Qwen Image 2 Pro API, Qwen Image Edit API (Free), Qwen Image API: Pricing, Documentation

Qwen Image 2 Pro API, developers can access text-to-image generation, image editing, layered image creation, and LoRA training features. The API represents Alibaba's advanced AI research applied to visual content creation, suitable for both consumer applications and enterprise workflows.

Get API Key

Models Version

WELCOME BONUS

Get $5 Free Credit on First Payment

No strings attached — add funds and get $5 bonus instantly

Claim Your $5 →

Qwen Image Max Edit API Documentation

https://gateway.pixazo.ai/qwen-image-max-edit/v1/qwen-image-max-edit-request

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Qwen Image Max Edit generate request - Qwen Image Max Edit

Request Code

POST https://gateway.pixazo.ai/qwen-image-max-edit/v1/qwen-image-max-edit-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Transform the background into a serene mountain landscape with snow-capped peaks and a clear blue sky",
  "image_urls": [
    "https://imagesai.appypie.com/7686410/JUEOHp2Y3FDjmXwOQJVy_017731476841749.png"
  ]
}

import requests

url = "https://gateway.pixazo.ai/qwen-image-max-edit/v1/qwen-image-max-edit-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Transform the background into a serene mountain landscape with snow-capped peaks and a clear blue sky",
    "image_urls": [
        "https://imagesai.appypie.com/7686410/JUEOHp2Y3FDjmXwOQJVy_017731476841749.png"
    ]
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/qwen-image-max-edit/v1/qwen-image-max-edit-request';

const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};

const data = {
  prompt: 'Transform the background into a serene mountain landscape with snow-capped peaks and a clear blue sky',
  image_urls: [
    'https://imagesai.appypie.com/7686410/JUEOHp2Y3FDjmXwOQJVy_017731476841749.png'
  ]
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST "https://gateway.pixazo.ai/qwen-image-max-edit/v1/qwen-image-max-edit-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "Transform the background into a serene mountain landscape with snow-capped peaks and a clear blue sky",
    "image_urls": [
      "https://imagesai.appypie.com/7686410/JUEOHp2Y3FDjmXwOQJVy_017731476841749.png"
    ]
  }'

Output

{
  "request_id": "qwen-image-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "qwen-image-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-max-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "qwen-image-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-max-edit",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - Qwen Image Max Edit generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	Max 800 characters	Text prompt describing the desired edit. Supports Chinese and English. Be specific about the change (subject, context, lighting, environment).
negative_prompt	No	string	""	Max 500 characters	Describes unwanted elements or artifacts to avoid in the output. Improves quality by exclusion.
image_size	No	string or object	—	square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or a custom {width, height} object	Dimensions of the generated image. If omitted, the size of the input image is used.
enable_prompt_expansion	No	boolean	true	true, false	Automatically rewrites and enriches your prompt with extra detail before generation to improve results.
seed	No	integer	—	0–2147483647	Random seed for reproducible results. Reuse the same seed with the same inputs to regenerate a similar image.
enable_safety_checker	No	boolean	true	true, false	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
sync_mode	No	boolean	false	true, false	When true, the image is returned inline as a data URI in the response instead of a hosted URL, and the output is not saved to your request history.
num_images	No	integer	1	1–6	Number of edited images to generate. Must be between 1 and 6.
output_format	No	string	png	png, jpeg, webp	Output image format. Supported values: png, jpeg, webp.
image_urls	Yes	array of strings	—	1–3 image URLs	Public URLs of the reference image(s) to edit (1–3 images). Order matters — the first URL is image 1, the second image 2, and so on; reference them by position in your prompt. Each image 384–5000px per dimension, max 10 MB; JPG, PNG (no alpha), or WEBP.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	—	JPG, PNG, WEBP · < 10 MB	Image(s) to edit.

Minimum Request

{
  "prompt": "Transform the background into a serene mountain landscape with snow-capped peaks and a clear blue sky",
  "image_urls": [
    "https://imagesai.appypie.com/7686410/JUEOHp2Y3FDjmXwOQJVy_017731476841749.png"
  ]
}

Full Request (all options)

{
  "prompt": "Transform the background into a serene mountain landscape with snow-capped peaks and a clear blue sky",
  "negative_prompt": "low resolution, error, worst quality, low quality, deformed",
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "num_images": 1,
  "output_format": "png",
  "image_urls": [
    "https://imagesai.appypie.com/7686410/JUEOHp2Y3FDjmXwOQJVy_017731476841749.png"
  ]
}

Response

{
  "request_id": "qwen-image-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for Qwen Image Max Edit generate request.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

