Alicloud Ai Image Qwen Image

Name: Alicloud Ai Image Qwen Image
Author: cinience

cinience/alicloud-skills

366 installs
396 repo stars
Updated July 18, 2026
cinience/alicloud-skills

Add text-to-image generation with Qwen image models for thumbnails, ads, avatars, and creative assets inside web and mobile products.

About

Implements Alibaba Cloud Qwen text-to-image generation: prompt tuning, API parameters, async jobs, asset delivery, and app integration patterns for SaaS and content products needing on-demand visuals.

Text-to-image via Qwen on AliCloud
Resolution, style, and seed controls
Async job polling and asset retrieval
CDN or object storage upload
Content safety and quota handling

Alicloud Ai Image Qwen Image by the numbers

366 all-time installs (skills.sh)
Ranked #463 of 1,335 Generative Media skills by installs in the Skillselion catalog
Data as of Aug 5, 2026 (Skillselion catalog sync)

npx skills add https://github.com/cinience/alicloud-skills --skill alicloud-ai-image-qwen-image

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/cinience/alicloud-skills/alicloud-ai-image-qwen-image.svg)](https://skillselion.com/skills/cinience/alicloud-skills/alicloud-ai-image-qwen-image)

Installs	366
repo stars	★ 396
Last updated	July 18, 2026
Repository	cinience/alicloud-skills ↗

What it does

Add text-to-image generation with Qwen image models for thumbnails, ads, avatars, and creative assets inside web and mobile products.

Files

SKILL.mdMarkdownGitHub ↗

Category: provider

Model Studio Qwen Image

Validation

mkdir -p output/alicloud-ai-image-qwen-image
python -m py_compile skills/ai/image/alicloud-ai-image-qwen-image/scripts/generate_image.py && echo "py_compile_ok" > output/alicloud-ai-image-qwen-image/validate.txt

Pass criteria: command exits 0 and output/alicloud-ai-image-qwen-image/validate.txt is generated.

Output And Evidence

Write generated image URLs, prompts, and metadata to output/alicloud-ai-image-qwen-image/.
Keep at least one sample JSON response per run.

Build consistent image generation behavior for the video-agent pipeline by standardizing image.generate inputs/outputs and using DashScope SDK (Python) with the exact model name.

Prerequisites

Install SDK (recommended in a venv to avoid PEP 668 limits):

python3 -m venv .venv
. .venv/bin/activate
python -m pip install dashscope

Set DASHSCOPE_API_KEY in your environment, or add dashscope_api_key to ~/.alibabacloud/credentials (env takes precedence).

Critical model names

Use one of these exact model strings:

qwen-image
qwen-image-plus
qwen-image-max
qwen-image-2.0
qwen-image-2.0-pro
qwen-image-2.0-2026-03-03
qwen-image-2.0-pro-2026-03-03
qwen-image-max-2025-12-30
qwen-image-plus-2026-01-09

Normalized interface (image.generate)

Request

prompt (string, required)
negative_prompt (string, optional)
size (string, required) e.g. 1024*1024, 768*1024
style (string, optional)
seed (int, optional)
reference_image (string | bytes, optional)

Response

image_url (string)
width (int)
height (int)
seed (int)

Quickstart (normalized request + preview)

Minimal normalized request body:

{
  "prompt": "a cinematic portrait of a cyclist at dusk, soft rim light, shallow depth of field",
  "negative_prompt": "blurry, low quality, watermark",
  "size": "1024*1024",
  "seed": 1234
}

Preview workflow (download then open):

curl -L -o output/alicloud-ai-image-qwen-image/images/preview.png "<IMAGE_URL_FROM_RESPONSE>" && open output/alicloud-ai-image-qwen-image/images/preview.png

Local helper script (JSON request -> image file):

python skills/ai/image/alicloud-ai-image-qwen-image/scripts/generate_image.py \\
  --request '{"prompt":"a studio product photo of headphones","size":"1024*1024"}' \\
  --output output/alicloud-ai-image-qwen-image/images/headphones.png \\
  --print-response

Parameters at a glance

Field	Required	Notes
`prompt`	yes	Describe a scene, not just keywords.
`negative_prompt`	no	Best-effort, may be ignored by backend.
`size`	yes	`WxH` format, e.g. `10241024`, `7681024`.
`style`	no	Optional stylistic hint.
`seed`	no	Use for reproducibility when supported.
`reference_image`	no	URL/file/bytes, SDK-specific mapping.

