Image Generation and Editing (GPT Image 2 All) Skills

Usage Guide

Step 1: Requirement Analysis and Parameter Extraction

1. Clarify Intent: Distinguish whether the user needs [Text-to-Image] (generate new images), [Image-to-Image] (edit/modify existing images), or [Multi-Image Fusion].
2. Prompt Analysis:
   • Use the user's original complete input: Directly use the user's original full question and requirement description as the main body of the

     -p

     prompt. Avoid rewriting, summarizing, or secondary creation on your own to prevent loss of details.
   • Confirm first when supplementation is needed: If information is insufficient (e.g., missing style, number of subjects, shot language, scene details, text content, prohibited elements, etc.), ask the user for confirmation first; after the user confirms, append the supplementary content to the original prompt in an "appended" manner.
   • Examples:
     • User input: "Help me generate a picture of a cat, with a cute style."
     • Correct example: Use the user's input directly as the prompt:

       -p "Help me generate a picture of a cat, with a cute style."

     • Incorrect example: Unauthorized rewriting to "Generate a cute-style cat picture" will lose the details and tone of the user's original input.
     • If details need to be supplemented (e.g., color, background, etc.), ask for confirmation first: "What color do you want the cat to be? Any requirements for the background?" After the user replies, append it to the prompt:

       -p "Help me generate a picture of a cat, with a cute style. The cat is orange, and the background is grass."

3. Key Parameter Organization:
   • Prompt (Required): The final prompt after analysis (default = the user's original complete and consistent input; only append supplementary information after user confirmation).
   • Filename (Optional): Output image filename/path (must include a random identifier to avoid duplication). If not provided, the script will automatically generate a filename with a timestamp. It is recommended to generate a reasonable filename based on the content (e.g.,

     cat_in_garden.png

     ), avoid using generic names.
   • Size/Aspect (Optional): Since the model has no explicit size parameter, the size is controlled by prompt description. It is recommended to describe the size at the beginning of the prompt.
     • "Mobile wallpaper" -> Write

       Vertical 9:16

       or

       Mobile poster 9:16

       at the start of the prompt
     • "Computer wallpaper/video cover" -> Write

       Horizontal 16:9

       or

       Movie aspect ratio 16:9

       at the start of the prompt
     • "Avatar" -> Write

       1:1 Square composition

       or

       1024×1024 Square image

       at the start of the prompt
     • Default: If the user does not explicitly specify the image ratio, leave it blank (adaptive by the model).
   • Response Format (Optional): Response format, default is

     url

     (R2 CDN accelerated link), optional

     b64_json

     (base64 image data).
   • Note: The model does not support

     size

     ,

     n

     ,

     quality

     ,

     aspect_ratio

     parameters; passing them may trigger parameter validation errors.

Step 2: Environment Check and Command Execution

1. Check Environment: Confirm whether the

   APIYI_API_KEY

   environment variable is set (usually assumed to be set; prompt the user if the operation fails).
2. Build and Run Commands:
   • Priority: Node.js version: If Node is available in the environment (the

     node

     command works), prefer using

     scripts/generate_image.js

     (zero dependencies, parameters consistent with Python).
   • Use Python version if Node is unavailable: Use

     scripts/generate_image.py

     .
   Text-to-Image Command Template (Priority: Node.js):
   bash

   node scripts/generate_image.js -p "{prompt}" -f "{filename}" [-r {response_format}]

   Image-to-Image Command Template (Priority: Node.js):
   bash

   node scripts/generate_image.js -p "{edit_instruction}" -i "{input_path}" -f "{output_filename}" [-r {response_format}]

   Multi-Image Fusion Command Template (Priority: Node.js):
   bash

   node scripts/generate_image.js -p "Merge the styles of image 1 and image 2" -i ref1.png ref2.png -f "merged.png" [-r {response_format}]

   (Optional) Python Version Command Template (When Node is Unavailable):
   bash

   python scripts/generate_image.py -p "{prompt}" -f "{filename}" [-r {response_format}]
   python scripts/generate_image.py -p "{edit_instruction}" -i "{input_path}" -f "{output_filename}" [-r {response_format}]

⏱️ Long-running Task Handling Strategy

1. Pre-task Prompt

• "Image generation has started, it is expected to take 60 to 300 seconds"

2. 🎨 Best Practice Example

"Image generation in progress, expected to complete in 60 to 300 seconds...
⏳ Generating..."

Step 3: Result Feedback

1. Execution Feedback: Wait for the terminal command to complete execution.
2. Success: Inform the user that the image has been generated and indicate the save path.
3. Failure:
   • If prompted with missing API Key, guide the user to set the environment variable.
   • If prompted with network error, suggest the user check the network or try again later.

