Topics
Each hub gathers our Lab posts, directory entries and pipelines for one tool or technique.
- HyperFrames
37 posts · 12 skills & repos · 4 pipelines
HyperFrames is HeyGen's open-source (Apache-2.0) renderer that turns HTML, CSS and GSAP into frame-exact MP4.
- Remotion
27 posts · 15 skills & repos · 2 pipelines
Remotion is the established React-to-video framework, and it now ships official agent skills.
- ComfyUI
47 posts · 62 skills & repos · 1 pipeline
ComfyUI is the node-graph workbench where most open video models land first: Wan, LTX, MiniMax H3, plus partner nodes for hosted models.
- Higgsfield
20 posts · 19 skills & repos · 4 pipelines
Higgsfield is a hosted AI video studio.
- Seedance
19 posts · 7 skills & repos · 4 pipelines
Seedance is ByteDance's video model family, a common choice for the cinematic 'plate' under code-made motion graphics and for Blender-blockout-to-shot workflows.
- Kling
10 posts · 5 skills & repos · 1 pipeline
Kling is Kuaishou's video model.
- Claude Motion & code motion skills
9 posts · 4 skills & repos · 2 pipelines
Two things share this name.
- Audio, voice & music
38 posts · 69 skills & repos · 6 pipelines
The sound side of AI video: text-to-speech and voice, music generation, foley, stem separation and word-level timing for captions and cuts.
- Open-weight video & audio models
49 posts · 63 skills & repos · 2 pipelines
Video and audio models you can download and run yourself instead of renting through an app: LTX, Wan, MiniMax H3, HunyuanVideo-Foley, ACE-Step and friends.
- Wan
4 posts · 6 skills & repos · 1 pipeline
Wan is Alibaba's video model family.
- Video MCP servers
43 posts · 47 skills & repos · 5 pipelines
MCP servers let Claude, Codex or Cursor drive video tools directly: generation (Higgsfield, Kling), voice (ElevenLabs), or a whole editor.
- Motion graphics skills
32 posts · 51 skills & repos · 2 pipelines
Agent skills and pipelines for motion graphics made in code: launch videos, explainers, animated type and B-roll timed to narration.