Notes & Tips

Poll the results endpoint every 2–3 seconds until status is COMPLETED or FAILED
Implement exponential backoff for retry logic on 500 or 429 responses
Use clear, specific prompts that describe the desired change in context, lighting, or environment
Avoid overly vague prompts like “make it better”; specify elements such as “replace sky with sunset”
Validate image URLs are publicly accessible and use HTTPS before submission

Limit num_images to 1 unless multiple variations are required to

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'qwen-image-max-edit' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "qwen-image-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-max-edit",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/qwen-image-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "qwen-image-max-edit_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-max-edit",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-max-edit_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Qwen Image Max Edit API Pricing

Your request will cost $0.075 per image.

2. Qwen Image Max t2i

Qwen Image Max t2i API Documentation

https://gateway.pixazo.ai/qwen-image-max/v1/qwen-image-max-request

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Qwen Image Max generate request - Qwen Image Max

Request Code

POST https://gateway.pixazo.ai/qwen-image-max/v1/qwen-image-max-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A majestic white tiger resting on a mossy rock beside a waterfall in a tropical rainforest, photorealistic"
}

import requests

url = "https://gateway.pixazo.ai/qwen-image-max/v1/qwen-image-max-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A majestic white tiger resting on a mossy rock beside a waterfall in a tropical rainforest, photorealistic"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = "https://gateway.pixazo.ai/qwen-image-max/v1/qwen-image-max-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
};
const data = {
  prompt: "A majestic white tiger resting on a mossy rock beside a waterfall in a tropical rainforest, photorealistic"
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error("Error:", error));

curl -X POST "https://gateway.pixazo.ai/qwen-image-max/v1/qwen-image-max-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "A majestic white tiger resting on a mossy rock beside a waterfall in a tropical rainforest, photorealistic"
  }'

Output

{
  "request_id": "qwen-image-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "qwen-image-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-max",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "qwen-image-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-max",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - Qwen Image Max generate request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	A detailed text description of the desired image. Supports English and Chinese; up to 800 characters. Be specific about subjects, styles, lighting, and composition.
negative_prompt	No	string	—	—	A description of elements to avoid in the generated image (up to 500 characters). Helps refine output quality by excluding unwanted features.
image_size	No	string	square_hd	square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9	The resolution and aspect ratio of the output image. Choose one of the preset enum values, or pass a custom {width, height} object.
enable_prompt_expansion	No	boolean	true	true, false	Automatically rewrites and enriches your prompt with an LLM before generation to improve results.
enable_safety_checker	No	boolean	true	true, false	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
seed	No	integer	—	0–2147483647	Random seed for reproducibility. Reuse the same seed with identical inputs to reproduce a result; omit for a random seed each request.
num_images	No	integer	1	1–4	Number of images to generate in a single request.
output_format	No	string	png	png, jpeg, webp	The file format of the generated image. Supported values: png, jpeg, webp.

Minimum Request

{
  "prompt": "A majestic white tiger resting on a mossy rock beside a waterfall in a tropical rainforest, photorealistic"
}

Full Request (all options)

{
  "prompt": "A majestic white tiger resting on a mossy rock beside a waterfall in a tropical rainforest, photorealistic",
  "negative_prompt": "low resolution, error, worst quality, low quality, deformed",
  "image_size": "square_hd",
  "enable_prompt_expansion": true,
  "enable_safety_checker": true,
  "num_images": 1,
  "output_format": "png"
}

Response

{
  "request_id": "qwen-image-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for Qwen Image Max generate request.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'qwen-image-max' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "qwen-image-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-max",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/qwen-image-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "qwen-image-max_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-max",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-max_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Qwen Image Max t2i API Pricing

Your request will cost $0.075 per image.

3. Qwen Image Edit

Qwen Image Edit API Documentation

https://gateway.pixazo.ai/qwen-image/v1/generateMultimodeTextToImageEditRequest

Image Edit(Img2Img) - Qwen Image API

Request Code

POST https://gateway.pixazo.ai/qwen-image/v1/generateMultimodeTextToImageEditRequest
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "model": "qwen-image-edit",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/manwithbear.jpg"
          },
          {
            "text": "Change the person to a walking position, bending over to hold the bears front paws."
          }
        ]
      }
    ]
  },
  "parameters": {
    "negative_prompt": "",
    "watermark": false
  }
}

