fal-recipes

v2026.09.24

Use-case-driven multi-step pipelines on fal.ai. Trigger when the user asks for a specific kind of content production rather than a single endpoint call: "make a commercial", "ad creative", "product photography", "cinematic shot", "film look", "character design", "consistent character", "anchor system", "storyboard", "multi-shot", "narrative video", "talking head", "lip sync", "make this person talk", "virtual try-on", "garment transfer", "restore image", "deblur", "denoise", "fix face", "old photo restore", "add audio to video", "video sound effects", "product shot", "photoreal", "realistic photo", "candid photo", "editorial portrait", "documentary photo", "looks like a real photograph", "iPhone-style photo", "film photo", "archival photo". Each recipe describes inputs, the genmedia call sequence, and quality checks.

GitHub
安装命令
npx skhub add fal-ai-community/fal-recipes
Markdown
SKILL.md

fal.ai Recipes

Runtime: All endpoint calls run via the genmedia CLI. See the genmedia skill for command syntax; run genmedia init once if not yet installed.

A recipe is a use-case-driven pipeline. It tells you the inputs to collect, the genmedia calls to chain, and the quality bar to verify before returning.

Recipes use genmedia for execution and fal-models-catalog for endpoint defaults. They differ from fal-workflow:

  • fal-workflow = how to build a pipeline (JSON authoring or CLI orchestration patterns), generic
  • fal-recipes = how to produce a specific kind of content, opinionated by use case

Available recipes

ReferenceUse for
cinematography.mdCinematic stills and video, shot language, lighting, lens, color grade
character-design.mdOriginal characters with consistent identity across shots
commercial.mdProduct photography, ads, e-commerce batches, hero shots
storytelling.mdMulti-shot narratives, short films, ads, brand films, social stories
character-lipsync.mdTalking head / lip-sync video (TTS → animated portrait)
image-restoration.mdSmart-dispatch restoration, deblur, denoise, dehaze, fix faces, document restore
virtual-tryon.mdApply a garment onto a person photo (with optional cleanup chain)
video-with-audio.mdAdd narration / SFX / music to a silent video
product-shot.mdHero product photography from a packshot reference
realism.mdPhotoreal stills (candid, editorial, documentary, archival, food, nature, architectural) with an anti-AI-look checklist

How to choose a recipe

  1. Match the user's intent to a use case in the table above.
  2. If multiple recipes apply (e.g., "commercial featuring a consistent character"), load both and run the dominant one, usually the more specific one (character-design first, then commercial framing).
  3. If no recipe matches but the task is multi-step, fall back to fal-workflow Mode B (CLI orchestration) and design the pipeline from scratch.
  4. If the task is a single endpoint call, skip recipes, go directly to the right fal-models-catalog reference.

Universal recipe structure

Every reference follows the same skeleton so the agent knows where to look:

  1. Inputs to collect: only what changes the pipeline.
  2. Genmedia workflow: endpoint discovery, schema inspection, upload, run, status, download.
  3. Prompt build order: domain-specific structure (e.g., SCLCAM for cinema, anchor + variable for character).
  4. Patterns / examples: concrete prompt templates and finished examples.
  5. Quality bar: explicit checks before returning.

Cross-references

Information lives in one place. If a recipe needs an endpoint listed in the catalog, it links to the catalog instead of duplicating the list.

发现
标签

此技能尚未发布标签。

版本
最新版本元数据

版本

v2026.09.24

发布时间

2026年9月24日

分类

未分类

许可证

未指定

源路径

skills/fal-recipes

默认分支

main

最新提交

9ca8504

Tree SHA

de24add