Skip to main content
skill CX Codex

gpt-image-v2 — Claude Code skill: what it does, how to install

gpt-image-v2 is a Claude Code skill for creating and editing images through EachLabs with GPT Image v2 models.

no license 169 installs ★ 48 updated 2026-10-07

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add eachlabs/skills --skill gpt-image-v2 -a claude-code
Open on GitHub

What gpt-image-v2 does

The gpt-image-v2 skill sends requests to the EachLabs Predictions API and returns image outputs from gpt-image-v2-text-to-image or gpt-image-v2-edit. One model creates an image from a prompt; the other applies an instruction to an existing image while preserving selected details.

Its flow covers model-schema lookup, prediction creation, and status checks through polling or a webhook. It requires the EACHLABS_API_KEY environment variable. Image inputs must use public HTTPS URLs, so localhost and data URIs cannot be used.

The key is sent in the X-API-Key header. Results come from the output array, while failed requests expose message and details.

What it helps with

  • create an image from a text prompt
  • replace the background of an existing image
  • preserve a product label and camera angle during an edit
  • retrieve a prediction result through polling or a webhook

Example prompts for the agent

  • Create a product poster with exact wording and specified typography through GPT Image v2.
  • Edit product.jpg by replacing its background while keeping the label and camera angle unchanged.
  • Look up the schema for gpt-image-v2-edit, create the prediction, and wait for its webhook result.

How to install gpt-image-v2

1Skills CLI (Vercel)

npx skills add eachlabs/skills --skill gpt-image-v2 -a claude-code

2Manually: put the files in place

~/.claude/skills/gpt-image-v2/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/gpt-image-v2/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about gpt-image-v2

How do I install gpt-image-v2 in Claude Code?

Run npx skills add eachlabs/skills --skill gpt-image-v2 -a claude-code, then open ~/.claude/skills/gpt-image-v2/SKILL.md.

What does gpt-image-v2 do?

The skill creates images from text prompts and edits existing images through the EachLabs Predictions API. It uses gpt-image-v2-text-to-image and gpt-image-v2-edit.

What does gpt-image-v2 need to work?

It needs the EACHLABS_API_KEY environment variable for EachLabs. Image inputs must be public HTTPS URLs; localhost and data URIs are not supported.

Similar skills

All skills for AI and ML →

From the same set102

The whole set →
album-cover-generation The album-cover-generation skill draws album, single and EP artwork with each::sense. Describe the genre and mood, get a cover sized for streaming or a physical release. CX Codex +1 220installs video-speed-adjustment video-speed-adjustment is a Claude Code skill that changes video playback speed through each::sense AI. Invoke it to create slow motion, time-lapse, reverse playback, or speed changes within a clip. CX Codex +1 220installs age-transformation The age-transformation skill uses each::sense to age or de-age a face in a photo, or create an adult-age interpretation of a child. Useful for visual effects and creative work. CX Codex +1 217installs hair-color-changer hair-color-changer — a skill that sends a photo to each::sense AI and returns it with the hair recolored — natural shades, fantasy colors, ombre, highlights. It calls the eachsense/beta model with an image URL and streams the result back. CX Codex +1 216installs face-morphing face-morphing blends facial portraits via external image links, renders gradual video morphs, and predicts family traits through each::sense AI. CX Codex +1 212installs eye-color-changer eye-color-changer modifies eye colors in portrait photos via the each::sense API. Handles realistic recoloring, fantasy shades, and heterochromia. CX Codex +1 206installs bytedance-seedance-2-0 Wraps ByteDance Seedance 2.0 (Fast) on EachLabs: prompt-to-clip or animate a still, with sound produced in the same pass. CX Codex +1 165installs eachlabs-music The eachlabs-music skill connects coding agents to EachLabs Mureka models for songs, lyrics, speech, podcasts, and audio processing. Use it when a project needs generated or analyzed sound. CX Codex +1 1installs

Project sponsors

Companies that keep this analytics open