import requests

url = "https://gateway.pixazo.ai/qwen-image/v1/generateMultimodeTextToImageEditRequest"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "model": "qwen-image-edit",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/manwithbear.jpg"
                    },
                    {
                        "text": "Change the person to a walking position, bending over to hold the bears front paws."
                    }
                ]
            }
        ]
    },
    "parameters": {
        "negative_prompt": "",
        "watermark": False
    }
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/qwen-image/v1/generateMultimodeTextToImageEditRequest';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};

const data = {
  model: 'qwen-image-edit',
  input: {
    messages: [
      {
        role: 'user',
        content: [
          {
            image: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/manwithbear.jpg'
          },
          {
            text: 'Change the person to a walking position, bending over to hold the bears front paws.'
          }
        ]
      }
    ]
  },
  parameters: {
    negative_prompt: '',
    watermark: false
  }
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -v -X POST "https://gateway.pixazo.ai/qwen-image/v1/generateMultimodeTextToImageEditRequest" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
--data-raw '{
  "model": "qwen-image-edit",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/manwithbear.jpg"
          },
          {
            "text": "Change the person to a walking position, bending over to hold the bears front paws."
          }
        ]
      }
    ]
  },
  "parameters": {
    "negative_prompt": "",
    "watermark": false
  }
}'

Output

{
  "status_code": 200,
  "request_id": "3daccb10-10ca-9399-8b6a-xxxxxx",
  "output": {
    "choices": [
      {
        "message": {
          "content": [
            {
              "image": "https://pub-...png"
            }
          ]
        }
      }
    ]
  }
}

Try Now

Request Parameters - Image Edit(Img2Img)

Parameter	Required	Type	Default	Allowed values / range	Description
model	Yes	string	—	qwen-image-edit	Model to use for this operation. Available value: "qwen-image-edit" (Qwen image editing model).
input	Yes	object	—	—	Container for the request payload. Holds the messages array.
input.messages	Yes	array	—	exactly 1 message object	Message list describing the edit. Only single-turn requests are supported, so the array must contain exactly one message object.
input.messages[].role	Yes	string	—	user	Role of the message sender. Must be "user" for image editing requests.
input.messages[].content	Yes	array	—	1 image item + 1 text item	Content items for the message: one image item ({"image": "..."}) and one editing instruction ({"text": "..."}). The qwen-image-edit model edits a single image per request (multi-image input is only available on the qwen-image-edit-plus / -max series).
input.messages[].content[].image	Yes	string	—	JPG, JPEG, PNG, BMP, TIFF, WEBP, GIF · < 10 MB · 384–3072 px per side	Input image to edit. Either a publicly accessible HTTP/HTTPS URL or Base64 data in the form data:{MIME_type};base64,{base64_data}. For animated GIFs only the first frame is processed. The generated image is returned as PNG.
input.messages[].content[].text	Yes	string	—	≤ 800 tokens	Editing instruction describing the desired changes (English or Chinese). Supports text editing, colour and style changes, and adding, removing or moving objects. Text beyond the limit is truncated.
parameters	No	object	—	—	Optional controls for the image generation.
parameters.negative_prompt	No	string	—	≤ 500 characters	Describes content that should NOT appear in the edited image (for example "low resolution, blurry, extra fingers"). Empty by default.
parameters.watermark	No	boolean	false	true, false	Whether to add the "Qwen-Image" watermark to the bottom-right corner of the edited image.
parameters.seed	No	integer	random	0 – 2147483647	Random seed used for generation. Reuse the same seed with the same input to get repeatable results. If omitted, a random seed is used.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	—	JPG, PNG, WEBP · < 10 MB	Image(s) to edit.

Example Request

{
  "model": "qwen-image-edit",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/manwithbear.jpg"
          },
          {
            "text": "Change the person to a walking position, bending over to hold the bear's front paws."
          }
        ]
      }
    ]
  },
  "parameters": {
    "negative_prompt": "",
    "watermark": false
  }
}

Response

{
  "status_code": 200,
  "request_id": "3daccb10-10ca-9399-8b6a-xxxxxx",
  "code": "",
  "message": "",
  "output": {
    "text": null,
    "finish_reason": null,
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "image": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/qwen-image-edit/qwen-image-edit-3daccb10-10ca-9399-8b6a-xxxxxx-1703123456789.png"
            }
          ]
        }
      }
    ]
  },
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0,
    "width": 1248,
    "image_count": 1,
    "height": 832
  }
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	YOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes for Image Edit(Img2Img).

Code	Meaning
200	Success
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

Qwen Image Edit API Pricing

Your request will cost $0.045 per image.

