메뉴
Builds and submits ComfyUI JSON payloads for the Sienna Nomad project using pre-built Python scripts. Do NOT attempt to build payloads manually or read workflow JSON files — always use the scripts.
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
A specialized AI agent that ruthlessly evaluates all marketing assets against world-class standards, ensuring only premium content is approved for final delivery.
A specialized framework for generating high-fidelity prompts optimized for Flux.2 (image) and LTX 2.5 (video). Focuses on materiality, optical physics, temporal dynamics, and cinematic technicality to move beyond "vibe-coded" descriptions.
Automates the transformation of narrative Markdown prompts into technical JSON payloads for Z-Image Turbo ComfyUI workflows. Handles extraction, sanitization against banned terms, and dynamic parameter injection (Resolution/Node Targeting).
Transforms narrative script data into cinematic prompt batches for FLUX/LTX.
Expert-tier prompting protocol for Grok Imagine Video Generation (xAI). Focuses on 'Hollywood sequence' narrative prose, SCENE LOCK consistency, and handheld realism.
High-precision prompting protocol for LTX 2.3 (Lightricks) video generation, optimized for ComfyUI VFX pipelines and local control. Incorporates cinematic prose, camera motion selectors, and the community-standard 3-stage sampling hack.
| name | sienna-nomad-anchor-payload-builder |
| description | Builds and submits ComfyUI JSON payloads for the Sienna Nomad project using pre-built Python scripts. Do NOT attempt to build payloads manually or read workflow JSON files — always use the scripts. |
Never build JSON payloads manually. Never read the workflow JSON into context. Always use the scripts below. They handle all parsing, formatting, and submission.
When: Any time payloads need to be built or rebuilt from .md files.
python3 /Users/zgbot/Desktop/Sienna_Nomad_Project/build_payloads.py
Options:
--rebuild — overwrite all existing payloads (use after .md files change)--dry-run — show what would be built without writing anything--type anchor|photo|video — build only one typeThis script scans the entire project automatically. It handles all 3 prompt formats (standard CINEMATIC CONTEXT, markdown bullets, plain key:value). No batch files needed. Run once, it builds everything.
When: ComfyUI is online and renders are needed. Order: Always run images first, videos separately when LTX workflow is ready.
# Step 1 — anchors + photos (z-image-turbo):
python3 /Users/zgbot/Desktop/Sienna_Nomad_Project/submit_to_comfyui.py --type image
# Step 2 — videos (run later when LTX workflow is configured):
python3 /Users/zgbot/Desktop/Sienna_Nomad_Project/submit_to_comfyui.py --type video
Options:
--resume — skip files whose PNG already exists (safe to re-run after interruption)--dry-run — list files without submitting--port 8188 — restrict to one GPUhttp://localhost:8188http://localhost:8189GET http://localhost:8188/api/system_stats/Users/zgbot/Desktop/Sienna_Nomad_Project/04_Prompt_Library/EP##_Name/ with JSON_PAYLOADS/ subfolder/Users/zgbot/workflows/hermes_z_image_turbo_api.json/Users/zgbot/Desktop/Sienna_Nomad_Project/build_log.txt/Users/zgbot/Desktop/Sienna_Nomad_Project/submit_log.txtpython3 build_payloads.py --rebuild — build all JSONspython3 submit_to_comfyui.py --type image — render all anchors + photos