placement.
39	- Land the climax line on the drop. The climax tableau is timed so the payoff line sits on
40	the sub-bass drop; accent that line.
41	- Persistent logo bug, suppressed on the end card. Burn a white brand wordmark bottom-left
42	over the body bars (cairosvg → PIL from the real SVG), suppressed on the end card where the big
43	wordmark dominates.
44	- End card via cairosvg + PIL from the real wordmark — never AI-render brand text. Solid
45	brand-color card + white wordmark + subhead, holding ~3s WITH the song still playing under it
46	(afade-out over the tail — no silent tail). A diffusion model garbles a wordmark.
47	- FFmpeg composite, deterministic, FREE. Cut each clip to its bar window, hard-concat, burn
48	the logo bug + captions, append the end card, mux the song over the whole video with a 0.5s
49	afade tail, `loudnorm I=-14` → a 1080×1920 h264+aac master. No paid calls, no keys. When the host
50	ffmpeg lacks libass/drawtext, BOTH the captions and the logo bug are timed PIL PNG overlays
51	(`overlay=x:y:enable='between(t,st,en)'`), not an ASS burn.
52	- QC PER SCENE, never just the master — the two failure modes are content, not assembly. The
53	upstream keyframe/i2v steps can (a) drift the character felt → smooth-3D "man" partway
54	through and (b) hallucinate hands — realistic fingers in a hand macro, a pointing finger on a
55	"tap the phone" shot, or a

People who liked this also viewed

6 picks

Type

render-cartoon-music-video

1.0kstars193forks

View on GitHub

How to install render-cartoon-music-video?

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

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# render-cartoon-music-video
2
3	Assemble a cartoon music-video ad from a config: an animated / illustrated / hand-crafted
4	story (stop-motion felt-and-foam, claymation, 2D toon, cut-out) where a sung song is the entire
5	script and one recurring animated character carries every shot, cut to the bar with the climax
6	line on the drop. This capability is the FREE, deterministic assembly — cut-to-bar,
7	hard-concat, the logo bug + captions burn, and the solid-color end card.
8
9	`scripts/config.example.json` is the worked example (Coinbase "Bet on anything", ~55s 1080×1920
10	9:16, 16 body bars + a 3s end card); `scripts/PIPELINE.md` maps every config block to its source
11	step and `scripts/README.md` documents the free assembly.
12
13	## Run
14
15	This is the FREE, deterministic assembly stage — it spends nothing. The paid inputs are
16	separate capabilities: the sung song (`create-music-elevenlabs`, or a user-supplied mp3 + Whisper
17	word timings) beat-tracked with librosa so the BAR GRID sets the timeline; one locked recurring
18	character + one keyframe per bar in one look pack (`create-image-fal`, Nano Banana); and one
19	Seedance i2v clip per bar (`create-video-fal`). Given the song + `word-timestamps.json` +
20	`bars.json` + one clip per bar + the brand wordmark SVG, `render-cartoon-music-video` cuts each
21	clip to its bar window, hard-concats on the bar, burns the logo bug + captions, appends the
22	solid-color end card, and muxes the song under it → the master. Re-cuts reuse the existing song /
23	keyframes / clips and cost $0.
24
25	## Contract (the free assembly)
26
27	- The sung song carries the narrative — no separate VO. The generated/supplied track IS the
28	bed (no VO to duck under); do not add a spoken voiceover or a second bed.
29	- Plan the timeline AROUND the delivered song's BAR GRID. Beat-track the song with librosa
30	(assume 4/4); one bar = one shot (default). Snap every tableau window to the bar boundaries —
31	never trim the song to a pre-planned grid.
32	- Captions from the song's word timings, re-spelled against the locked lyrics. Whisper
33	mishears shouted accents ("BETS" → "Hearts"); re-spell the timed tokens against the locked
34	lyric file (never edit lyrics to match Whisper). VEED-whisper white bold sans in the
35	BOTTOM third (Alignment 2, `margin_v` above the bottom-left logo bug), ~4–5 words per cue,
36	NO background pill; captions STOP at the end-card boundary. Never mid-frame — it covers the
37	character (fixed 2026-07). If the host ffmpeg lacks libass, render the cues as timed PIL PNG
38	overlays (ffmpeg `overlay=…:enable='between(t,st,en)'`) at the same bottom placement.
39	- Land the climax line on the drop. The climax tableau is timed so the payoff line sits on
40	the sub-bass drop; accent that line.
41	- Persistent logo bug, suppressed on the end card. Burn a white brand wordmark bottom-left
42	over the body bars (cairosvg → PIL from the real SVG), suppressed on the end card where the big
43	wordmark dominates.
44	- End card via cairosvg + PIL from the real wordmark — never AI-render brand text. Solid
45	brand-color card + white wordmark + subhead, holding ~3s WITH the song still playing under it
46	(afade-out over the tail — no silent tail). A diffusion model garbles a wordmark.
47	- FFmpeg composite, deterministic, FREE. Cut each clip to its bar window, hard-concat, burn
48	the logo bug + captions, append the end card, mux the song over the whole video with a 0.5s
49	afade tail, `loudnorm I=-14` → a 1080×1920 h264+aac master. No paid calls, no keys. When the host
50	ffmpeg lacks libass/drawtext, BOTH the captions and the logo bug are timed PIL PNG overlays
51	(`overlay=x:y:enable='between(t,st,en)'`), not an ASS burn.
52	- QC PER SCENE, never just the master — the two failure modes are content, not assembly. The
53	upstream keyframe/i2v steps can (a) drift the character felt → smooth-3D "man" partway
54	through and (b) hallucinate hands — realistic fingers in a hand macro, a pointing finger on a
55	"tap the phone" shot, or a

People who liked this also viewed

6 picks

Type