4. Qwen Image Edit 2509

Qwen Image Edit 2509 API Documentation

https://gateway.pixazo.ai/qwen-image-lite/v1/qwen-image-lite-request

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Qwen Image Edit Request - Qwen Image Edit

Request Code

POST https://gateway.pixazo.ai/qwen-image-lite/v1/qwen-image-lite-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "image_url": "https://your-host.com/input.png",
  "prompt": "Add a small bright red party hat on top, keep everything else identical",
  "negative_prompt": "",
  "num_inference_steps": 4,
  "true_cfg_scale": 1.0,
  "guidance_scale": 1.0,
  "seed": 42,
  "num_images": 1,
  "output_format": "png"
}

import requests

url = "https://gateway.pixazo.ai/qwen-image-lite/v1/qwen-image-lite-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "image_url": "https://your-host.com/input.png",
    "prompt": "Add a small bright red party hat on top, keep everything else identical",
    "negative_prompt": "",
    "num_inference_steps": 4,
    "true_cfg_scale": 1.0,
    "guidance_scale": 1.0,
    "seed": 42,
    "num_images": 1,
    "output_format": "png"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/qwen-image-lite/v1/qwen-image-lite-request';

const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};

const data = {
  image_url: 'https://your-host.com/input.png',
  prompt: 'Add a small bright red party hat on top, keep everything else identical',
  negative_prompt: '',
  num_inference_steps: 4,
  true_cfg_scale: 1.0,
  guidance_scale: 1.0,
  seed: 42,
  num_images: 1,
  output_format: 'png'
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST "https://gateway.pixazo.ai/qwen-image-lite/v1/qwen-image-lite-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "image_url": "https://your-host.com/input.png",
    "prompt": "Add a small bright red party hat on top, keep everything else identical",
    "negative_prompt": "",
    "num_inference_steps": 4,
    "true_cfg_scale": 1.0,
    "guidance_scale": 1.0,
    "seed": 42,
    "num_images": 1,
    "output_format": "png"
  }'

Output

{
  "request_id": "qwen-image-lite_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-lite_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "qwen-image-lite_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-lite",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-lite_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "qwen-image-lite_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-lite",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - Qwen Image Edit Request

Parameter	Required	Type	Default	Allowed values / range	Description
image_url	Yes (one source)	string	—	Public http(s) URL	Source image to edit. Recommended. Provide exactly one image source — `image_url`, `image_base64`, or `image_urls`.
image_base64	Yes (one source)	string	—	Raw base64 (no data: prefix)	Base64-encoded source image. Alternative to `image_url`.
image_urls	Yes (one source)	array of strings	—	Array of public URLs (1 – 3 recommended)	One or more source image URLs (multi-image edit). Qwen-Image-Edit-2509 is tuned for 1–3 reference images (e.g. person + product, person + scene); more images may degrade quality. Alternative to `image_url`.
prompt	Yes	string	—	Any text	Edit instruction describing the change. Be specific for best results.
negative_prompt	No	string	" " (space)	Any text	Concepts to steer away from in the output. Only takes effect when `true_cfg_scale` is greater than 1.0 — at the default `true_cfg_scale` of 1.0 the negative prompt is ignored.
num_inference_steps	No	integer	4	≥ 1	Denoising steps. This Lightning model is tuned for 4 steps; higher values rarely improve quality.
true_cfg_scale	No	number	1.0	≥ 1.0	True classifier-free guidance scale — the control that actually affects prompt adherence. `1.0` (default) disables CFG, which is what the 4-step Lightning schedule expects. Set it above 1.0 together with a `negative_prompt` to enable CFG: stronger prompt adherence, but roughly 2× slower and often lower image quality.
guidance_scale	No	number	1.0	≥ 1.0	Embedded (distillation) guidance value. It is accepted for compatibility but has no effect on this pipeline — raising it will not increase prompt adherence. Use `true_cfg_scale` instead.
seed	No	integer	42	Any integer	Random seed for reproducible results.
num_images	No	integer	1	1 – 4	Number of edited images to generate.
output_format	No	string	png	png, jpg	Output image format.

Content Item Types & Limits

Type	Max	Format / Size	Description
image_url	1	JPG, PNG, WEBP · < 10 MB	Image to edit.
image_urls	—	JPG, PNG, WEBP · < 10 MB	Additional reference image(s).

