comfyui-dispatcher

Routes image-generation requests between fal.ai and local ComfyUI based on cost and latency.

1|Updated Feb 6, 2026

Search Tags:#automation #routing #image generation #dispatch #cost optimization #fal.ai #comfyui

Ready to run

npx skills add https://github.com/williamsforeal/Cyclone-SS --skill comfyui-dispatcher

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: comfyui-dispatcher
Source: https://github.com/williamsforeal/Cyclone-SS/tree/main/global-skills/_deferred/comfyui-dispatcher
Command: npx skills add https://github.com/williamsforeal/Cyclone-SS --skill comfyui-dispatcher

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Scheduling image-generation requests across both cloud compute (fal.ai) and a local ComfyUI GPU setup is difficult to do cost-effectively and reliably.

Core Features & Use Cases

GPU vs cloud routing: Decide whether to run a job locally or send it to fal.ai based on a “use local GPU / run ComfyUI / batch >50 -> local / cost-sensitive single shots -> cloud” policy.
Batch-aware dispatch: Use job size thresholds to optimize throughput and cost.
Operational guardrails: Acknowledge this skill is currently a stub and document how the finished implementation should behave before it is promoted.

Quick Start

Ask the assistant to review the canonical detail card and build checklist for comfyui-dispatcher, then produce the full non-stub SKILL.md implementation.

Frequently Asked Questions about comfyui-dispatcher

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I route image generation requests between a local ComfyUI GPU and fal.ai cloud?▼

You can route image generation requests by using a dispatcher policy that evaluates job size thresholds and cost sensitivity to send batch workloads to a local ComfyUI GPU and single shots to fal.ai.

How does batch-aware dispatch optimize cost and latency for image generation?▼

Batch-aware dispatch optimizes cost and latency by applying job size thresholds, such as routing batch runs larger than 50 images to a local ComfyUI GPU to maximize throughput and minimize cloud compute expenses.

What environment variables and dependencies do I need to automate image generation routing?▼

To automate image generation routing, you need to configure required environment variables and dependencies that establish authenticated connections to both your local ComfyUI instance and the fal.ai cloud service.

Can I use this dispatcher for mixed workloads with both cost-sensitive single shots and local GPU batches?▼

Yes, you can use this dispatcher for mixed workloads because it evaluates request policies to send cost-sensitive single shots to the cloud while directing larger ComfyUI batch runs to the local GPU.

What are the limitations of using a stub implementation for ComfyUI image job routing?▼

The limitation of this stub implementation is that it currently provides only trigger-to-routing logic and documentation, requiring you to build the full non-stub execution paths before promoting it to production.