ComfyUI

In plain words: Engine: ComfyUI

Designed 4 min read 7 glossary terms 9 connected pages
The short version written for the Snayu team

Design for running ComfyUI as a local graph engine for image, video and audio work, where each admitted preset pins the exact graph, nodes, models and allowed parameters.

Why read it: Read this before working on image/video generation or the Workbench Comfy probe.
  1. 1Arbitrary caller graphs, cloud nodes and runtime downloads stay closed; only admitted presets run.
  2. 2A local model and a hosted API with the same name are different routes unless proven equal.
  3. 3A separate Workbench engineering probe exists, but only with mock transport evidence.

Designed No native ComfyUI adapter or visual output path is delivered.

Words on this page, decoded click one for its card

The original text Underlined words open their plain-English card.

Choose a bounded workflow before admitting ComfyUI. Its graph and dependency closure must describe exactly what may execute, which parameters may vary, and how results return to their owners. ComfyUI is a graph execution engine; a local service can become a SoulstoneLocal Model when LychD owns its container, queue, readiness, GPU placement, model mounts, and lifecycle. Several semantic owners may use that engine.

This native adapter is a Designed candidate. No native ServiceJob adapter or admitted visual byte path is delivered; State of Work owns delivery status. The separate Workbench engineering probe exercises classic-server submission/reconciliation and bounded retrieval outside native admission. Its mock-transport evidence does not prove a running server, model closure, generation or semantic acceptance. State owns that subset.

Keep model, engine, and road apart

Begin with the operation and the owner that will judge its result. That domain's immutable semantic profile pins request and result schemas, model or voice identity, languages, formats, license, limits, and bake evidence. Each engine or provider implementation then pins this exact semantic revision together with its dialect, runtime, placement, and evidence.

This comparison must reach beyond a familiar model name. Local open-weight MiniMax Music and the hosted MiniMax API remain different routes unless exact model, protocol, and evidence establish equivalence. The engine and semantic-owner map explains the shared division of responsibility.

The preset is the complete program you are admitting: immutable editor/API graph, node and custom-node closure, model files, permitted parameter openings, output mapping and paths, network behavior, container revision, and licenses. Assimilation must admit that program before execution. A caller can then choose the preset and its permitted parameters. Arbitrary caller graphs, partner/cloud nodes, runtime downloads, and ambient custom-node installation remain closed.

The SoulstoneLocal Model RuneService Config File pins the local container, endpoint, devices, mounts, lifecycle, resources, and admitted profile/preset references. A PortalCloud Model requires separate admission of provider, endpoint, dialect, credentials, custody, cost, and reconciliation. A local pack name proves no remote equivalence.

Scroll placement pins the semantic SpellStep request, result, authority, recovery, and finish. Its Resolution Lock pins the chosen exact local SoulstoneLocal Model or PortalCloud Model implementation. Comfy editor state is not a ScrollWorkflow Version.

Pin the dialect and execution lifecycle

The official external Comfy API v2 is exposed by cloud and serverless services. Self-hosting that v2 API currently requires a separately pinned comfy-api-proxy alongside ordinary ComfyUI; its default loopback arrangement connects proxy port 8189 to ComfyUI port 8188. A deployment choosing that dialect therefore pins both services. The classic server, including /prompt, /history, /queue, /interrupt, and WebSocket communication, remains a distinct dialect.

Before relying on job recovery, pin the chosen route's authentication, retention, and restart behavior. The v2 submission contract uses a single-use Idempotency-Key: a duplicate is rejected, rather than returning the previous response. The self-hosted proxy needs persistent --state-dir storage for its own records, which does not preserve ComfyUI queue/history or output bytes after restart. If submission is ambiguous, look it up before deciding recovery. Blind retry is inadmissible: it cannot resolve the missing account.

An admitted adapter must supply upload, submit, queue, progress, history, output, interruption, cancellation-request, and reconciliation facts. Core alone owns ServiceJobAttempt@1; the domain job links that attempt. LychD retains authority, custody, retry law, and canonical provenance. Filenames and PNG metadata may support evidence, but cannot serve as durable identity.

Measure each admitted profile

GPU placement belongs to an exact profile and instance. Separate comfy-qwen and comfy-ltx instances may use separate GPUs. An experimental multi-GPU instance requires explicit device nodes and a measured profile. Neither arrangement implies parallelism, pooled VRAM, residency, or batching.

Candidate profiles begin with Qwen image/edit, LTX-2.5 or Wan video, and MiniMax Music 3. Exact speech, role-qualified sound, and Form profiles follow. Each must independently prove inputs and outputs, languages, limits, cancellation, VRAM and offload behavior, licenses, and artifact validation. Evidence for one profile does not admit another.

Preserve compound results through handoff

For native synchronized video and sound, the exact PrismVision & Media VideoJob@2 receives provider identity, the compound container digest, child streams, shared timebase, and engine facts. Sound is enabled only after MediaFacetAuthoritySet@1 declares every requested role, the consuming CompositionApp identity and revision, and the owner-request digest. Follow PrismVision & Media's compound-facet admission for detailed sound preflight and inseparable-facet behavior.

PrismVision & Media links the Core attempt; Reliquary owns custody and provenance. Each requested facet needs its consuming owner's independent SemanticFacetAdmissionReceipt@1 under the linked Video contract. Unexpected sound is quarantined or deleted rather than assigned a guessed owner.

Broadcast alone judges the final editorial audiovisual relation. Engine completion supplies execution facts; passage to an application still requires the exact profile's artifact validation, preserved custody and provenance, and each requested facet's independent semantic admission.