Video Loom

Multi-provider AI video workflow

Use the right AI video provider for each shot.

Video Loom is built around provider choice. Route scenes through configured cloud APIs, hosted inference, Runway, MiniMax, xAI, Vertex, FAL-backed models, or local ComfyUI workflows — inside one project.

Open Video Loom See how it works
Per-scene AI video provider and model routing in Video Loom

Model choice at the shot level

A performance closeup, an abstract lyric visual, a bridge transition, and a source-video restyle may each need a different model. Video Loom keeps that routing inside the project.

  • Per-scene provider and model overrides.
  • Fallback chains for configured adapters.
  • Provider status and diagnostics in the workspace.

Continuity travels with the request

Provider calls can receive the scene prompt plus available references, source media, continuity cues, and previous-shot context.

  • Reference frames and continuity anchors.
  • Text, image, and source-video paths.
  • Take metadata for review and retry decisions.

Local and hosted in one project

Use hosted services for speed or local ComfyUI workflows for GPU-local control while preserving a single project and timeline.

  • Canonical ComfyUI workflow templates.
  • Hosted FAL-backed model catalog support.
  • Cloud persistence and recoverable jobs where supported.

Questions

What teams ask before opening the app.

Does Video Loom require one AI video provider?

No. It is designed for configured provider routing, so teams can choose the best available model per scene.

Can local ComfyUI workflows join the same project?

Yes. When enabled and configured, local ComfyUI workflows participate alongside cloud and hosted providers.

Keep exploring

AI video storyboard Storyboard AI video before spending on generation. Source media to video Turn your images and footage into generated scenes. AI video pricing Simple credit-based pricing for AI video production.