Image Generation · Moss API

Request parameters

FieldTypeRequiredDescription

model: stringRequired

Model ID. Use the stable model ID for regular calls, or a snapshot model ID when you need to reproduce results from a fixed version.

prompt: stringRequired

The text description of the image to generate; a non-empty string of at most 4,000 characters.

negative_prompt: stringOptional

Content that should not appear in the image; at most 4,000 characters. The examples use the negative tags recommended in the model card.

size: stringOptional

Image size in the format widthxheight; defaults to 1024x1024. Each side must be 256–2048 and a multiple of 16; the total pixel count must not exceed 2097152.

n: integerOptional

Number of images to generate; only 1 is supported.

seed: integerOptional

Random seed that controls the randomness of generation and makes results reproducible, from 0 to 2^53−1. If omitted, the system generates one at random.

num_inference_steps: integerOptional

Number of inference steps, from 1 to 100.

guidance_scale: numberOptional

Guidance scale, from 0 to 10; an explicit 0 is honored.

response_format: stringOptional

Only url is supported; b64_json is not supported.

output_watermark: objectOptional

Output watermark settings. enabled is a boolean; when omitted, the visible watermark is on by default. Pass {"enabled": false} to turn off the visible watermark; the image still keeps its AIGC metadata.

Return value

On success, the endpoint returns JSON containing the image URL. Currently one PNG is generated per request, and streaming output is not supported.

FieldTypeDescription

created: integer

The creation timestamp in the response.

data: array

The list of generated image results.

data[].url: string

The URL of the generated image.

usage: object

The actual image generation usage.

usage.generated_images: integer

The number of images actually generated.

usage.output_width: integer

The actual image width, in pixels.

usage.output_height: integer

The actual image height, in pixels.

Error codes

HTTPerror.codeTrigger and suggested action

400: invalid_field_value

The body is not valid JSON, a field has an invalid type or value, the request contains unsupported parameters, or the model / version cannot be found. Check field names and parameter ranges; do not pass a separate version for a snapshot model.

403: 2 error codes

Authentication failed, or the platform safety review blocked the request.

404: resource_not_found

The generated image asset does not exist. Resubmit the generation request; if it recurs, keep the request identifiers and contact the service provider.

429: 2 error codes

The concurrency or request-rate limit was exceeded.

502: upstream_invalid_result

The upstream result failed structure, model version, or usage validation. Keep the task and trace identifiers and contact the service provider.

Next steps

Scenario guide

Image generation: from input to image result

Generate images from text descriptions, with support for long text and text rendering, for poster design, illustration, and visual content creation.

Models

MOSS-Image-Base-1.0

Model ID, capabilities, and snapshots.

Request example

curl --max-time 900 -X POST "https://api.mosi.cn/v1/images/generations" \
  -H "Authorization: Bearer $MOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "moss-image-base-1.0",
  "prompt": "An orange cat sitting by the window, a garden after the rain outside, soft natural light, warm and delicate photographic style.",
  "negative_prompt": "nsfw, worst quality, bad anatomy, watermark, jpeg artifact",
  "size": "1024x1024",
  "n": 1,
  "response_format": "url"
}'

import os
import requests

response = requests.post(
    "https://api.mosi.cn/v1/images/generations",
    headers={
        "Authorization": f"Bearer {os.environ['MOSS_API_KEY']}",
        "Content-Type": "application/json",
    },
    timeout=900,
    json={
        "model": "moss-image-base-1.0",
        "prompt": "An orange cat sitting by the window, a garden after the rain outside, soft natural light, warm and delicate photographic style.",
        "negative_prompt": "nsfw, worst quality, bad anatomy, watermark, jpeg artifact",
        "size": "1024x1024",
        "n": 1,
        "response_format": "url",
    },
)

response.raise_for_status()
print(response.json())

const response = await fetch("https://api.mosi.cn/v1/images/generations", {
  method: "POST",
  signal: AbortSignal.timeout(900_000),
  headers: {
    "Authorization": "Bearer " + process.env.MOSS_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "moss-image-base-1.0",
    "prompt": "An orange cat sitting by the window, a garden after the rain outside, soft natural light, warm and delicate photographic style.",
    "negative_prompt": "nsfw, worst quality, bad anatomy, watermark, jpeg artifact",
    "size": "1024x1024",
    "n": 1,
    "response_format": "url"
  }),
})

if (!response.ok) throw new Error(`HTTP ${response.status}`)
console.log(await response.json())

Response example

{
  "created": 1792380763,
  "data": [
    {
      "url": "https://example.com/generated-image.png"
    }
  ],
  "usage": {
    "generated_images": 1,
    "output_width": 1024,
    "output_height": 1024
  }
}