# Media Workflow > Chain several `vg generate` steps into one production — ads, product shots, restorations, talking heads, try-ons, scored or subtitled video — when no single endpoint does the job. - Skill: `kyh/media-workflow` (Agent Skill, multi-file: 15 files) - Install (CLI): `npx skillmds@latest add kyh/media-workflow` - Raw SKILL.md: https://api.skillmd.com/api/skills/kyh/media-workflow/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Productivity - Author: kyh (https://skillmd.com/u/kyh) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/kyh/media-workflow --- # `vg generate` workflow production > **Runtime:** All endpoint calls use the `vg generate` CLI (`npm install -g vibedgames`, or `pnpm dogfood` in this repo). The API key lives on the vibedgames server, so there is no per-machine setup. See the `generate` skill for the command reference. Use this skill when a single model call is not enough. There are two ways in: - **Use-case recipe** — your task matches a known kind of content production (commercial, character, lip-sync, restoration…). Start from the recipe table below; each recipe lists inputs, the `vg generate` call sequence, and a quality bar. - **Custom pipeline** — no recipe matches. Design the workflow from scratch using the orchestration patterns in this skill. A workflow either way is a planned sequence of vg generate calls with clear inputs, outputs, dependencies, and quality checks. ## Use-case recipes Match the user's intent to a recipe, then load that reference. If two apply (e.g. "commercial featuring a consistent character"), load both and run the more specific one first. If the task is a single endpoint call, skip recipes and go straight to the right `model-catalog` reference. | Reference | Use for | | ------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | | [cinematography.md](references/cinematography.md) | Cinematic stills and video, shot language, lighting, lens, color grade | | [character-design.md](references/character-design.md) | Original characters with consistent identity across shots | | [commercial.md](references/commercial.md) | Product photography, ads, e-commerce batches, hero shots | | [storytelling.md](references/storytelling.md) | Multi-shot narratives, short films, ads, brand films, social stories | | [character-lipsync.md](references/character-lipsync.md) | Talking head / lip-sync video (TTS → animated portrait) | | [image-restoration.md](references/image-restoration.md) | Smart-dispatch restoration, deblur, denoise, dehaze, fix faces, document restore | | [virtual-tryon.md](references/virtual-tryon.md) | Apply a garment onto a person photo (with optional cleanup chain) | | [video-with-audio.md](references/video-with-audio.md) | Add narration / SFX / music to a silent video | | [product-shot.md](references/product-shot.md) | Hero product photography from a packshot reference | | [realism.md](references/realism.md) | Photoreal stills (candid, editorial, documentary, archival, food, nature, architectural) with an anti-AI-look checklist | Each recipe links to `model-catalog` for endpoint defaults rather than listing models inline, so the catalog stays the single source of truth. 3D assets have no recipe here — they are routed by `model-catalog` (text-to-3d / image-to-3d): rigged characters → `regenerate-3d`; rigged or openable props as procedural code → `image-to-threejs`. ## Custom pipelines Load these references as needed: - `references/pipeline-patterns.md` - `references/node-rules.md` - `references/utility-endpoints.md` - `references/recipes.md` — generic workflow recipes (multi-scene video, dataset, social batch…) - `model-catalog` for creative model defaults Use `model-catalog` for default creative model choices. Still inspect schemas, check pricing when cost matters, and use exact endpoint fields. ## Inputs to collect Ask only for missing information that changes the pipeline: - Final deliverable: image set, video, clips, audio, subtitles, dataset, social batch, product campaign, storyboard, style exploration. - Source assets: product images, character references, first frames, video, audio, logo, transcript, brand guide. - Runtime limits: quality target, cost sensitivity, number of variants, duration, aspect ratios, deadline. - Continuity requirements: product identity, character face, scene layout, voice, color grade. - Model preference: ask the user only when quality, speed, cost, or audio tradeoffs are not clear from the brief. ## Core workflow 1. Write a short pipeline graph before running anything. ```text input assets -> planner -> generation nodes -> utility nodes -> QA -> final outputs ``` 2. Resolve endpoints for each role. Check known endpoint IDs first. ```bash vg generate models --endpoint_id openai/gpt-image-2 --json vg generate models --endpoint_id fal-ai/nano-banana-pro/edit --json vg generate models --endpoint_id bytedance/seedance-2.0/image-to-video --json vg generate models --endpoint_id xai/grok-imagine-video/image-to-video --json vg generate models --endpoint_id veed/fabric-1.0 --json ``` Use text search only as fallback discovery for roles not covered by `model-catalog` or the utility reference: ```bash vg generate models "image generation product photography" --json vg generate models "image editing reference preservation" --json vg generate models "image to video" --json vg generate models "subtitle video utility" --json vg generate docs "workflow utility endpoints" --json ``` 3. Inspect every endpoint before use. ```bash vg generate schema --json vg generate pricing --json ``` 4. Upload local files once and reuse returned URLs. ```bash vg generate upload ./input.png --json vg generate upload ./voiceover.wav --json ``` 5. Run each node with JSON output. Use async for slow generation. ```bash vg generate run -- "" --json vg generate run -- "" --async --json vg generate status --download "./outputs/workflow/{request_id}_{index}.{ext}" --json ``` 6. For downstream nodes, pass the media URL from the previous `result` when it is available. If you only have a local file path, upload it first. 7. Download final assets with templates that cannot collide. ```bash --download "./outputs/workflow/{request_id}_{index}.{ext}" ``` 8. Return a compact manifest. ```json { "goal": "short deliverable description", "nodes": [ { "id": "shot_01", "role": "image_to_video", "endpoint_id": "...", "request_id": "...", "input_urls": ["..."], "output_urls": ["..."], "downloaded_files": ["..."], "notes": "continuity or defect notes" } ], "final_files": ["..."] } ``` ## Pipeline rules - Keep one node responsible for one clear transformation. - Fan out independent generation, crop, upscale, subtitle, or variation nodes. - Keep sequential chains only when node B needs node A output. - For consistency, prefer reference/edit or image-to-video over independent text-only generations. - For default creative model choices, follow `model-catalog` unless the user names a model. - Use utility endpoints for deterministic work: crop, resize, grid, composite, audio merge, subtitle, speed change, compression. - Record endpoint, schema-relevant parameters, request ID, and output path for every node. - If a 422 error occurs, read `validation_errors`, inspect schema again, then fix the exact field. ## Quality gate Before returning, verify: - The pipeline graph matches the requested deliverable. - No generation model was chosen from memory alone. - All local source files were uploaded before use. - Final files were saved through `--download`. - Utility endpoints used exact schema fields. - Continuity anchors were repeated where identity or product fidelity matters. - Each node output is either accepted, retried, or marked with a defect. If the workflow becomes too complex, stop expanding and ask the user to choose between faster iteration, higher fidelity, or broader variation.