comfyui-gateway（comfyui 网关）

ComfyUI Gateway

Overview

REST API gateway for ComfyUI servers. Workflow management, job queuing, webhooks, caching, auth, rate limiting, and image delivery (URL + base64).

When to Use This Skill

• When the user mentions "comfyui" or related topics
• When the user mentions "comfy ui" or related topics
• When the user mentions "stable diffusion api gateway" or related topics
• When the user mentions "gateway comfyui" or related topics
• When the user mentions "api gateway imagens" or related topics
• When the user mentions "queue imagens" or related topics

Do Not Use This Skill When

• The task is unrelated to comfyui gateway
• A simpler, more specific tool can handle the request
• The user needs general-purpose assistance without domain expertise

How It Works

A production-grade REST API gateway that transforms any ComfyUI server into a universal, secure, and scalable service. Supports workflow templates with placeholders, job queuing with priorities, webhook callbacks, result caching, and multiple storage backends.

Architecture Overview

┌─────────────┐     ┌──────────────────────────────────┐     ┌──────────┐
│   Clients    │────▶│        ComfyUI Gateway           │────▶│ ComfyUI  │
│ (curl, n8n,  │     │                                  │     │ Server   │
│  Claude,     │     │  ┌─────────┐  ┌──────────────┐  │     │ (local/  │
│  Lovable,    │     │  │ Fastify │  │ BullMQ Queue │  │     │  remote) │
│  Supabase)   │     │  │ API     │──│ (or in-mem)  │  │     └──────────┘
│              │◀────│  └─────────┘  └──────────────┘  │
│              │     │  ┌─────────┐  ┌──────────────┐  │     ┌──────────┐
│              │     │  │ Auth +  │  │ Storage      │  │────▶│ S3/MinIO │
│              │     │  │ RateL.  │  │ (local/S3)   │  │     │(optional)│
│              │     │  └─────────┘  └──────────────┘  │     └──────────┘
└─────────────┘     └──────────────────────────────────┘

Components

Quick Start

## 1. Install

cd comfyui-gateway
npm install

## 2. Configure

cp .env.example .env

## 3. Initialize

npx tsx src/cli/index.ts init

## 4. Add A Workflow

npx tsx src/cli/index.ts add-workflow ./workflows/sdxl_realism_v1.json \
  --id sdxl_realism_v1 --schema ./workflows/sdxl_realism_v1.schema.json

## 5. Start (Api + Worker In One Process)

npm run dev

## Or Separately:

npm run start:api   # API only
npm run start:worker # Worker only

Environment Variables

All configuration is via .env — nothing is hardcoded:

Health & Capabilities

GET /health
→ { ok: true, version, comfyui: { reachable, url, models? }, uptime }

GET /capabilities
→ { workflows: [...], maxSize, maxBatch, formats, storageProvider }

Workflows (Crud)

GET    /workflows            → list all workflows
POST   /workflows            → register new workflow
GET    /workflows/:id        → workflow details + input schema
PUT    /workflows/:id        → update workflow
DELETE /workflows/:id        → remove workflow

Jobs

POST   /jobs                 → create job (returns jobId immediately)
GET    /jobs/:jobId          → status + progress + outputs
GET    /jobs/:jobId/logs     → sanitized execution logs
POST   /jobs/:jobId/cancel   → request cancellation
GET    /jobs                 → list jobs (filters: status, workflowId, after, before, limit)

Outputs

GET    /outputs/:jobId       → list output files + metadata
GET    /outputs/:jobId/:file → download/stream file

Job Lifecycle

queued → running → succeeded
                 → failed
                 → canceled

1. Client POSTs to /jobs with workflowId + inputs
2. Gateway validates, checks cache, checks idempotency
3. If cache hit → returns existing outputs immediately (status: cache_hit)
4. Otherwise → enqueues job, returns jobId + pollUrl
5. Worker picks up job, renders workflow template, submits to ComfyUI
6. Worker polls ComfyUI for progress (or listens via WebSocket)
7. On completion → downloads outputs, stores them, updates DB
8. If callbackUrl → sends signed webhook POST
9. Client polls /jobs/:jobId or receives webhook

Workflow Templates

Workflows are ComfyUI JSON with {{placeholder}} tokens. The gateway resolves these at runtime using the job's inputs and params:

{
  "3": {
    "class_type": "KSampler",
    "inputs": {
      "seed": "{{seed}}",
      "steps": "{{steps}}",
      "cfg": "{{cfg}}",
      "sampler_name": "{{sampler}}",
      "scheduler": "normal",
      "denoise": 1,
      "model": ["4", 0],
      "positive": ["6", 0],
      "negative": ["7", 0],
      "latent_image": ["5", 0]
    }
  },
  "6": {
    "class_type": "CLIPTextEncode",
    "inputs": {
      "text": "{{prompt}}",
      "clip": ["4", 1]
    }
  }
}

Each workflow has an inputSchema (Zod) that validates what the client sends.

Security Model

• API Keys: X-API-Key header; keys configured via API_KEYS env var as key1:admin,key2:user
• JWT: Optional; when JWT_SECRET is set, accepts Authorization: Bearer <token>
• Roles: admin (full CRUD on workflows + jobs), user (create jobs, read own jobs)
• Rate Limiting: Per key + per IP, configurable window and max
• Webhook Security: HMAC-SHA256 signature in X-Signature header
• Callback Allowlist: Only approved domains receive webhooks
• Privacy Mode: When enabled, prompts are redacted from logs and DB
• Idempotency: metadata.requestId prevents duplicate processing
• CORS: Configurable allowed origins
• Input Validation: Zod schemas on every endpoint; max size/batch enforced

Comfyui Integration

The gateway communicates with ComfyUI via its native HTTP API:

The client auto-detects ComfyUI version and adapts:

• Tries WebSocket first for progress, falls back to polling
• Handles both /history response formats
• Detects OOM errors and classifies them with recommendations

Cache Strategy

Cache key = SHA-256 of workflowId + sorted(inputs) + sorted(params) + checkpoint. On cache hit, the gateway returns a "virtual" job with pre-existing outputs — no GPU computation needed. Cache is stored alongside job data in the DB with configurable TTL.