Minimum Request

{
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/upscaler_019ed0c8-bb34-7854-afbc-b2a164758a15b/output.png",
  "prompt": "Add a small bright red party hat on top"
}

Full Request (all options)

{
  "image_url": "https://your-host.com/input.png",
  "prompt": "Add a small bright red party hat on top, keep everything else identical",
  "negative_prompt": "",
  "num_inference_steps": 4,
  "true_cfg_scale": 1.0,
  "guidance_scale": 1.0,
  "seed": 42,
  "num_images": 1,
  "output_format": "png"
}

Response

{
  "request_id": "qwen-image-lite_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-lite_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for Qwen Image Edit Request.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'qwen-image-lite' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "qwen-image-lite_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-lite",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/qwen-image-lite_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "qwen-image-lite_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-lite",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-lite_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Qwen Image Edit 2509 API Pricing

Your request is Free

5. Qwen Image

Qwen Image API Documentation

https://gateway.pixazo.ai/qwen-image/v1/generateMultimodeTextToImageRequest

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Text To Image Request - Qwen Image API

Request Code

POST /generateMultimodeTextToImageRequest HTTP/1.1
Host: gateway.pixazo.ai
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "model": "qwen-image",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "text": "A serene lake at sunset, with mountains reflected in the water and a lone canoe on the shore."
          }
        ]
      }
    ]
  },
  "parameters": {
    "size": "1328*1328"
  }
}

import requests

url = "https://gateway.pixazo.ai/qwen-image/v1/generateMultimodeTextToImageRequest"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "model": "qwen-image",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "text": "A serene lake at sunset, with mountains reflected in the water and a lone canoe on the shore."
                    }
                ]
            }
        ]
    },
    "parameters": {
        "size": "1328*1328"
    }
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

fetch('https://gateway.pixazo.ai/qwen-image/v1/generateMultimodeTextToImageRequest', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Cache-Control': 'no-cache',
    'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
  },
  body: JSON.stringify({
    model: 'qwen-image',
    input: {
      messages: [
        {
          role: 'user',
          content: [
            {
              text: 'A serene lake at sunset, with mountains reflected in the water and a lone canoe on the shore.'
            }
          ]
        }
      ]
    },
    parameters: {
      size: '1328*1328'
    }
  })
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST "https://gateway.pixazo.ai/qwen-image/v1/generateMultimodeTextToImageRequest" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "model": "qwen-image",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": [
            {
              "text": "A serene lake at sunset, with mountains reflected in the water and a lone canoe on the shore."
            }
          ]
        }
      ]
    },
    "parameters": {
      "size": "1328*1328"
    }
  }'

Output

{
  "images": [
    {
      "file_name": "nano-banana-pro-edit-output.png",
      "content_type": "image/png",
      "url": "[RESPONSE_URL]"
    }
  ],
  "description": ""
}

Try Now

Request Parameters - Text To Image Request

Parameter	Required	Type	Default	Allowed values / range	Description
model	Yes	string	—	qwen-image	Model to call. This endpoint serves Qwen-Image text-to-image generation, so pass "qwen-image".
input.messages	Yes	array	—	exactly 1 message	Message array carrying the request. Only single-turn generation is supported, so it must contain exactly one message object.
input.messages[].role	Yes	string	—	user	Role of the message sender. Fixed value "user".
input.messages[].content	Yes	array	—	exactly 1 text object	Content array for the message. It must contain exactly one text object — omitting it, or passing more than one, returns an error.
input.messages[].content[].text	Yes	string	—	up to 800 tokens	Positive prompt describing the content, style and composition you want. Chinese and English are supported, and the model is particularly strong at rendering text inside the image.
parameters.negative_prompt	No	string	—	up to 500 characters	Describes what you do not want to see in the image, for example "blurry, extra fingers, low quality". Chinese and English are supported.
parameters.size	No	string	1664*928	1664928 (16:9), 14721104 (4:3), 13281328 (1:1), 11041472 (3:4), 928*1664 (9:16)	Output resolution, written as "width*height". This model accepts only the five sizes listed; custom dimensions are not supported.
parameters.prompt_extend	No	boolean	true	true, false	Lets the model rewrite and enrich a short prompt with extra detail before generating. Set false when you want your prompt followed exactly.
parameters.watermark	No	boolean	false	true, false	Adds a "Qwen-Image" watermark to the bottom-right corner of the generated image.
parameters.seed	No	integer	random	0 – 2147483647	Random seed. Reusing the same seed with the same prompt and settings keeps results relatively stable; leave it out to get a different image each time.

