Generate or Edit Images from a Description · Alibaba

Provide an image description and explicit output dimensions to create new images, or add up to three references for editing. Successful results include image download links to review and save.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use generate-and-edit-images-alibaba (Tool ID 5a48419e-b5d8-4326-b40b-c1396577767e) to generate one abstract forest phone wallpaper within my existing authorization and budget. Reuse my Toolmu connection or follow https://toolmu.com/SKILL.md. Set body.prompt="Abstract forest phone wallpaper, deep-green tree silhouettes, soft light, simple composition, no text or logos", body.size=1080*1920 and body.n=1. Omit the entire body.images field for text-only generation; do not rely on an empty array to select the mode. Size is required and uses an asterisk between width and height, not auto or the letter x. Generate only the requested image and do not automatically add images or repeat the operation. After success, show the actual returned image and available download link. Read its actual dimensions and count; new model links are temporary, typically about 24 hours. Do not claim a finished image before a successful result is available.

Task:
Create a phone wallpaper showing [a misty pine forest at sunrise], with [soft green light] and [no words or logos]. If I do not know the size, choose a common tall phone shape. Make one picture and share its download link.

Paste into your connected AI's conversation.

Connection guide

Up to 0.5508 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

Alibaba

Generate or Edit Images from a Description · Alibaba

Provide an image description and explicit output dimensions to create new images, or add up to three references for editing. Successful results include image download links to review and save.

You receive

Generate an image from your description and requested size, or use up to three input images to change the scene. You can request 1–6 outputs, default one; a successful operation returns downloadable images.

Start with your task

Create a phone wallpaper showing [a misty pine forest at sunrise], with [soft green light] and [no words or logos]. If I do not know the size, choose a common tall phone shape. Make one picture and share its download link.

What to know

Output dimensions are required and must meet the total-pixel and aspect-ratio limits; actual dimensions can vary slightly. References need eligible public HTTPS links. Requested count, visual details and edit fidelity are not guaranteed, and new model download links typically last about 24 hours.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
body`body`	`object`	Required	Required fields `prompt, size`
Requested image count`body.n`	`integer`	Optional	Optional integer from 1 to 6; default 1. Requests that many output images in ordinary generation or editing, without guaranteeing every requested image will succeed. Default `1` Minimum `1` Maximum `6`
Random seed`body.seed`	`integer`	Optional	Optional integer from 0 to 2147483647. A fixed seed can help reproducibility, but the same seed does not guarantee identical images. Minimum `0` Maximum `2147483647`
Required output dimensions`body.size`	`string`	Required	Required widthheight string, such as 10801920; use an asterisk, not x or auto. Total pixel area must be between 512×512 and 2048×2048 for both generation and editing, with aspect ratio 1:8–8:1. These are total-pixel bounds, not per-side bounds; actual generated dimensions can vary slightly. Pattern `^\d+\*\d+$`
Ordered input images for editing`body.images`	`array`	Optional	Optional array of up to three public HTTPS image links. Their order defines the reference order. Omit the whole field for text-only generation rather than relying on empty-array behavior. Maximum items `3`
Reference image link and file requirements`body.images[]`	`string`	—	Each supplied entry must be a nonempty public HTTPS file URL. Use JPG, JPEG, PNG, BMP, TIFF, WEBP or GIF, up to 10 MB each. Width and height of 384–2048 pixels are recommended, not mandatory side bounds. This Tool does not accept HTTP, local paths, Base64 or asset IDs. Minimum length `1`
Image description or editing instruction`body.prompt`	`string`	Required	Required nonempty text describing content, style and composition, or the desired edit when input images are supplied. Chinese and English are supported. Recommended length is at most 4500 tokens, which are model text units rather than characters; this is a recommendation, not a fixed character cap. Minimum length `1`
AI Generated watermark`body.watermark`	`boolean`	Optional	Optional boolean; default false. true requests an AI Generated watermark on the result. Default `false`
Rewrite the instruction`body.prompt_extend`	`boolean`	Optional	Optional boolean; default true. Enables model-assisted rewriting, useful for a short instruction, without guaranteeing a better image. Default `true`
Thinking mode`body.enable_thinking`	`boolean`	Optional	Optional boolean; default true. Requires prompt rewriting to be enabled. It can increase processing time and does not guarantee quality or fidelity.
Requested exclusions`body.negative_prompt`	`string`	Optional	Optional text describing content to exclude. It guides generation or editing but does not guarantee those elements will be absent.
Instruction rewriting mode`body.prompt_extend_mode`	`string`	Optional	Optional direct or agent; default direct. direct supports generation and editing. agent is only for text-only generation without input images; it rewrites more extensively, without a guaranteed quality improvement. Options `direct, agent`