Quick start (Python + DashScope SDK)

Use the DashScope SDK and map the normalized request into the SDK call. Note: For qwen-image-max, the DashScope SDK currently succeeds via ImageGeneration (messages-based) rather than ImageSynthesis. If the SDK version you are using expects a different field name for reference images, adapt the input mapping accordingly.

import os
from dashscope.aigc.image_generation import ImageGeneration

# Prefer env var for auth: export DASHSCOPE_API_KEY=...
# Or use ~/.alibabacloud/credentials with dashscope_api_key under [default].


def generate_image(req: dict) -> dict:
    messages = [
        {
            "role": "user",
            "content": [{"text": req["prompt"]}],
        }
    ]

    if req.get("reference_image"):
        # Some SDK versions accept {"image": <url|file|bytes>} in messages content.
        messages[0]["content"].insert(0, {"image": req["reference_image"]})

    response = ImageGeneration.call(
        model=req.get("model", "qwen-image-max"),
        messages=messages,
        size=req.get("size", "1024*1024"),
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # Pass through optional parameters if supported by the backend.
        negative_prompt=req.get("negative_prompt"),
        style=req.get("style"),
        seed=req.get("seed"),
    )

    # Response is a generation-style envelope; extract the first image URL.
    content = response.output["choices"][0]["message"]["content"]
    image_url = None
    for item in content:
        if isinstance(item, dict) and item.get("image"):
            image_url = item["image"]
            break
    return {
        "image_url": image_url,
        "width": response.usage.get("width"),
        "height": response.usage.get("height"),
        "seed": req.get("seed"),
    }

Error handling

Error	Likely cause	Action
401/403	Missing or invalid `DASHSCOPE_API_KEY`	Check env var or `~/.alibabacloud/credentials`, and access policy.
400	Unsupported size or bad request shape	Use common `WxH` and validate fields.
429	Rate limit or quota	Retry with backoff, or reduce concurrency.
5xx	Transient backend errors	Retry with backoff once or twice.

Output location

Default output: output/alicloud-ai-image-qwen-image/images/
Override base dir with OUTPUT_DIR.

Operational guidance

Store the returned image in object storage and persist only the URL in metadata.
Cache results by (prompt, negative_prompt, size, seed, reference_image hash) to avoid duplicate costs.
Add retries for transient 429/5xx responses with exponential backoff.
Some backends ignore negative_prompt, style, or seed; treat them as best-effort inputs.
If the response contains no image URL, surface a clear error and retry once with a simplified prompt.

Size notes

Use WxH format (e.g. 1024*1024, 768*1024).
Prefer common sizes; unsupported sizes can return 400.

Anti-patterns

Do not invent model names or aliases; use official model IDs only.
Do not store large base64 blobs in DB rows; use object storage.
Do not omit user-visible progress for long generations.

Workflow

1) Confirm user intent, region, identifiers, and whether the operation is read-only or mutating. 2) Run one minimal read-only query first to verify connectivity and permissions. 3) Execute the target operation with explicit parameters and bounded scope. 4) Verify results and save output/evidence files.

References

See references/api_reference.md for a more detailed DashScope SDK mapping and response parsing tips.
See references/prompt-guide.md for prompt patterns and examples.
For edit workflows, use skills/ai/image/alicloud-ai-image-qwen-image-edit/.

Source list: references/sources.md

interface:
  display_name: "Alibaba Cloud AI Image Qwen Image"
  short_description: "Qwen image generation workflows"
  default_prompt: "Use $alicloud-ai-image-qwen-image to complete this ai/image task on Alibaba Cloud."

