mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-05-05 02:31:47 +00:00

SHL0MS 9d885b266c feat(skills): add manim-video skill for mathematical and technical animations

Production pipeline for creating 3Blue1Brown-style animated videos
using Manim Community Edition. The agent handles the full workflow:
creative planning, Python code generation, rendering, scene stitching,
audio muxing, and iterative refinement.

Modes: concept explainers, equation derivations, algorithm
visualizations, data stories, architecture diagrams, paper explainers,
3D visualizations.

9 reference files, setup verification script, README.
All API references verified against ManimCommunity/manim source.

2026-04-05 19:09:37 -04:00

2.4 KiB

Raw Blame History

Rendering Reference

Prerequisites

manim --version       # Manim CE
pdflatex --version    # LaTeX
ffmpeg -version       # ffmpeg

CLI Reference

manim -ql script.py Scene1 Scene2    # draft (480p 15fps)
manim -qm script.py Scene1           # medium (720p 30fps)
manim -qh script.py Scene1           # production (1080p 60fps)
manim -ql --format=png -s script.py Scene1  # preview still (last frame)
manim -ql --format=gif script.py Scene1     # GIF output

Quality Presets

Flag	Resolution	FPS	Use case
`-ql`	854x480	15	Draft iteration (layout, timing)
`-qm`	1280x720	30	Preview (use for text-heavy scenes)
`-qh`	1920x1080	60	Production

Text rendering quality: -ql (480p15) produces noticeably poor text kerning and readability. For scenes with significant text, preview stills at -qm to catch issues invisible at 480p. Use -ql only for testing layout and animation timing.

Output Structure

media/videos/script/480p15/Scene1_Intro.mp4
media/images/script/Scene1_Intro.png  (from -s flag)

Stitching with ffmpeg

cat > concat.txt << 'EOF'
file 'media/videos/script/480p15/Scene1_Intro.mp4'
file 'media/videos/script/480p15/Scene2_Core.mp4'
EOF
ffmpeg -y -f concat -safe 0 -i concat.txt -c copy final.mp4

Add Voiceover

# Mux narration
ffmpeg -y -i final.mp4 -i narration.mp3 -c:v copy -c:a aac -b:a 192k -shortest final_narrated.mp4

# Concat per-scene audio first
cat > audio_concat.txt << 'EOF'
file 'audio/scene1.mp3'
file 'audio/scene2.mp3'
EOF
ffmpeg -y -f concat -safe 0 -i audio_concat.txt -c copy full_narration.mp3

Add Background Music

ffmpeg -y -i final.mp4 -i music.mp3 \
  -filter_complex "[1:a]volume=0.15[bg];[0:a][bg]amix=inputs=2:duration=shortest" \
  -c:v copy final_with_music.mp4

GIF Export

ffmpeg -y -i scene.mp4 \
  -vf "fps=15,scale=640:-1:flags=lanczos,split[s0][s1];[s0]palettegen[p];[s1][p]paletteuse" \
  output.gif

Aspect Ratios

manim -ql --resolution 1080,1920 script.py Scene  # 9:16 vertical
manim -ql --resolution 1080,1080 script.py Scene  # 1:1 square

Render Workflow

Draft render all scenes at -ql
Preview stills at key moments (-s)
Fix and re-render only broken scenes
Stitch with ffmpeg
Review stitched output
Production render at -qh
Re-stitch + add audio

2.4 KiB Raw Blame History