View raw JSON

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "prompt",
        "size"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "n": {
          "type": "integer",
          "default": 1,
          "maximum": 6,
          "minimum": 1,
          "description": "Optional integer from 1 to 6; default 1. Requests that many output images in ordinary generation or editing, without guaranteeing every requested image will succeed."
        },
        "seed": {
          "type": "integer",
          "maximum": 2147483647,
          "minimum": 0,
          "description": "Optional integer from 0 to 2147483647. A fixed seed can help reproducibility, but the same seed does not guarantee identical images."
        },
        "size": {
          "type": "string",
          "pattern": "^\\d+\\*\\d+$",
          "description": "Required width*height string, such as 1080*1920; use an asterisk, not x or auto. Total pixel area must be between 512×512 and 2048×2048 for both generation and editing, with aspect ratio 1:8–8:1. These are total-pixel bounds, not per-side bounds; actual generated dimensions can vary slightly."
        },
        "images": {
          "type": "array",
          "items": {
            "type": "string",
            "minLength": 1,
            "description": "Each supplied entry must be a nonempty public HTTPS file URL. Use JPG, JPEG, PNG, BMP, TIFF, WEBP or GIF, up to 10 MB each. Width and height of 384–2048 pixels are recommended, not mandatory side bounds. This Tool does not accept HTTP, local paths, Base64 or asset IDs."
          },
          "maxItems": 3,
          "description": "Optional array of up to three public HTTPS image links. Their order defines the reference order. Omit the whole field for text-only generation rather than relying on empty-array behavior."
        },
        "prompt": {
          "type": "string",
          "minLength": 1,
          "description": "Required nonempty text describing content, style and composition, or the desired edit when input images are supplied. Chinese and English are supported. Recommended length is at most 4500 tokens, which are model text units rather than characters; this is a recommendation, not a fixed character cap."
        },
        "watermark": {
          "type": "boolean",
          "default": false,
          "description": "Optional boolean; default false. true requests an AI Generated watermark on the result."
        },
        "prompt_extend": {
          "type": "boolean",
          "default": true,
          "description": "Optional boolean; default true. Enables model-assisted rewriting, useful for a short instruction, without guaranteeing a better image."
        },
        "enable_thinking": {
          "type": "boolean",
          "description": "Optional boolean; default true. Requires prompt rewriting to be enabled. It can increase processing time and does not guarantee quality or fidelity."
        },
        "negative_prompt": {
          "type": "string",
          "description": "Optional text describing content to exclude. It guides generation or editing but does not guarantee those elements will be absent."
        },
        "prompt_extend_mode": {
          "enum": [
            "direct",
            "agent"
          ],
          "type": "string",
          "description": "Optional direct or agent; default direct. direct supports generation and editing. agent is only for text-only generation without input images; it rewrites more extensively, without a guaranteed quality improvement."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

For a portrait wallpaper, a width of 1080 and height of 1920 give 2073600 total pixels and a 9:16 ratio. These output dimensions are separate from the recommended input-image dimensions. Choose a size within the total-pixel and aspect-ratio limits, then inspect the actual result.

For editing, describe what to change and what you want retained, and keep the reference images in the intended order. Review fine details, lettering and subject appearance in the finished image; a model interpretation can differ from the instruction.

Alibaba Qwen image generation and editing documentation describes the source. This Tool uses Qwen Image 3.0 Pro with the explicit dimensions and HTTPS references listed above.

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

No. This Tool requires explicit width and height, such as 1080*1920 with an asterisk separator; auto and the letter x are not accepted. Total pixels must be between 512×512 and 2048×2048, with aspect ratio 1:8–8:1. These are total-pixel bounds, not independent limits on each side.

Generate or Edit Images from a Description · Alibaba

Generate or Edit Images from a Description · Alibaba

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Use an AI wallpaper generator for a phone background

Create a realistic AI image from your description

Edit a picture using its share link

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Use an AI wallpaper generator for a phone background

Create a realistic AI image from your description

Edit a picture using its share link

Questions about this tool.

Can I omit size or use auto?

How do I edit existing images?

Does a fixed seed produce an identical result?