메뉴
This skill should be used when the user asks to "generate images", "generate images with ComfyUI", "use local ComfyUI", "use remote ComfyUI", "use Z-Image", "add an image generation provider", or needs image-generation endpoint setup through local or HivemindOS Tailscale routes.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when generating images with Flux.2 on Apple Silicon, working with MLX Swift, implementing text-to-image/image-to-image pipelines, LoRA training, or quantized model inference in Swift.
Use this skill whenever adding, wiring, surfacing, or debugging a new node in an existing ComfyUI Mobile workflow JSON, especially when the user says a node is missing from a workflow they already use. It prevents the common failure mode where the saved workflow file is changed correctly but ComfyUI Mobile still renders an older persisted/open workflow, hides the node as static, or fails to expose custom-node widgets.
Operate the agent-first Hivemind Content Studio for durable first-frame animation ads, stickman ads, static text ads, faceless shorts, clipping, local or cloud media generation, exact voice, assembly, semantic evaluation, approval-gated social posting, experiments, and monetization metrics. Use when an agent must create, resume, inspect, evaluate, publish, or optimize social content through the unified repo rather than invoking Auto Clipper, AI Animation Factory, MoneyPrinterTurbo, MUAPI, Higgsfield, Media Studio, Postiz, or Upload-Post as overlapping standalone pipelines.
Use when setting up or operating AI animation content factories that turn briefs into scripts, frame prompts, motion prompts, voice lines, music briefs, and publishing metadata across tools such as Claude/OpenAI, Midjourney, Runway, ElevenLabs, Suno, Make, and YouTube.
Use the local unpaid Auto Clipper control plane to ingest public creator research URLs, render Podcli clip candidates, require human approval, and schedule only approved clips through self-hosted Postiz.
Generate images/videos/3D assets/audio via Higgsfield AI. Defaults: GPT Image 2 for image/design/text, Seedance 2.0 for video, Nano Banana 2/Pro for character/reference images, Marketing Studio for ads, Sonilo/Mirelo for audio, plus Soul models and Kling 3.0. Use when: "generate an image", "make a video", "animate this photo", "image-to-video", "edit/stylize/remix this image", "produce a clip", "reframe this video", "edit this video from a sketch", "create a 3D model", "make a GLB/mesh", "create a sound effect", "make music", "text-to-audio", "create an ad", "make a UGC video", "product demo", "unboxing", "brand video", "presenter video", "import product from URL", "create avatar for ad", or "analyze video virality". Supports image-to-image, image-to-video, image-to-3D (`multi_image_to_3d`), text-to-audio (`mirelo_text_to_audio`), text-to-music (`sonilo_music`), workflow generation (`draw_to_video`, `reframe`), references, job/upload IDs, Marketing Studio, and Virality Predictor (`brain_activity`). Supports t
| name | comfyui-image-generation |
| description | This skill should be used when the user asks to "generate images", "generate images with ComfyUI", "use local ComfyUI", "use remote ComfyUI", "use Z-Image", "add an image generation provider", or needs image-generation endpoint setup through local or HivemindOS Tailscale routes. |
| version | 0.1.0 |
Generate images through ComfyUI-style local or remote services. Keep image providers in this skill as blocks so agents can compare local and Tailnet routes without scattering image-generation instructions across separate skills.
Use one of two modes:
Do not require Tailnet clients to have ComfyUI installed locally. Do not use client-local 127.0.0.1 for a remote generator.
Use this block when documenting a remote ComfyUI/Z-Image/Flux/SD image endpoint available through Tailscale.
Client route
https://<magicdns-or-tailnet-ip>:<https-port> or http://<magicdns-or-tailnet-ip>:<http-port>http://<magicdns-or-tailnet-ip>:<http-port>127.0.0.1 from the client unless the client is also the service host.Tailnet client preflight
curl -kfsS -I --max-time 8 https://<tailnet-host>:<https-port>/ || true
curl -fsS -I --max-time 8 http://<tailnet-host>:<http-port>/ || true
If both fail, diagnose Tailnet reachability or the remote image-generation service. Do not fall back to local ComfyUI paths on the client.
Service-host facts to fill in
<machine-name><launchctl/systemd/docker/manual><command>http://127.0.0.1:<port>http://127.0.0.1:<port><path><model or workflow name><cuda/mps/cpu/ram/vram constraints>Browser generation flow
API generation flow
Inspect the wrapper's documented API shape before guessing endpoint names. Prefer wrapper APIs that redact prompt history and preserve output privacy. Avoid raw ComfyUI /queue and /history unless the user explicitly authorizes plaintext prompt inspection.
Use this block when the current machine runs the image generator.
Local preflight
curl -fsS --max-time 5 http://127.0.0.1:<comfy-port>/system_stats
curl -fsS -I --max-time 5 http://127.0.0.1:<ui-port>/ || true
lsof -nP -iTCP:<comfy-port> -sTCP:LISTEN || true
Local generation notes
file or a browser/image preview before returning them.Use this block as a starting point for a Z-Image-backed ComfyUI wrapper.
Recommended shape
https://<z-image-host>.<tailnet-name>.ts.net:<port> or https://<tailnet-ip>:<port>http://<tailnet-host>:<port>flash-attn.Service-host diagnostics only
<stack-command> status
curl -fsS --max-time 5 http://127.0.0.1:<comfy-port>/system_stats
curl -fsS --max-time 5 http://127.0.0.1:<wrapper-port>/health
curl -fsS -I --max-time 5 http://127.0.0.1:<ui-port>/