Minimum Request

{
  "model": "qwen-image",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "text": "A serene lake at sunset, with mountains reflected in the water and a lone canoe on the shore."
          }
        ]
      }
    ]
  },
  "parameters": {
    "size": "1328*1328"
  }
}

Full Request (all options)

{
  "model": "qwen-image",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "text": "A serene lake at sunset, with mountains reflected in the water and a lone canoe on the shore."
          }
        ]
      }
    ]
  },
  "parameters": {
    "negative_prompt": "",
    "prompt_extend": true,
    "watermark": true,
    "size": "1328*1328"
  }
}

Response

{
  "images": [
    {
      "file_name": "nano-banana-pro-edit-output.png",
      "content_type": "image/png",
      "url": "[RESPONSE_URL]"
    }
  ],
  "description": ""
}

Response Fields - Text To Image Request

Field	Type	Description
images	array	Array of generated image objects.
images[].file_name	string	Name of the generated image file.
images[].content_type	string	MIME type of the image, typically "image/png".
images[].url	string	URL where the generated image can be downloaded.
description	string	Optional descriptive text about the generated image, currently always empty.

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for Text To Image Request.

Code	Meaning
200	Success
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

Qwen Image API Pricing

Your request will cost $0.045 per image.

6. Qwen LoRA v1

Qwen LoRA v1 API Documentation

https://gateway.pixazo.ai/qwen-image-edit-plus/v1/qwen-image-edit-plus-lora/generate

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Generate Image Edit Request - Qwen Image Edit Plus Lora API

Request Code

POST https://gateway.pixazo.ai/qwen-image-edit-plus/v1/qwen-image-edit-plus-lora/generate
Content-Type: application/json

{
  "prompt": "Close shot of a woman standing next to this car on this highway",
  "image_urls": [
    "https://example.com/reference1.png",
    "https://example.com/reference2.png",
    "https://example.com/reference3.png"
  ]
}

import requests

url = "https://gateway.pixazo.ai/qwen-image-edit-plus/v1/qwen-image-edit-plus-lora/generate"
headers = {
    "Content-Type": "application/json"
}
data = {
    "prompt": "Close shot of a woman standing next to this car on this highway",
    "image_urls": [
        "https://example.com/reference1.png",
        "https://example.com/reference2.png",
        "https://example.com/reference3.png"
    ]
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/qwen-image-edit-plus/v1/qwen-image-edit-plus-lora/generate';

const data = {
  prompt: 'Close shot of a woman standing next to this car on this highway',
  image_urls: [
    'https://example.com/reference1.png',
    'https://example.com/reference2.png',
    'https://example.com/reference3.png'
  ]
};

fetch(url, {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST https://gateway.pixazo.ai/qwen-image-edit-plus/v1/qwen-image-edit-plus-lora/generate \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Close shot of a woman standing next to this car on this highway",
    "image_urls": [
      "https://example.com/reference1.png",
      "https://example.com/reference2.png",
      "https://example.com/reference3.png"
    ]
  }'

Output

{
  "request_id": "qwen-image-edit-plus-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-edit-plus-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "qwen-image-edit-plus-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-edit-plus-lora",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-edit-plus-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "qwen-image-edit-plus-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-edit-plus-lora",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - Generate Image Edit Request

Parameter	Required	Type	Default	Allowed values / range	Description
prompt	Yes	string	—	—	The text instruction describing the edit you want applied to the input image(s).
image_urls	Yes	array	—	—	Publicly accessible URLs of the images to edit. Provide one or more reference images (or Base64 data URIs).
loras	No	array	[] (no LoRA)	up to 3 entries	LoRA weights to apply on top of the base model. Each entry is an object with `path` (required — URL of the LoRA weights) and `scale` (number, default 1, range 0-4). Up to 3 LoRAs are merged together for the final image.
image_size	No	string or object	size of the final input image	square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, or a custom {"width": …, "height": …} object (1-14142 px per side)	Size of the generated image. If omitted, the size of the final input image is used.
num_inference_steps	No	integer	28	2-50	Number of refinement steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
seed	No	integer	—	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
guidance_scale	No	number	4	0-20	CFG scale — controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation.
num_images	No	integer	1	1-4	Number of images to generate in a single request.
output_format	No	string	png	png, jpeg	The file format of the generated image.
negative_prompt	No	string	" " (a single space)	—	A description of elements to avoid in the generated image.
acceleration	No	string	regular	none, regular	Acceleration level for image generation. "regular" balances speed and quality; "none" disables acceleration.
enable_safety_checker	No	boolean	true	true, false	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
webhook	No	string	—	—	Webhook URL for async notifications
webhook_events_filter	No	array	—	—	Event types to receive: ["start"], ["complete"], ["*"]

Content Item Types & Limits

Type	Max	Format / Size	Description
image	—	JPG, PNG, WEBP · < 10 MB	Image(s) to edit.

