QWEN Image Plus API

Fast generation with excellent quality Integrate this model via REST with endpoint docs, parameters, and code examples.

Image Generation

LoRA

Editing

Content moderation disabled

Credit Cost

1 credit

Type

image

Get API Key

Create auth keys for apps and agents

See Usage

Track requests, credits, and logs

Buy Credits

Top up prepaid API capacity

API Endpoint

POST

/api/v1/models/qwen-image-plus/run

LLM.txt

AI-Ready

For AI assistants

Copy this model's documentation into Claude, GPT, or any AI for instant integration help.

/llm/qwen-image-plus.txt

OpenAPI Spec

Swagger compatible

Import into Postman, Swagger UI, or generate client SDKs in any language.

/api/openapi

Parameters

Input parameters accepted by this model

Parameter	Type	Description	Default
`prompt` required	string	Text description of the image to generate (max 800 characters).	-
`generation_model`	enum	DashScope model variant. Rolling: qwen-image-plus, qwen-image-max. Dated snapshots for pinning: qwen-image-plus-2026-01-09, qwen-image-max-2025-12-30. Legacy: qwen-image. Ignored when lora_weights is set (LoRA path uses Replicate). `qwen-image-plusqwen-image-plus-2026-01-09qwen-image-maxqwen-image-max-2025-12-30qwen-image`	`qwen-image-plus`
`aspect_ratio`	enum	Image aspect ratio. The qwen-image-plus / qwen-image-max series ship five recommended aspect ratios; 21:9 is only available on the LoRA Replicate path. `1:116:99:164:33:4`+1 more	`1:1`
`negative_prompt`	string	What to avoid in the output (max 500 characters).	-
`prompt_extend`	boolean	Enable smart prompt rewriting on the DashScope path. The model expands your prompt for richer detail. Default true.	`true`
`watermark`	boolean	Adds a "Qwen-Image" watermark to the bottom-right corner.	`false`
`num_inference_steps`	integer	LoRA path only — number of inference steps (28-50). min: 28 \| max: 50	`35`
`guidance`	number	LoRA path only — guidance scale (2-4). min: 2 \| max: 4	`3`
`go_fast`	boolean	LoRA path only — enable faster generation.	`false`
`numberOfImages`	integer	Number of images to generate. The DashScope path (qwen-image-plus / qwen-image-max) is fixed at 1 per upstream contract; the LoRA Replicate path supports 1-4. min: 1 \| max: 4	`1`
`seed`	integer	Random seed for reproducibility (0–2147483647). min: 0 \| max: 2147483647	-
`lora_weights`	string	URL or HuggingFace path to a Qwen Image LoRA. Supplying this routes the request through the Replicate LoRA remix variant and unlocks numberOfImages > 1 + LoRA-specific params.	-
`lora_scale`	number	Strength of the LoRA effect (typical 0–2). min: 0 \| max: 2	`1`

Supported Aspect Ratios

1:1

16:9

9:16

4:3

3:4

21:9

Example Outputs

Real outputs generated by this model

View Details

A dramatic low-angle photograph of a master martial artist mid-strike inside a sleek modern dojo, shattering a wooden board that explodes into thousands of glowing purple and pink pixel fragments that scatter through the air like embers. The dojo has polished concrete floors, floor-to-ceiling windows revealing a rain-soaked Tokyo cityscape at night, and minimal Japanese architectural details — clean wooden beams, a torii gate silhouette visible through the glass. The pixel fragments cast colored light across the fighter's face and the wet floor reflections. Shot on Sony A7R V, 35mm f/1.4, shallow depth of field, dramatic side lighting from a single overhead spotlight cutting through atmospheric haze, rain streaks visible on the windows. Hyperrealistic, editorial photography, 8K resolution

1 credits

6.8s

Code Examples

Copy and paste to get started

bash

curl -X POST "https://pixeldojo.ai/api/v1/models/qwen-image-plus/run" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A beautiful mountain landscape at golden hour",
    "aspect_ratio": "1:1"
  }'

Response Format

Submit Response (202 Accepted)

json

{
  "jobId": "job_abc123...",
  "status": "pending",
  "statusUrl": "https://pixeldojo.ai/api/v1/jobs/job_abc123...",
  "creditCost": 1,
  "creditsRemaining": 95,
  "expiresAt": "2025-01-23T12:00:00Z"
}

Completed Response