create-image-fal

v2026.09.25

Generate or edit an image via any FAL image model (nano-banana edit, gpt-image, flux, ...), ROUTED THROUGH THE fal-proxy so it bills the Ads agent. image_urls must be public URLs (orchestrator hosts local product refs via MCP upload->presign). The recipe names the model + prompt. Use for keyframes, flat-cover transforms, product hero edits. (For the OpenAI gpt-image family specifically, create-image-gpt-image-fal also exists.)

GitHub
安装命令
npx skhub add gooseworks-ai/create-image-fal
Markdown
SKILL.md

create-image-fal

Generate or edit an image via any FAL image model (nano-banana edit, gpt-image, flux, ...), ROUTED THROUGH THE fal-proxy so it bills the Ads agent. image_urls must be public URLs (orchestrator hosts local product refs via MCP upload->presign). The recipe names the model + prompt. Use for keyframes, flat-cover transforms, product hero edits. (For the OpenAI gpt-image family specifically, create-image-gpt-image-fal also exists.)

Run

gen_image.py --model fal-ai/nano-banana/edit --payload '{...}' --out keyframe.png — bills the agent; returns the *.fal.media URL.

Contract

  • Paid calls route through the GooseWorks proxies (bills the Ads agent) via the bundled media_proxy.py — never a provider SDK's default host.
  • The template recipe (DB) supplies the model + params; this capability is generic.
发现
标签

此技能尚未发布标签。

版本
最新版本元数据

版本

v2026.09.25

发布时间

Sep 25, 2026

分类

未分类

许可证

MIT

源路径

skills/ads/capabilities/create-image-fal

默认分支

main

最新提交

a9f4676

Tree SHA

99d4730