Z-Image LoRA

Overview

Z-Image LoRA is an asynchronous text-to-image model for generating a single image from a prompt. It supports explicit size input, common aspect_ratio presets, optional seed control, and prompt extension.

Capability	Value
Model ID	`z-image-LoRA`
Modes	`text-to-image`
Default mode	`text-to-image`
Default size	`1024*1536`
Size formats	`WIDTH*HEIGHT`, `WIDTHxHEIGHT`, `WIDTHXHEIGHT`
Size range	Each side must be between `256` and `1536` pixels
Aspect ratios	`1:1`, `2:3`, `3:2`, `3:4`, `4:3`, `9:16`, `16:9`
Prompt extension	`prompt_extend`, default `true`

Endpoint and authentication

Base URL:

https://api.apixo.ai/api/v1

Method	Endpoint	Purpose
`POST`	`/generateTask/z-image-LoRA`	Submit a text-to-image task
`GET`	`/statusTask/z-image-LoRA?taskId={taskId}`	Poll task status and retrieve results

All requests require your APIXO API key:

Authorization: Bearer YOUR_API_KEY

Submit requests also require:

Content-Type: application/json

Copy-paste async quickstart

curl -X POST "https://api.apixo.ai/api/v1/generateTask/z-image-LoRA" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-image",
      "prompt": "a cinematic portrait of a warrior standing in falling snow",
      "aspect_ratio": "16:9",
      "prompt_extend": true
    }
  }'

Successful response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678"
  }
}

Save the taskId; you need it to poll for the final result.

Poll for result

curl -X GET "https://api.apixo.ai/api/v1/statusTask/z-image-LoRA?taskId=task_12345678" \
  -H "Authorization: Bearer YOUR_API_KEY"

Processing response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "processing",
    "createTime": 1767965610929
  }
}

Success response:

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "task_12345678",
    "state": "success",
    "resultJson": "{\"resultUrls\":[\"https://file.apixo.ai/image.png\"]}",
    "createTime": 1767965610929,
    "completeTime": 1767965652317,
    "costTime": 41388
  }
}

Parse resultJson after state becomes success:

const payload = JSON.parse(data.resultJson);
const imageUrls = payload.resultUrls;

Request body

Generate with aspect ratio

{
  "request_type": "async",
  "input": {
    "mode": "text-to-image",
    "prompt": "a cinematic portrait of a warrior standing in falling snow",
    "aspect_ratio": "16:9",
    "prompt_extend": true
  }
}

Generate with explicit size

{
  "request_type": "async",
  "input": {
    "mode": "text-to-image",
    "prompt": "a watercolor mountain lake at sunrise",
    "size": "1024*1536",
    "seed": 42,
    "prompt_extend": false
  }
}

Parameters

string

default:"async"

required

Result delivery mode. Use async and poll with statusTask.

object

required

Z-Image LoRA input parameters.

Show properties

string

default:"text-to-image"

Generation mode. This model supports text-to-image only. If omitted by SDK helpers, APIXO uses text-to-image.

string

required

Prompt text describing the image to generate. Must be a non-empty string.

string

default:"1024*1536"

Optional explicit output size. Supports WIDTH*HEIGHT, WIDTHxHEIGHT, and WIDTHXHEIGHT, for example 1024*1536, 1024x1536, or 1024X1536. Width and height must each be between 256 and 1536. When size is provided, it takes precedence over aspect_ratio.

string

default:"2:3"

Output aspect ratio used when size is not provided. Supported values: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9.

integer

Optional random seed. Use a fixed non-negative integer seed for more reproducible experiments.

boolean

default:"true"

Whether to enable prompt extension. Prompt extension does not add an extra public charge.

Response format

Submit task response

POST /generateTask/z-image-LoRA returns a task ID when the task is accepted:

integer

API status code. 200 means the task was accepted.

string

Human-readable status message.

string

Unique task identifier used with the status endpoint.

Status response fields

string

Unique task identifier.

string

Current task state: pending, processing, success, or failed.

string

JSON string containing generated image URLs in resultUrls. Present when state is success.

string

Machine-readable failure code. Present when state is failed.

string

Human-readable failure message. Present when state is failed.

integer

Task creation timestamp in Unix milliseconds.

integer

Task completion timestamp in Unix milliseconds. Present after completion.

integer

Processing duration in milliseconds when available.

Billing

Z-Image LoRA is billed per generated image.

Unit	APIXO price
One generated image	`$0.0156 / image`

Prompt extension does not add an extra public charge. For current route and market comparison pricing, see Pricing.

Latency and polling

Z-Image LoRA tasks are asynchronous. Actual latency varies by prompt complexity and current queue load.

Use case	Recommended first poll	Poll interval
Standard generation	10s after task creation	5s-10s

Rate limits and concurrency can vary by account, API key, and route. If you receive 429, slow down requests and retry with backoff. For account-level details, see System APIs.

Size rules

If neither size nor aspect_ratio is provided, the default output size is 1024*1536.
size supports *, x, and X separators.
size takes precedence over aspect_ratio.
Explicit size requires width and height to each stay within 256-1536.
aspect_ratio is used only when size is not provided.
Supported aspect_ratio values map to platform-managed output sizes within the allowed range.

Aspect ratio	Output size
`1:1`	`1536*1536`
`2:3`	`1024*1536`
`3:2`	`1536*1024`
`3:4`	`1152*1536`
`4:3`	`1536*1152`
`9:16`	`864*1536`
`16:9`	`1536*864`

Errors and troubleshooting

HTTP errors

Code	Meaning	What to do
`400`	Invalid request body, mode, parameter type, or value	Fix the request before retrying
`401`	Missing or invalid API key	Check the `Authorization` header
`402`	Insufficient balance or quota	Add balance or switch account/key
`403`	Key or route cannot access the model	Check permissions and route strategy
`404`	Task not found	Verify the `taskId` and model ID
`429`	Rate limit or concurrency limit reached	Retry with exponential backoff
`500`	Server or unmapped model error	Retry with backoff
`502`	Model service error	Retry with backoff
`504`	Model service timeout	Retry or poll again later

Request validation

Condition	Backend behavior
Invalid `mode`	Returns a mode validation error; use `text-to-image`
Missing or empty `prompt`	Returns a missing-parameter or validation error
Invalid `size` format	Returns a size format validation error
`size` outside `256-1536` per side	Returns a size range validation error
Unsupported `aspect_ratio`	Returns the supported aspect-ratio list
Negative `seed`	Returns a seed validation error

See Error Codes for the full error reference.

Getting Started

Image Models

Video Models

Audio Models

Text & Utility Models

Z-Image LoRA

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Generate with aspect ratio

Generate with explicit size

Parameters

Response format

Submit task response

Status response fields

Billing

Latency and polling

Size rules

Errors and troubleshooting

HTTP errors

Request validation

​Overview

​Endpoint and authentication

​Copy-paste async quickstart

​Poll for result

​Request body

​Generate with aspect ratio

​Generate with explicit size

​Parameters

​Response format

​Submit task response

​Status response fields

​Billing

​Latency and polling

​Size rules

​Errors and troubleshooting

​HTTP errors

​Request validation

​Related links

Overview

Endpoint and authentication

Copy-paste async quickstart

Poll for result

Request body

Generate with aspect ratio

Generate with explicit size

Parameters

Response format

Submit task response

Status response fields

Billing

Latency and polling

Size rules

Errors and troubleshooting

HTTP errors

Request validation

Related links