OpenAI Image Format (Image)¶

Official Documentation

📝 Introduction¶

Given a text prompt and/or input image, the model will generate new images. OpenAI offers several powerful image generation models that can create, edit, and modify images based on natural language descriptions. Currently supported models include:

Model	Description
DALL·E Series	Includes two versions, DALL·E 2 and DALL·E 3, which differ significantly in image quality, creative expression, and accuracy
GPT-Image-1	OpenAI's latest image model, supporting multi-image editing features, capable of creating new composite images based on multiple input images

💡 Request Examples¶

Create Image ✅¶

# 基础图片生成
curl https://zhaotouai.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ZHAOTOU_API_KEY" \
  -d '{
    "model": "dall-e-3",
    "prompt": "一只可爱的小海獭",
    "n": 1,
    "size": "1024x1024"
  }'

# 高质量图片生成
curl https://zhaotouai.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ZHAOTOU_API_KEY" \
  -d '{
    "model": "dall-e-3",
    "prompt": "一只可爱的小海獭",
    "quality": "hd",
    "style": "vivid",
    "size": "1024x1024"
  }'

# 使用 base64 返回格式
curl https://zhaotouai.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ZHAOTOU_API_KEY" \
  -d '{
    "model": "dall-e-3",
    "prompt": "一只可爱的小海獭",
    "response_format": "b64_json"
  }'

Response Example:

{
  "created": 1589478378,
  "data": [
    {
      "url": "https://...",
      "revised_prompt": "一只可爱的小海獭在水中嬉戏,它有着圆圆的眼睛和毛茸茸的皮毛"
    }
  ]
}

Edit Image ✅¶

# dall-e-2 图片编辑
curl https://zhaotouai.com/v1/images/edits \
  -H "Authorization: Bearer $ZHAOTOU_API_KEY" \
  -F image="@otter.png" \
  -F mask="@mask.png" \
  -F prompt="一只戴着贝雷帽的可爱小海獭" \
  -F n=2 \
  -F size="1024x1024"

# gpt-image-1 多图片编辑示例
curl https://zhaotouai.com/v1/images/edits \
  -H "Authorization: Bearer $ZHAOTOU_API_KEY" \
  -F "model=gpt-image-1" \
  -F "image[]=@body-lotion.png" \
  -F "image[]=@bath-bomb.png" \
  -F "image[]=@incense-kit.png" \
  -F "image[]=@soap.png" \
  -F "prompt=创建一个包含这四个物品的精美礼品篮" \
  -F "quality=high"

Response Example (dall-e-2):

{
  "created": 1589478378,
  "data": [
    {
      "url": "https://..."
    },
    {
      "url": "https://..."
    }
  ]
}

Response Example (gpt-image-1):

{
  "created": 1713833628,
  "data": [
    {
      "b64_json": "..."
    }
  ],
  "usage": {
    "total_tokens": 100,
    "input_tokens": 50,
    "output_tokens": 50,
    "input_tokens_details": {
      "text_tokens": 10,
      "image_tokens": 40
    }
  }
}

Generate Image Variations ✅¶

curl https://zhaotouai.com/v1/images/variations \
  -H "Authorization: Bearer $ZHAOTOU_API_KEY" \
  -F image="@otter.png" \
  -F n=2 \
  -F size="1024x1024"

Response Example:

{
  "created": 1589478378,
  "data": [
    {
      "url": "https://..."
    },
    {
      "url": "https://..."
    }
  ]
}

📮 Request¶

Endpoints¶

Create Image¶

POST /v1/images/generations

Creates an image given a text prompt.

Edit Image¶

POST /v1/images/edits

Creates an edited or extended image based on one or more original images and a prompt. This endpoint supports the dall-e-2 and gpt-image-1 models.

Generate Variation¶

POST /v1/images/variations

Creates a variation of a given image.

Authentication Method¶

Include the following in the request header for API key authentication:

Authorization: Bearer $ZHAOTOU_API_KEY

Where $OPENAI_API_KEY is your API key.

Request Body Parameters¶

Create Image¶

`prompt`¶

Type: string
Required: Yes
Description: A text description of the desired image(s).
dall-e-2 maximum length is 1000 characters
dall-e-3 maximum length is 4000 characters
Tips:
Use specific and detailed descriptions
Include key visual elements
Specify the desired artistic style
Describe composition and perspective

`model`¶

Type: string
Required: No
Default: dall-e-2
Description: The model to use for image generation.

`n`¶

Type: integer or null
Required: No
Default: 1
Description: The number of images to generate. Must be between 1 and 10. dall-e-3 only supports n=1.

`quality`¶

Type: string
Required: No
Default: standard
Description: The quality of the generated image. The hd option generates more detailed and consistent images. This parameter is only supported by dall-e-3.

`response_format`¶

Type: string or null
Required: No
Default: url
Description: The format in which the generated images are returned. Must be one of url or b64_json. URLs are valid for 60 minutes after generation.

`size`¶

Type: string or null
Required: No
Default: 1024x1024
Description: The size of the generated images. dall-e-2 must be one of 256x256, 512x512, or 1024x1024. dall-e-3 must be one of 1024x1024, 1792x1024, or 1024x1792.

`style`¶

Type: string or null
Required: No
Default: vivid
Description: The style of the generated images. Must be one of vivid or natural. vivid tends to generate hyper-real and dramatic images, while natural tends to generate more natural, less hyper-real images. This parameter is only supported by dall-e-3.