Example Request

{
  "prompt": "Close shot of a woman standing next to this car on this highway",
  "image_urls": [
    "https://example.com/reference1.png",
    "https://example.com/reference2.png",
    "https://example.com/reference3.png"
  ],
  "image_size": "square_hd",
  "num_inference_steps": 50,
  "guidance_scale": 4,
  "num_images": 1,
  "output_format": "png",
  "negative_prompt": " ",
  "acceleration": "regular",
  "enable_safety_checker": true
}

Response

{
  "request_id": "qwen-image-edit-plus-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-edit-plus-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'qwen-image-edit-plus-lora' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "qwen-image-edit-plus-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-edit-plus-lora",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/qwen-image-edit-plus-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "qwen-image-edit-plus-lora_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-edit-plus-lora",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-edit-plus-lora_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Qwen LoRA v1 API Pricing

Your request will cost $0.055 per image.

Image to Image (LoRA Trainer)

Qwen LoRA v1 API Documentation

https://gateway.pixazo.ai/qwen-image-edit-plus-trainer/v1/qwen-image-edit-plus-trainer/generate

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Training Request - Qwen Image Edit Plus Trainer API

Request Code

POST https://gateway.pixazo.ai/qwen-image-edit-plus-trainer/v1/qwen-image-edit-plus-trainer/generate
Content-Type: application/json
Ocp-Apim-Subscription-Key: your-subscription-key

{
  "image_data_url": "https://example.com/lighting-training.zip",
  "steps": 1000
}

import requests

url = "https://gateway.pixazo.ai/qwen-image-edit-plus-trainer/v1/qwen-image-edit-plus-trainer/generate"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "your-subscription-key"
}
data = {
    "image_data_url": "https://example.com/lighting-training.zip",
    "steps": 1000
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/qwen-image-edit-plus-trainer/v1/qwen-image-edit-plus-trainer/generate';
const headers = {
  'Content-Type': 'application/json',
  'Ocp-Apim-Subscription-Key': 'your-subscription-key'
};
const data = {
  image_data_url: 'https://example.com/lighting-training.zip',
  steps: 1000
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST https://gateway.pixazo.ai/qwen-image-edit-plus-trainer/v1/qwen-image-edit-plus-trainer/generate \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: your-subscription-key" \
  -d '{
    "image_data_url": "https://example.com/lighting-training.zip",
    "steps": 1000
  }'

Output

{
  "request_id": "qwen-image-edit-plus-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-edit-plus-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "qwen-image-edit-plus-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-edit-plus-trainer",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-edit-plus-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "qwen-image-edit-plus-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-edit-plus-trainer",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - Training Request

Parameter	Required	Type	Default	Allowed values / range	Description
image_data_url	Yes	string	—	—	URL to the ZIP archive of training data. The ZIP holds image pairs named `ROOT_start.EXT` / `ROOT_end.EXT` (e.g. `photo_start.jpg` and `photo_end.jpg`). Extra reference images per pair are named `ROOT_start2.EXT`, `ROOT_start3.EXT`, … and an optional `ROOT.txt` per pair supplies that pair's edit instruction.
learning_rate	No	number	0.0001	—	Learning rate for the LoRA parameters. Lower values train more slowly but more reliably; higher values train faster but risk instability.
steps	No	integer	1000	1-30000	Number of training steps to run. More steps generally improve fidelity but increase training time and cost.
default_caption	No	string	—	—	Caption used for any image pair that has no `ROOT.txt` caption file. If it is omitted and a caption file is missing, the training run fails.
reference_image_count	No	integer	—	—	Number of reference images supplied per training pair in the ZIP archive (the `ROOT_start2`/`ROOT_start3` files).
webhook	No	string	—	—	Webhook URL for training completion notifications
webhook_events_filter	No	array	—	—	Event types to receive ("*" for all)

Example Request

{
  "image_data_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/upscaler_019ed0c8-bb34-7854-afbc-b2a164758a15b/output.png",
  "learning_rate": 0.0002,
  "steps": 2000,
  "default_caption": "professional cinematic lighting with dramatic shadows",
  "reference_image_count": 2,
  "webhook": "https://your-domain.com/training-complete"
}

Response

{
  "request_id": "qwen-image-edit-plus-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-edit-plus-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Ocp-Apim-Subscription-Key	Your subscription key

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'qwen-image-edit-plus-trainer' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "qwen-image-edit-plus-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-edit-plus-trainer",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/qwen-image-edit-plus-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "qwen-image-edit-plus-trainer_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-edit-plus-trainer",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-edit-plus-trainer_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Qwen LoRA v1 API Pricing

Your request will cost $0.04 per LoRA training job.

