GPT-Image-2 — text-to-image generation and editing via inference.sh (short listing)
💳 Paid API — short listing (license not verifiable): generate and edit images with OpenAI GPT-Image-2 through the inference.sh belt CLI — text-to-image, reference-based editing, mask inpainting, batch generation up to 10 images
- What
- 💳 Paid API — short listing (license not verifiable): generate and edit images with OpenAI GPT-Image-2 through the inference.sh belt CLI — text-to-image, reference-based editing, mask inpainting, batch generation up to 10 images
- Cost
- Free
- Needs
- an inference.sh account with billing enabled (image generation is billed per image: ~$0.006 low / $0.024 medium / $0.21 high quality); the belt CLI installed (see the repo's cli-install.md)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Selected by Skill Harbor — short listing (the discovery manifest carries no verifiable license for this skill — the manifest makes faith, so no content is reproduced): 💳 Paid inference required — image generation is billed per image (~$0.006 low / $0.024 medium / $0.21 high quality; larger resolutions cost more), via an inference.sh account. @halt-catch-fire's gpt-image skill teaches the agent to generate and edit images with OpenAI GPT-Image-2 through the inference.sh belt CLI: text-to-image, image editing with reference images, mask-based inpainting, multi-image reference composition, batch generation (up to 10 images), custom resolutions (256–4096px), and PNG/JPEG/WebP output — with parameter tables, example commands for product mockups and marketing visuals, and links to sibling skills (FLUX models, full platform CLI). Honest caveats: license terms not verifiable — short listing with a link only, nothing copied; requires installing the belt CLI and an inference.sh account with billing; generated content is subject to OpenAI's usage policies; follow the source link and read the terms yourself before use. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: an inference.sh account with billing enabled (image generation is billed per image: ~$0.006 low / $0.024 medium / $0.21 high quality); the belt CLI installed (see the repo's cli-install.md) Install "GPT-Image-2 — text-to-image generation and editing via inference.sh (short listing)" for me. It gives my agent @halt-catch-fire's GPT-Image-2 workflow: run text-to-image, reference-based image editing, mask-based inpainting, multi-image reference composition, and batch generation (up to 10 images) through the belt CLI — with parameters for quality, resolution (256–4096px), and output format (png/jpeg/webp). IMPORTANT: the license terms were not verifiable (the discovery manifest records no license) — fetch from the link only, reproduce nothing beyond the link, and read the terms yourself before use. Repository: https://github.com/halt-catch-fire/mutiny/blob/main/tools/image/gpt-image/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code — my inference.sh credentials must never be pasted here. Verify that holds; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "gpt-image". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install the belt CLI, run belt login, confirm per-image pricing for the quality level I want). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.