DashScope SDK Reference (Qwen Image)

Keep this reference minimal and update it only when the DashScope SDK behavior changes.

Install

python3 -m venv .venv
. .venv/bin/activate
python -m pip install dashscope

Environment

export DASHSCOPE_API_KEY=your_key

If env vars are not set, you can also place dashscope_api_key under [default] in ~/.alibabacloud/credentials.

Suggested mapping

Use the normalized image.generate request and map fields into the SDK call. Note: For qwen-image-max, the DashScope SDK currently succeeds via ImageGeneration (messages-based) rather than ImageSynthesis. The exact parameter names for reference images can vary across SDK versions.

import os
from dashscope.aigc.image_generation import ImageGeneration

messages = [
    {
        "role": "user",
        "content": [{"text": prompt}],
    }
]

if reference_image:
    # Some SDK versions accept {"image": <url|file|bytes>} in messages content.
    messages[0]["content"].insert(0, {"image": reference_image})

response = ImageGeneration.call(
    model="qwen-image-max",
    messages=messages,
    size=size,
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    negative_prompt=negative_prompt,
    style=style,
    seed=seed,
)

Response parsing

DashScope SDK response shapes can differ slightly by version. Extract the first result URL and normalize into:

image_url
width
height
seed

Prefer this pattern:

content = response.output["choices"][0]["message"]["content"]
image_url = next((item.get("image") for item in content if isinstance(item, dict) and item.get("image")), None)
width = response.usage.get("width")
height = response.usage.get("height")
seed = seed

Notes

negative_prompt, style, and seed may be ignored by some deployments; treat them as best-effort.
If no image URL is returned, fail fast with a clear error and retry with a shorter prompt.

Prompt Guide (Qwen Image)

Five practical prompt patterns to improve image generation quality.

Core principle

Describe a scene, not just keywords.

Bad: cat, cute, window, sunlight
Good: a white cat napping on a sunny windowsill, soft afternoon light, shallow depth of field

1) Photorealistic

Include camera and lighting details.

Example:

portrait photo, 85mm lens, f/1.8, golden hour rim light, natural skin texture, soft bokeh background

2) Illustration / Sticker

Call out a clear style and line treatment.

Example:

flat vector sticker of a smiling coffee mug, pastel palette, thick black outline, clean white background

3) Text-in-image

Be explicit about font, placement, and size.

Example:

birthday card with the text "HAPPY BIRTHDAY", bold sans-serif, centered, large type, pastel balloons background

4) Product photo

Use studio lighting and a specific angle.

Example:

product photo of wireless earbuds on a white sweep, softbox lighting, 45 degree angle, minimal shadow, high detail

5) Minimal design

Emphasize negative space and limited palette.

Example:

minimal abstract wallpaper, light blue gradient background, small geometric shape in bottom-right, lots of whitespace

Editing prompts (when using reference_image)

Add:

add a rainbow in the background

Remove:

remove the person in the background

Change:

change the hair color to blonde

Style transfer:

convert to watercolor style

#!/usr/bin/env python3
"""Generate an image using DashScope (qwen-image-max) from a normalized request.

Usage:
  python scripts/generate_image.py --request '{"prompt":"a cat","size":"1024*1024"}'
  python scripts/generate_image.py --file request.json --output output/ai-image-qwen-image/images/cat.png
"""

from __future__ import annotations

import argparse
import configparser
import json
import os
import sys
import urllib.request
from pathlib import Path
from typing import Any



def _find_repo_root(start: Path) -> Path | None:
    for parent in [start] + list(start.parents):
        if (parent / ".git").exists():
            return parent
    return None


def _load_dotenv(path: Path) -> None:
    if not path.exists():
        return
    for line in path.read_text().splitlines():
        line = line.strip()
        if not line or line.startswith("#") or "=" not in line:
            continue
        key, value = line.split("=", 1)
        key = key.strip()
        value = value.strip().strip('"').strip("'")
        if key and key not in os.environ:
            os.environ[key] = value


