Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

create-image-gpt-image-fal

Generate a single photoreal or designed image with OpenAI gpt-image-1/gpt-image-2 through fal.ai, with optional reference-image editing.

Image & VideoIntermediate★ 1,226⑂ 211AI score 8/10Last updated: Sep 29, 2026

What it does

  • Wraps fal.ai's OpenAI gpt-image endpoints behind one script, switching model families via --model (gpt-image-1 default, gpt-image-2 for custom sizes).
  • Automatically routes to the /edit variant when one or more public reference URLs are supplied, so character identity carries across angles.
  • Supports custom output dimensions (multiples of 16, up to 3840px) on gpt-image-2 for storyboard sheets and layout-heavy designs.
  • Writes a .meta.json sidecar with model id, request params, gateway, and cost for reproducibility and budget tracking.

Who it's for

  • Teams running AI ad/short-video pipelines that need consistent character anchors and keyframes.
  • Anyone who wants explicit control over fal.ai image cost tiers (low/medium/high).
  • Existing GooseWorks users whose generations must be billed to an agent and project.

Examples

  1. Vertical 9:16 character anchor: --prompt "..." --output anchor.png --aspect-ratio 9:16.
  2. Feed the hosted anchor URL back via --ref-image to produce a three-quarter-left angle keyframe.
  3. --model gpt-image-2 --image-size 1728x2304 --quality high for a designed ad storyboard sheet.

Caveat: the skill explicitly warns that readable text in prompts gets mangled — overlay copy with PIL or ffmpeg drawtext instead.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/gooseworks-ai/goose-skills/HEAD/skills/ads/capabilities/create-image-gpt-image-fal/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/ads/capabilities/create-image-gpt-image-fal folder from the GitHub repo gooseworks-ai/goose-skills into my ~/.claude/skills/create-image-gpt-image-fal/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/gooseworks-ai/goose-skills.git && mkdir -p ~/.claude/skills && cp -r goose-skills/skills/ads/capabilities/create-image-gpt-image-fal ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Clone the repository: git clone https://github.com/gooseworks-ai/goose-skills.git
  2. Copy the skill into Claude's skills folder: mkdir -p ~/.claude/skills && cp -r goose-skills/skills/ads/capabilities/create-image-gpt-image-fal ~/.claude/skills/
  3. Check the Python dependency: python3 -c "import requests" || pip3 install requests
  4. Authenticate with GooseWorks: run gooseworks login to create ~/.gooseworks/credentials.json. Do not set a raw FAL_API_KEY.
  5. Attribute spend to a project: export GW_PROJECT_ID=<your ad project id>
  6. Restart Claude Code and ask, e.g., "generate a 9:16 photoreal character anchor with gpt-image".
View source on GitHub ↗License: MIT