# Qwen Image 3.0 Text-to-Image — Atlas Cloud API

> Generates images from a text prompt at resolutions up to 2048×2048, with automatic prompt rewriting and prompt-guided resolution selection, building on Qwen strength in complex text rendering and precise prompt adherence

This is the machine-readable API reference for **Qwen Image 3.0 Text-to-Image** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `qwen-image-3.0/text-to-image`
- **Modality**: Image
- **Model page**: https://www.atlascloud.ai/models/qwen-image-3.0/text-to-image
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.04 per image
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_image` with `model: "qwen-image-3.0/text-to-image"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate image qwen-image-3.0/text-to-image -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateImage` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `qwen-image-3.0/text-to-image`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  model name
  - Default: `"qwen-image-3.0/text-to-image"`

- **`prompt`** (`string`, _required_):
  The text prompt describing the image to generate.

- **`size`** (`string`, _optional_):
  Output resolution as width*height (e.g. 2048*2048). Omit to let the model pick a resolution automatically from the prompt. Valid range: 512*512–2048*2048.

- **`n`** (`integer`, _optional_):
  Number of images to generate.
  - Default: `1`
  - Min: 1
  - Max: 4

- **`negative_prompt`** (`string`, _optional_):
  Describes content that should NOT appear in the generated image.

- **`seed`** (`integer`, _optional_):
  Seed for reproducible generation, range [0, 2147483647]. Omit for a random seed.
  - Min: 0
  - Max: 2147483647

- **`prompt_extend`** (`boolean`, _optional_):
  Enable intelligent prompt rewriting for richer results.
  - Default: `true`

- **`prompt_extend_mode`** (`string`, _optional_):
  Prompt rewriting strategy. 'direct' (DPE) rewrites in a single pass; 'agent' (APE) uses an agentic rewrite pipeline.
  - Default: `"direct"`
  - Options: "direct", "agent"



**Required Parameters Example**:

```json
{
  "model": "qwen-image-3.0/text-to-image",
  "prompt": ""
}
```


**Full Example**:

```json
{
  "model": "qwen-image-3.0/text-to-image",
  "prompt": "",
  "size": "",
  "n": 1,
  "negative_prompt": "",
  "seed": 0,
  "prompt_extend": true,
  "prompt_extend_mode": "direct"
}
```


### Output Schema

The API returns the following output format:


- **`model`** (`string`, _optional_):
  model name
  - Default: `"qwen-image-3.0/text-to-image"`

- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created (e.g., "2023-04-01T12:34:56.789Z").

- **`has_nsfw_contents`** (`array[boolean]`, _optional_):
  Array of boolean values indicating NSFW detection for each output.

- **`id`** (`string`, _optional_):
  Unique identifier for the prediction.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the generated images. Null when status is not completed. URLs are valid for about 24 hours — download promptly.

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example Response**:

```json
{
  "model": "qwen-image-3.0/text-to-image",
  "created_at": "",
  "has_nsfw_contents": [],
  "id": "",
  "outputs": [
    ""
  ],
  "status": "",
  "urls": {}
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen-image-3.0/text-to-image",
  "prompt": "",
  "size": "",
  "n": 1,
  "negative_prompt": "",
  "seed": 0,
  "prompt_extend": true,
  "prompt_extend_mode": "direct"
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/qwen-image-3.0/text-to-image)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### Qwen-Image 3.0 (Text-to-Image)

**Qwen-Image 3.0** is a high-fidelity text-to-image model that generates images from detailed text prompts. Built-in prompt expansion (DPE/APE) enriches short prompts, while flexible resolution and reproducible seeds make it suitable for both rapid exploration and controlled iteration.

> Invite-beta model for interface testing. Output does not represent final quality.

#### 🌟 Key Features

##### ✏️ Text-to-Image
Generate high-fidelity images from text prompts alone, with strong semantic understanding and photorealistic quality.

##### 🧠 Prompt Expansion (DPE / APE)
`prompt_extend` intelligently rewrites short prompts. Choose `direct` (DPE, single-pass) or `agent` (APE, agentic pipeline).

##### 📐 Flexible Resolution
Specify `size` as `width*height` (up to 2048×2048), or omit it to let the model pick automatically from the prompt.

##### 🔁 Reproducible Results
Pin a `seed` value to reproduce or iterate on a specific generation, enabling systematic prompt refinement.

##### 🖼 Batch Generation
Request multiple images per call with `n` to explore variations at once.

#### ⚙️ Parameters

| Parameter | Required | Description |
|---|---|---|
| `prompt` | ✅ | Text description of the image to generate. |
| `size` | ❌ | Output resolution as `width*height` (e.g. `2048*2048`). Omit for automatic. Range: 512×512–2048×2048. |
| `n` | ❌ | Number of images to generate (default: 1). |
| `negative_prompt` | ❌ | Content that should NOT appear in the image. |
| `seed` | ❌ | Seed for reproducible output, range `[0, 2147483647]`. Omit for random. |
| `prompt_extend` | ❌ | Enable intelligent prompt rewriting (default: `true`). |
| `prompt_extend_mode` | ❌ | `direct` (DPE, default) or `agent` (APE). |

#### 💡 Prompt Tips

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/qwen-image-3.0/text-to-image · Docs: https://www.atlascloud.ai/docs