agentleFS
frankxaifrankxai/creator-skills/skills/video/video-engine-routing/SKILL.md

video-engine-routing

Skill6 starsChanged 47 days agoMITView on GitHub

Decide WHERE video/image generation runs when cost, volume, or capability forces a choice - subscription credits vs pay-per-use APIs vs cloud ComfyUI. Use when asked "which video engine should I use", "is Higgsfield/fal/RunComfy worth it", "credits ran out", "cheapest way to generate N clips", "do I need ComfyUI", "should I run this locally", or when the video-gen skill escalates a budget or capability ceiling. Contains the pricing table, graduation triggers, and the never-local rule for iGPU machines.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Back down: if a rented workflow runs less than monthly, cancel the machine and take the per-use price.

    line 53
  2. Distinctive:

    Don't install vendor API-wrapper skill packs for engines you don't pay for — every one of them is lock-in to that vendor's endpoint with no …

    line 58
  3. Distinctive:

    Don't run modern video models on integrated GPUs (see rule 4 above).

    line 60
  4. Distinctive:

    Don't hold two overlapping subscriptions to hedge.

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

video-engine-routing — when you outgrow your default engine

The default stack (see video-gen) assumes a subscription engine. This skill is the escalation path: what to do when credits run out, volume grows, or the pipeline needs control the subscription engine cannot give.

The decision tree

  1. Under ~50 clips/month, mixed styles, no custom pipeline → stay on the subscription engine you already pay for (an all-in-one such as Higgsfield, or an equivalent). Sunk cost, routing across many models, zero ops.
  2. Bursty overflow or budget clips at volume → pay-per-use API (fal.ai). No subscription, no credit expiry, cheapest per-clip for budget models.
  3. Custom pipeline: LoRA character consistency at batch scale, ControlNet/IPAdapter chains, motion transfer, community models → cloud ComfyUI (RunComfy machines or Comfy Cloud). You are paying for control, not per-clip price.
  4. Local GPU rendering → only with a recent NVIDIA card with 16 GB+ VRAM. On an iGPU machine (Intel Arc/AMD APU, shared memory): never. Modern video models blow through shared-memory budgets, and quantized variants degrade video coherence. Cloud is faster and cheaper than wasted local hours.

Pricing reference (mid-2026, one 5-second 1080p clip)

These are the author's working estimates, not vendor quotes, and none is sourced here. Open each vendor's current pricing page before you decide.

RouteCost per 5s clipNotes
All-in-one subscription (Higgsfield)~$0.30–0.50 in creditstiers $15–129/mo; credits don't roll over
fal.ai — Seedance 2.0 Fast~$0.11cheapest respectable social clip
fal.ai — Kling~$0.35pay-per-second, no minimums
fal.ai — Veo 3.1 Fast~$0.50 (720p)4K tier ~3×
RunComfy machines$0.99–9.59/hr + Pro $20/mocustom ComfyUI workflows; cold-start overhead makes single clips uneconomic
Comfy Cloud$20/mo ≈ 180 GPU-minofficial ComfyUI cloud, credit-based
ComfyDeploy—defunct; stack was open-sourced, managed service gone

Recompute before deciding: prices move quarterly. The structure (subscription vs per-use vs machine-rental) is what stays stable.

Graduation triggers

  • To fal.ai: monthly credit top-ups exceed ~$20 two months running, or you need one premium model your subscription lacks.
  • To cloud ComfyUI: you need the same character across 10+ videos via LoRA, or a ControlNet/IPAdapter/motion-control chain no API engine exposes, or 100+ clips/month of one repeatable workflow where machine-hours beat per-clip pricing.
  • Back down: if a rented workflow runs less than monthly, cancel the machine and take the per-use price. Idle infrastructure is the most expensive engine.

What not to do

  • Don't install vendor API-wrapper skill packs for engines you don't pay for — every one of them is lock-in to that vendor's endpoint with no portable workflow definition.
  • Don't run modern video models on integrated GPUs (see rule 4 above).
  • Don't hold two overlapping subscriptions to hedge; pick one default and use per-use APIs as the hedge.

Credits

The single-dispatcher/model-leaf routing pattern used by video-gen is adapted from the router design in agentspace-so's RunComfy skill pack — pattern absorbed, dependency skipped.

Disclosure: the author is a Higgsfield Ambassador, and Higgsfield links on frankx.ai may be affiliate links. The routing logic here does not depend on that relationship: the decision tree sends you to fal.ai or ComfyUI whenever those genuinely win.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.