Image to Image (Image Editing — Layered)

Qwen LoRA v1 API Documentation

https://gateway.pixazo.ai/qwen-image-layered/v1/qwen-image-layered-request

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Qwen Image Layered generate request - Qwen Image Layered API

Request Code

POST https://gateway.pixazo.ai/qwen-image-layered/v1/qwen-image-layered-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/car_race.jpeg",
  "num_inference_steps": 28,
  "guidance_scale": 5.0,
  "num_images": 1,
  "enable_safety_checker": true,
  "output_format": "png",
  "acceleration": "regular"
}

import requests

url = "https://gateway.pixazo.ai/qwen-image-layered/v1/qwen-image-layered-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/car_race.jpeg",
    "num_inference_steps": 28,
    "guidance_scale": 5.0,
    "num_images": 1,
    "enable_safety_checker": True,
    "output_format": "png",
    "acceleration": "regular"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/qwen-image-layered/v1/qwen-image-layered-request';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  image_url: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/car_race.jpeg',
  num_inference_steps: 28,
  guidance_scale: 5.0,
  num_images: 1,
  enable_safety_checker: true,
  output_format: 'png',
  acceleration: 'regular'
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST "https://gateway.pixazo.ai/qwen-image-layered/v1/qwen-image-layered-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/car_race.jpeg",
    "num_inference_steps": 28,
    "guidance_scale": 5.0,
    "num_images": 1,
    "enable_safety_checker": true,
    "output_format": "png",
    "acceleration": "regular"
  }'

Output

{
  "request_id": "qwen-image-layered_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-layered_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your submit request to receive a POST callback when the job completes — no polling required.

Webhook Headers

Header	Required	Default	Description
`X-Webhook-URL`	Yes (to enable)	—	HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).
`X-Webhook-Mode`	No	`terminal`	`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at 15s for tighter progress updates.

Example: enable webhook

X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal

Callback Payload

Your endpoint receives a POST application/json with the same shape as the GET /v2/requests/status/{request_id} response. Example terminal callback (mode terminal):

{
  "request_id": "qwen-image-layered_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-layered",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-layered_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}

Failure callback shape

{
  "request_id": "qwen-image-layered_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-layered",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}

Delivery semantics

terminal mode (default) — exactly one POST when the request reaches a terminal status. No callback during PROCESSING.
sync mode — POST on every status poll (with delay capped at ~15s) plus a final POST at terminal status. Use when you want progress updates.
Idempotency — use request_id as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
Response — respond 200 OK within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
HTTPS required — plain http:// URLs are rejected.

Request Parameters - Qwen Image Layered generate request

Parameter	Required	Type	Default	Allowed values / range	Description
image_url	Yes	string	—	—	The input image to be decomposed into layers. Must be a publicly accessible URL reachable by the server.
prompt	No	string	—	—	Optional caption describing the input image. A short, accurate caption helps the model separate the layers more reliably.
num_layers	No	integer	4	1-10	Number of layers to decompose the input image into.
num_inference_steps	No	integer	28	1-50	Number of refinement steps the model runs while generating. Higher values refine detail and quality but increase processing time; lower values are faster.
guidance_scale	No	number	5	1-20	Controls how closely the output follows your prompt (prompt adherence). Higher values stick more strictly to the prompt; lower values allow more creative variation.
num_images	No	integer	1	1	Number of layer sets to generate (currently only 1 is supported).
negative_prompt	No	string	"" (empty)	—	A description of elements to avoid in the generated layers.
seed	No	integer	—	—	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.
acceleration	No	string	regular	none, regular, high	Acceleration level for generation. "high" is fastest, "regular" balances speed and quality, "none" disables acceleration.
enable_safety_checker	No	boolean	true	true, false	Turns on automatic filtering of unsafe or explicit (NSFW) content. Leave enabled unless you have a specific reason to disable it.
output_format	No	string	png	png, webp	The file format of the generated layers. Use png to preserve transparency.

Content Item Types & Limits

Type	Max	Format / Size	Description
image	1	JPG, PNG, WEBP · < 10 MB	Image to decompose into layers.

Example Request

{
  "image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/car_race.jpeg",
  "num_inference_steps": 28,
  "guidance_scale": 5.0,
  "num_images": 1,
  "enable_safety_checker": true,
  "output_format": "png",
  "acceleration": "regular"
}

Response

{
  "request_id": "qwen-image-layered_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/qwen-image-layered_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	YOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'qwen-image-layered' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "qwen-image-layered_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "qwen-image-layered",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/qwen-image-layered_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "qwen-image-layered_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "qwen-image-layered",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/qwen-image-layered_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Qwen LoRA v1 API Pricing

Your request will cost $0.05 per image.