OpenAI 全球独家总代
  1. SD3
OpenAI 全球独家总代
  • 发出请求
  • 模型接口
    • 聊天接口(Chat)
      • 聊天接口
      • gpts
      • gemini-pro
      • gpt-4-all(分析图片)
      • gpt-4-vision-preview
    • 自动补全接口(Completions)
      • 内容补全接口
    • 图像接口(Images)
      • DALL·E 3
      • gpt-4-all(生成图片)
    • 向量生成接口(Embeddings)
      • 创建嵌入
    • 音频接口(Audio)
      • 创建转录
      • 创建翻译
      • TTS文本转语音
    • MJ图像接口
      • 补充 - 其他参数以及回调
      • InsightFace任务提交
        • 提交swap_face任务
      • 任务提交
        • 执行动作
        • 提交Blend任务
        • 提交Describe任务
        • 提交Imagine任务
        • 提交Modal
        • 提交Shorten任务
      • 任务查询
        • 查询所有任务
        • 根据ID列表查询任务
        • 分页查询任务
        • 查询任务队列
        • 取消任务
        • 指定ID获取任务
        • 获取任务图片的seed(需设置mj或niji的私信ID)
    • Suno音乐接口
      • GoAmzAI格式
        • v3.5
          • 生成音乐
          • 获取音乐
        • v3.0
          • 生成音乐
          • 获取音乐
      • 官网原生格式(v2)
        • 官网格式
        • 所有接口
          • 音乐链接转成suno(upload)
          • 音乐生成(generations)
          • 查询任务(feed)
        • 场景1 生成自定义音乐(带歌词)
          • 音乐生成(generations)
          • 查询任务(feed)
        • 场景 2 通过提示词直接生成音乐(带歌词)
          • 音乐生成(generations)
          • 查询任务(feed)
        • 场景 4 通过提示词直接生成音乐(纯音乐)
          • 音乐生成(generations)
          • 查询任务(feed)
        • 场景3 生成自定义音乐(纯音乐)
          • 音乐生成(generations)
          • 查询任务(feed)
        • 场景 5 上传自定义音频并续写
          • 续写自定义音频步骤介绍
          • 音乐链接转成suno(upload)
          • 音乐生成(generations)
          • 查询任务(feed)
      • 生成歌词
        • 获取歌词
        • 生成歌词
    • Luma视频接口
      • GoAmzAI格式
        • 付费版
          • 生成视频
          • 获取视频
        • 免费版
          • 生成视频
          • 获取视频
      • 官网原生格式(v2)
        • 提交生成视频任务
        • 查询单个任务
        • 扩展视频
        • 获取视频无水印链接
    • SD图像接口
      • SD3
        • Stable Image Ultra
          POST
        • Stable Image Core
          POST
        • Stable Diffusion 3
          POST
      • SDXL
        • Text-to-image
  • 帮助中心
    • 常见问题及解决办法
  1. SD3

Stable Image Core

POST
/sd/v2beta/stable-image/generate/core
Generate
Our primary service for text-to-image generation, Stable Image Core represents the best quality achievable at high
speed. No prompt engineering is required! Try asking for a style, a scene, or a character, and see what you get.

Try it out#

Grab your API key and head over to Open Google Colab

How to use#

Please invoke this endpoint with a POST request.
The headers of the request must include an API key in the authorization field. The body of the request must be
multipart/form-data, and the accept header should be set to one of the following:
image/* to receive the image in the format specified by the output_format parameter.
application/json to receive the image encoded as base64 in a JSON response.
The body of the request should include:
prompt
The body may optionally include:
aspect_ratio
negative_prompt
seed
style_preset
output_format
Note: for more details about these parameters please see the request schema below.

Output#

The resolution of the generated image will be 1.5 megapixels.

Credits#

Flat rate of 3 credits per successful generation. You will not be charged for failed generations.

请求参数

Header 参数
authorization
string 
必需
Your Stability API key, used to authenticate your requests. Although you may have multiple keys in your account, you should use the same key for all requests to this API.
>= 1 字符
content-type
string 
必需
The content type of the request body. Do not manually specify this header; your HTTP client library will automatically include the appropriate boundary parameter.
>= 1 字符
示例值:
multipart/form-data
accept
enum<string> 
必需
Specify image/* to get the image bytes directly. Otherwise specify application/json to receive the image as base64 encoded JSON.
枚举值:
application/jsonimage/*
默认值:
image/*
Body 参数multipart/form-data
prompt
string 
必需
What you wish to see in the output image. A strong, descriptive prompt that clearly defines
elements, colors, and subjects will lead to better results.
To control the weight of a given word use the format (word:weight),
where word is the word you'd like to control the weight of and weight
is a value between 0 and 1. For example: The sky was a crisp (blue:0.3) and (green:0.8)
would convey a sky that was blue and green, but more green than blue.
>= 1 字符<= 10000 字符
aspect_ratio
enum<string> 
可选
Controls the aspect ratio of the generated image.
枚举值:
16:91:121:92:33:24:55:49:169:21
默认值:
1:1
示例值:
1:1
negative_prompt
string 
可选
A blurb of text describing what you do not wish to see in the output image.
This is an advanced feature.
<= 10000 字符
seed
number 
可选
A specific value that is used to guide the 'randomness' of the generation. (Omit this parameter or pass 0 to use a random seed.)
>= 0<= 4294967294
默认值:
0
style_preset
enum<string> 
可选
Guides the image model towards a particular style.
枚举值:
3d-modelanalog-filmanimecinematiccomic-bookdigital-artenhancefantasy-artisometricline-artlow-polymodeling-compoundneon-punkorigamiphotographicpixel-arttile-texture
output_format
enum<string> 
可选
Dictates the content-type of the generated image.
枚举值:
jpegpngwebp
默认值:
png
示例值:
png

示例代码

Python
JavaScript
Shell
Java
Swift
Go
PHP
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
请求示例请求示例
Python
JavaScript
Shell
Java
curl --location --request POST '/sd/v2beta/stable-image/generate/core' \
--header 'authorization;' \
--header 'accept;' \
--form 'prompt=""' \
--form 'aspect_ratio="1:1"' \
--form 'negative_prompt=""' \
--form 'seed=""' \
--form 'style_preset=""' \
--form 'output_format="png"'

返回响应

🟢200Generation was successful.
application/json
Body
object {0}
示例
{}
🟠400Invalid parameter(s), see the `errors` field for details.
🟠403Your request was flagged by our content moderation system.
🟠422You made a request with an unsupported language.
🟠429You have made more than 150 requests in 10 seconds.
🔴500An internal error occurred. If the problem persists [contact support](https://stabilityplatform.freshdesk.com/support/tickets/new).
上一页
Stable Image Ultra
下一页
Stable Diffusion 3
Built with