gpt-image
101-skills/superpowers
Generate and edit images with OpenAI's GPT-Image-2 via inference.sh CLI.
What is gpt-image?
This skill provides access to OpenAI's GPT-Image-2 model for text-to-image generation, image editing, and mask-based inpainting. Use it when you need to create product mockups, marketing visuals, concept art, or perform photo manipulation tasks.
- Generate images from text prompts with customizable quality levels
- Edit existing images using reference images and text prompts
- Perform mask-based inpainting to replace specific regions in images
- Generate multiple variations (up to 10) in a single batch
- Support flexible output resolutions from 256–4096px in 32px increments
- Output in PNG, JPEG, or WebP formats with compression options
How to install gpt-image
npx skills add https://github.com/101-skills/superpowers --skill gpt-image- Install the belt CLI skill: npx skills add belt-sh/cli
- Run belt login to authenticate with inference.sh
- Have an active inference.sh account with API access
How to use gpt-image
- 1.Run 'belt login' to authenticate with your inference.sh account
- 2.Construct a JSON input object with your prompt and desired parameters
- 3.Execute 'belt app run openai/gpt-image-2 --input' with your JSON payload
- 4.Retrieve the generated image URL(s) from the response
- 5.Optionally adjust quality, resolution, or other parameters for subsequent runs
Use cases
- Create product mockups and marketing visuals from text descriptions
- Generate concept art and design variations for creative projects
- Edit photos by changing backgrounds, objects, or other elements
- Perform inpainting to remove or replace specific regions in images
- Combine multiple reference images into a single cohesive scene
- Product designers and marketers creating visual assets
- Creative professionals working on concept art and illustrations
- Content creators needing image editing and manipulation
- Teams requiring batch image generation for campaigns
- Developers building image generation into applications
gpt-image FAQ
Quality affects both the visual fidelity and cost: low (~$0.006), medium (~$0.024), and high (~$0.21) per image. Larger resolutions also increase cost.
Yes, set the 'n' parameter to generate 1–10 images in a single request.
Provide the original image URL in the 'images' array, a mask image URL showing the region to edit, and a prompt describing what should replace the masked area.
PNG (default), JPEG, and WebP are supported. You can also control compression levels for JPEG and WebP.
Any size from 256–4096 pixels in 32-pixel increments for both width and height, allowing custom aspect ratios.
Full instructions (SKILL.md)
Source of truth, from 101-skills/superpowers.
name: gpt-image description: "Generate and edit images with OpenAI GPT-Image-2 via inference.sh CLI. Models: GPT-Image-2. Capabilities: text-to-image, image editing, inpainting, mask-based editing, multi-image reference, batch generation. Use for: product mockups, marketing visuals, image editing, concept art, inpainting, photo manipulation. Triggers: gpt image, gpt-image-2, openai image, chatgpt image, dall-e, dalle, openai image generation, gpt image edit, gpt inpainting, openai dall-e, gpt 4o image" allowed-tools: Bash(belt *)
Install the belt CLI skill:
npx skills add belt-sh/cli
GPT-Image-2
Generate and edit images with OpenAI's GPT-Image-2 via inference.sh CLI.
Quick Start
Requires inference.sh CLI (
belt). Install instructions
belt login
belt app run openai/gpt-image-2 --input '{"prompt": "a cat astronaut floating in space"}'
Capabilities
GPT-Image-2 supports text-to-image generation, image editing with reference images, and mask-based inpainting — all through a single model.
| Feature | Description |
|---|---|
| Text-to-Image | Generate images from text prompts |
| Image Editing | Edit images using reference images |
| Inpainting | Mask-based editing of specific regions |
| Batch Generation | Generate up to 10 images at once |
| Multiple Formats | PNG, JPEG, WebP output |
| Flexible Resolution | Any size in 32px increments (256–4096) |
Examples
Text-to-Image
belt app run openai/gpt-image-2 --input '{
"prompt": "professional product photo of sneakers on a white background, studio lighting",
"quality": "high"
}'
Multiple Images
belt app run openai/gpt-image-2 --input '{
"prompt": "minimalist logo design for a coffee shop",
"n": 4,
"quality": "medium"
}'
Image Editing with Reference
belt app run openai/gpt-image-2 --input '{
"prompt": "change the background to a beach at sunset",
"images": ["https://your-image.jpg"]
}'
Multi-Image Reference
belt app run openai/gpt-image-2 --input '{
"prompt": "combine these two characters into one scene",
"images": ["https://character1.jpg", "https://character2.jpg"]
}'
Inpainting with Mask
belt app run openai/gpt-image-2 --input '{
"prompt": "replace with a red sports car",
"images": ["https://street-scene.jpg"],
"mask": "https://car-mask.png"
}'
Custom Resolution
belt app run openai/gpt-image-2 --input '{
"prompt": "wide cinematic landscape, mountains at golden hour",
"width": 1920,
"height": 1080,
"quality": "high"
}'
Fast Drafts
belt app run openai/gpt-image-2 --input '{
"prompt": "quick concept sketch of a robot",
"quality": "low"
}'
Pricing
| Quality | ~Price per Image |
|---|---|
| Low | $0.006 |
| Medium | $0.024 |
| High | $0.21 |
Larger resolutions cost more. See belt app get openai/gpt-image-2 for full pricing details.
Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
prompt | string | required | Text prompt describing the image |
images | array | - | Reference image(s) for editing |
mask | string | - | Mask image for inpainting |
n | integer | 1 | Number of images (1–10) |
quality | string | - | low, medium, or high |
width | integer | - | Output width (256–4096, multiples of 32) |
height | integer | - | Output height (256–4096, multiples of 32) |
output_format | string | png | png, jpeg, or webp |
output_compression | integer | - | Compression level for jpeg/webp (0–100) |
Related Skills
# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli
# All image generation models
npx skills add inference-sh/skills@ai-image-generation
# FLUX models
npx skills add inference-sh/skills@flux-image
# Pruna P-Image (fast & economical)
npx skills add inference-sh/skills@p-image
Browse all image apps: belt app list --category image
Documentation
- Running Apps - How to run apps via CLI
- Streaming Results - Real-time progress updates
Related skills
More from 101-skills/superpowers and the wider catalog.
happyhorse
Generate and edit physically realistic videos with Alibaba HappyHorse 1.0 models via inference.sh CLI.
image-to-video
Convert still images to animated videos with AI models—select the right tool for realistic motion, fabric physics, or versatile animation.
infsh-cli
Run AI apps via inference.sh CLI—image generation, video, LLMs, search, 3D, Twitter automation.
landing-page-design
Design high-converting landing pages with AI-generated visuals and proven layout formulas.
p-image
Generate images fast with Pruna's optimized P-Image models via inference.sh CLI.
p-video
Generate videos from text or images using Pruna's optimized AI models via inference.sh CLI.