Error Classification

Bundled Workflows

Three production-ready workflow templates are included:

1. Sdxl_Realism_V1 — Photorealistic Generation

• Checkpoint: SDXL base
• Optimized for: Portraits, landscapes, product shots
• Default: 1024x1024, 30 steps, cfg 7.0

2. Sprite_Transparent_Bg — Game Sprites With Alpha

• Checkpoint: SD 1.5 or SDXL
• Optimized for: 2D game assets, transparent backgrounds
• Default: 512x512, 25 steps, cfg 7.5

3. Icon_512 — App Icons With Optional Upscale

• Checkpoint: SDXL base
• Optimized for: Square icons, clean edges
• Default: 512x512, 20 steps, cfg 6.0, optional 2x upscale

Observability

• Structured Logs: Pino JSON logs with correlationId on every request
• Metrics: Jobs queued/running/succeeded/failed, avg processing time, cache hit rate
• Audit Log: Admin actions (workflow CRUD, key management) logged with timestamp + actor

Cli Reference

npx tsx src/cli/index.ts init                    # Create dirs, .env.example
npx tsx src/cli/index.ts add-workflow <file>      # Register workflow template
  --id <id> --name <name> --schema <schema.json>
npx tsx src/cli/index.ts list-workflows           # Show registered workflows
npx tsx src/cli/index.ts run                      # Start API server
npx tsx src/cli/index.ts worker                   # Start job worker
npx tsx src/cli/index.ts health                   # Check ComfyUI connectivity

Troubleshooting

Read references/troubleshooting.md for detailed guidance on:

• ComfyUI not reachable (firewall, wrong port, Docker networking)
• OOM errors (reduce resolution, batch, or steps)
• Slow generation (GPU utilization, queue depth, model loading)
• Webhook failures (DNS, SSL, timeout, domain allowlist)
• Redis connection issues (fallback to in-memory)
• Storage permission errors (local path, S3 credentials)

Integration Examples

Read references/integration.md for ready-to-use examples with:

• curl commands for every endpoint
• n8n webhook workflow
• Supabase Edge Function caller
• Claude Code / Claude.ai integration
• Python requests client
• JavaScript fetch client

File Structure

comfyui-gateway/
├── SKILL.md
├── package.json
├── tsconfig.json
├── .env.example
├── src/
│   ├── api/
│   │   ├── server.ts          # Fastify setup + plugins
│   │   ├── routes/
│   │   │   ├── health.ts      # GET /health, /capabilities
│   │   │   ├── workflows.ts   # CRUD /workflows
│   │   │   ├── jobs.ts        # CRUD /jobs
│   │   │   └── outputs.ts     # GET /outputs
│   │   ├── middleware/
│   │   │   └── error-handler.ts
│   │   └── plugins/
│   │       ├── auth.ts        # API key + JWT
│   │       ├── rate-limit.ts
│   │       └── cors.ts
│   ├── worker/
│   │   └── processor.ts       # Job processor
│   ├── comfyui/
│   │   └── client.ts          # ComfyUI HTTP + WS client
│   ├── storage/
│   │   ├── index.ts           # Provider factory
│   │   ├── local.ts           # Local filesystem
│   │   └── s3.ts              # S3-compatible
│   ├── workflows/
│   │   └── manager.ts         # Template CRUD + rendering
│   ├── cache/
│   │   └── index.ts           # Hash-based cache
│   ├── notifications/
│   │   └── webhook.ts         # HMAC-signed callbacks
│   ├── auth/
│   │   └── index.ts           # Key/JWT validation + roles
│   ├── db/
│   │   ├── index.ts           # DB factory (SQLite/Postgres)
│   │   └── migrations.ts      # Schema creation
│   ├── cli/
│   │   └── index.ts           # CLI commands
│   ├── utils/
│   │   ├── config.ts          # Env loading + validation
│   │   ├── errors.ts          # Error classes
│   │   ├── logger.ts          # Pino setup
│   │   └── hash.ts            # SHA-256 hashing
│   └── index.ts               # Main entrypoint
├── config/
│   └── workflows/             # Bundled workflow templates
│       ├── sdxl_realism_v1.json
│       ├── sdxl_realism_v1.schema.json
│       ├── sprite_transparent_bg.json
│       ├── sprite_transparent_bg.schema.json
│       ├── icon_512.json
│       └── icon_512.schema.json
├── data/
│   ├── outputs/               # Generated images
│   ├── workflows/             # User-added wor

## Best Practices

- Provide clear, specific context about your project and requirements
- Review all suggestions before applying them to production code
- Combine with other complementary skills for comprehensive analysis

## Common Pitfalls

- Using this skill for tasks outside its domain expertise
- Applying recommendations without understanding your specific context
- Not providing enough project context for accurate analysis

## Related Skills

- `ai-studio-image` - Complementary skill for enhanced analysis
- `image-studio` - Complementary skill for enhanced analysis
- `stability-ai` - Complementary skill for enhanced analysis

## Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.