Command Line Usage Examples

Generate New Images

python scripts/generate_image.py -p "Image description text" -f "output.png" [-r url|b64_json]

# Basic generation
python scripts/generate_image.py -p "A cute orange cat playing on the grass" -f "cat.png"

# Specify size (describe at the start of the prompt)
python scripts/generate_image.py -p "Horizontal 16:9 Movie aspect ratio, sunset mountain scenery" -f "sunset.png"

# Vertical high-definition image (suitable for mobile wallpaper)
python scripts/generate_image.py -p "Vertical 9:16 Mobile poster, city night view" -f "city.png"

# Basic generation
node scripts/generate_image.js -p "A cute orange cat playing on the grass" -f "cat.png"

# Specify size
node scripts/generate_image.js -p "Horizontal 16:9 Movie aspect ratio, sunset mountain scenery" -f "sunset.png"

Edit Existing Images

python scripts/generate_image.py -p "Editing instruction" -f "output.png" -i "path/to/input.png"

# Modify style
python scripts/generate_image.py -p "Convert the image to watercolor style" -f "watercolor.png" -i "original.png"

# Add elements
python scripts/generate_image.py -p "Add a rainbow to the sky" -f "rainbow.png" -i "landscape.png"

# Replace background
python scripts/generate_image.py -p "Change the background to a beach" -f "beach-bg.png" -i "portrait.png"

# Modify style
node scripts/generate_image.js -p "Convert the image to watercolor style" -f "watercolor.png" -i "original.png"

# Merge multiple reference images (up to 5)
node scripts/generate_image.js -p "Merge the styles of image 1 and image 2" -i ref1.png ref2.png -f "merged.png"

Command Line Parameter Description

Parameters are consistent between Python and Node.js versions (short parameters are equivalent to long parameters).

-p

--prompt

-f

--filename

-r

--response-format

url

b64_json

-i

--input-image

File Resource Description

scripts/generate_image.js

scripts/generate_image.py

references/size-guide.md

references/batch-template.md

Batch Generation

1. Load Configuration Template: references/batch-template.md — includes JSON configuration format description and usage examples
2. Obtain/Generate JSON File: Users can provide their own JSON file, or describe requirements and let AI generate it based on the needs
3. Preprocess Prompt: Ensure each prompt starts with size description (e.g., "Horizontal 16:9"), supplement

   global.size_hint

   if necessary
4. Execute One by One: Read the prompts array, execute generation commands one by one, and feed back results after each image is completed
5. Summarize Feedback: After completion, inform the user of the number of successful images and the list of image paths

Note: Total time for batch tasks = single image time (60-300 seconds) × number of images. Please inform the user of the estimated duration in advance.

Image Ratio Description

Response Format Description

url (Default)

b64_json

data:image/png;base64,

• Server-side direct image data processing
• Need to write to local files
• Direct rendering on the frontend

Notes

• API Key must be set, which can be provided via environment variable or command line parameter
• Image generation time: approximately 60 to 300 seconds
• When editing images, the input image will be automatically converted to base64 encoding
• Ensure the output directory has write permission
• The model does not support

  size

  ,

  n

  ,

  quality

  ,

  aspect_ratio

  parameters
• The default response url field is an R2 CDN accelerated link, valid for approximately 24 hours

API Key Setup and Acquisition

How to Obtain API Key

1. Visit https://api.apiyi.com
2. Register/log in to your account
3. Create an API Key in the console
4. Copy the key and set it as an environment variable or use it in the command line

Set API Key

APIYI_API_KEY

# Linux/Mac
export APIYI_API_KEY="your-api-key-here"

# Windows CMD
set APIYI_API_KEY=your-api-key-here

# Windows PowerShell
$env:APIYI_API_KEY="your-api-key-here"

API Endpoint Description

Recommended Endpoint: POST /v1/chat/completions

/v1/images/generations

/v1/images/edits

• Only input text messages → Text-to-image generation
• Add image_url (URL or base64 data URL) to messages → Reference image-based modification
• Retain assistant historical messages and continue asking → Multi-round iterative image modification

Model Information

• Model Name: gpt-image-2-all
• Image Generation Speed: Approximately 60-300 seconds
• Output Resolution: No explicit size parameter, adaptive by the model (recommended to describe in prompt)
• Default Response Format: url (R2 CDN accelerated link, default 1-day validity)
• Optional Response Format: b64_json
• Chinese Prompts: ✅ Natively supported
• Supported Capabilities: Text-to-image generation, single image editing, multi-image fusion, natural language-based image modification
• Price: $0.03 per image

Author Introduction

• Everywhere who loves One Piece
• My WeChat Official Account: Ubiquitous Technology",