`user`¶

Type: string
Required: No
Description: A unique identifier representing your end-user, which can help OpenAI monitor and detect abuse.

`moderation`¶

Type: string
Required: No
Default: auto
Description: auto: Standard moderation, designed to limit the generation of certain content categories that may not be age-appropriate. low: Less restrictive moderation.

Edit Image¶

`image`¶

Type: file or file array
Required: Yes
Description: The image to be edited.
For dall-e-2: Must be a valid PNG file, less than 4MB, and square. If no mask is provided, the image must have transparency, which will be used as the mask.
For gpt-image-1: Multiple images can be provided as an array. Each image should be a PNG, WEBP, or JPG file, less than 25MB.

`prompt`¶

Type: string
Required: Yes
Description: A text description of the desired image(s).
dall-e-2 maximum length is 1000 characters
gpt-image-1 maximum length is 32000 characters

`mask`¶

Type: file
Required: No
Description: An additional image whose fully transparent areas (e.g., alpha zero areas) indicate where the image should be edited. If multiple images are provided, the mask will be applied to the first image. Must be a valid PNG file, less than 4MB, and have the same dimensions as the image.

`model`¶

Type: string
Required: No
Default: dall-e-2
Description: The model to use for image generation. Supports dall-e-2 and gpt-image-1. Defaults to dall-e-2 unless gpt-image-1 specific parameters are used.

`quality`¶

Type: string or null
Required: No
Default: auto
Description: The quality of the generated image.
gpt-image-1 supports high, medium, and low
dall-e-2 only supports standard
Defaults to auto

`size`¶

Type: string or null
Required: No
Default: 1024x1024
Description: The size of the generated images.
gpt-image-1 must be one of 1024x1024, 1536x1024 (landscape), 1024x1536 (portrait), or auto (default)
dall-e-2 must be one of 256x256, 512x512, or 1024x1024

Other parameters are the same as the Create Image interface.

Generate Variations¶

`image`¶

Type: file
Required: Yes
Description: The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.

Other parameters are the same as the Create Image interface.

📥 Response¶

Successful Response¶

All three endpoints return a response containing a list of image objects.

`created`¶

Type: integer
Description: The timestamp when the response was created

`data`¶

Type: array
Description: A list of generated image objects

`usage` (Only applicable to gpt-image-1)¶

Type: object
Description: Token usage for the API call
total_tokens: Total tokens used
input_tokens: Tokens used for input
output_tokens: Tokens used for output
input_tokens_details: Detailed information on input tokens (text tokens and image tokens)

Image Object¶

`b64_json`¶

Type: string
Description: If response_format is b64_json, this contains the base64 encoded JSON of the generated image

`url`¶

Type: string
Description: If response_format is url (default), this contains the URL of the generated image

`revised_prompt`¶

Type: string
Description: If the prompt was modified, this contains the revised prompt used to generate the image

Example Image Object:

{
  "url": "https://...",
  "revised_prompt": "一只可爱的小海獭在水中嬉戏,它有着圆圆的眼睛和毛茸茸的皮毛"
}

🌟 Best Practices¶

Prompt Writing Suggestions¶

Use clear and specific descriptions
Specify important visual details
Describe the desired artistic style and atmosphere
Include instructions for composition and perspective

Parameter Selection Suggestions¶

Model Selection
dall-e-3: Suitable for scenarios requiring high quality and precise details
dall-e-2: Suitable for rapid prototyping or simple image generation
Size Selection
1024x1024: Best choice for general scenarios
1792x1024/1024x1792: Suitable for landscape/portrait scenarios
Smaller sizes: Suitable for thumbnails or quick previews
Quality and Style
quality=hd: Used for images requiring fine detail
style=vivid: Suitable for creative and artistic effects
style=natural: Suitable for realistic scene reproduction

Common Issues¶

Image generation failure
Check if the prompt complies with content policies
Confirm file format and size limits
Verify API key permissions
Results do not match expectations
Optimize the prompt description
Adjust quality and style parameters
Consider using image editing or variation features

OpenAI Image Format (Image)¶

📝 Introduction¶

💡 Request Examples¶

Create Image ✅¶

Edit Image ✅¶

Generate Image Variations ✅¶

📮 Request¶

Endpoints¶

Create Image¶

Edit Image¶

Generate Variation¶

Authentication Method¶

Request Body Parameters¶

Create Image¶

prompt¶

model¶

n¶

quality¶

response_format¶

size¶

style¶

user¶

moderation¶

Edit Image¶

image¶

prompt¶

mask¶

model¶

quality¶

size¶

Generate Variations¶

image¶

📥 Response¶

Successful Response¶

created¶

data¶

usage (Only applicable to gpt-image-1)¶

Image Object¶

b64_json¶

url¶

revised_prompt¶

🌟 Best Practices¶

Prompt Writing Suggestions¶

Parameter Selection Suggestions¶

Common Issues¶

`prompt`¶

`model`¶

`n`¶

`quality`¶

`response_format`¶

`size`¶

`style`¶

`user`¶

`moderation`¶

`image`¶

`prompt`¶

`mask`¶

`model`¶

`quality`¶

`size`¶

`image`¶

`created`¶

`data`¶

`usage` (Only applicable to gpt-image-1)¶

`b64_json`¶

`url`¶

`revised_prompt`¶