def _load_env() -> None:
    _load_dotenv(Path.cwd() / ".env")
    repo_root = _find_repo_root(Path(__file__).resolve())
    if repo_root:
        _load_dotenv(repo_root / ".env")


def _load_dashscope_api_key_from_credentials() -> None:
    if os.environ.get("DASHSCOPE_API_KEY"):
        return
    credentials_path = Path(os.path.expanduser("~/.alibabacloud/credentials"))
    if not credentials_path.exists():
        return
    config = configparser.ConfigParser()
    try:
        config.read(credentials_path)
    except configparser.Error:
        return
    profile = os.getenv("ALIBABA_CLOUD_PROFILE") or os.getenv("ALICLOUD_PROFILE") or "default"
    if not config.has_section(profile):
        return
    key = config.get(profile, "dashscope_api_key", fallback="").strip()
    if not key:
        key = config.get(profile, "DASHSCOPE_API_KEY", fallback="").strip()
    if key:
        os.environ["DASHSCOPE_API_KEY"] = key

try:
    from dashscope.aigc.image_generation import ImageGeneration
except ImportError:
    print("Error: dashscope is not installed. Run: pip install dashscope", file=sys.stderr)
    sys.exit(1)


MODEL_NAME = "qwen-image-max"
DEFAULT_SIZE = "1024*1024"


def load_request(args: argparse.Namespace) -> dict[str, Any]:
    if args.request:
        return json.loads(args.request)
    if args.file:
        with open(args.file, "r", encoding="utf-8") as f:
            return json.load(f)
    raise ValueError("Either --request or --file must be provided")


def resolve_reference_image(value: str) -> Any:
    if value.startswith("http://") or value.startswith("https://"):
        return value
    path = Path(value)
    if path.exists():
        return path.read_bytes()
    return value


def _get_field(obj: Any, key: str, default: Any = None) -> Any:
    if obj is None:
        return default
    if isinstance(obj, dict):
        return obj.get(key, default)
    getter = getattr(obj, "get", None)
    if callable(getter):
        try:
            return getter(key, default)
        except TypeError:
            value = getter(key)
            return default if value is None else value
    try:
        return obj[key]
    except Exception:
        return getattr(obj, key, default)


def call_generate(req: dict[str, Any]) -> dict[str, Any]:
    prompt = req.get("prompt")
    if not prompt:
        raise ValueError("prompt is required")

    messages = [{"role": "user", "content": [{"text": prompt}]}]
    reference_image = req.get("reference_image")
    if reference_image:
        messages[0]["content"].insert(0, {"image": resolve_reference_image(reference_image)})

    response = ImageGeneration.call(
        model=MODEL_NAME,
        messages=messages,
        size=req.get("size", DEFAULT_SIZE),
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        negative_prompt=req.get("negative_prompt"),
        style=req.get("style"),
        seed=req.get("seed"),
    )

    output = _get_field(response, "output", response.output if hasattr(response, "output") else None)
    choices = _get_field(output, "choices", [])
    if not choices:
        raise RuntimeError(f"No choices returned by DashScope: {response}")
    message = _get_field(choices[0], "message", {})
    content = _get_field(message, "content", [])
    image_url = None
    for item in content:
        if isinstance(item, dict) and item.get("image"):
            image_url = item["image"]
            break

    if not image_url:
        raise RuntimeError("No image URL returned by DashScope")

    usage = _get_field(response, "usage", response.usage if hasattr(response, "usage") else {})
    return {
        "image_url": image_url,
        "width": _get_field(usage, "width"),
        "height": _get_field(usage, "height"),
        "seed": req.get("seed"),
    }


def download_image(image_url: str, output_path: Path) -> None:
    output_path.parent.mkdir(parents=True, exist_ok=True)
    with urllib.request.urlopen(image_url) as response:
        output_path.write_bytes(response.read())


def main() -> None:
    parser = argparse.ArgumentParser(description="Generate image with qwen-image-max")
    parser.add_argument("--request", help="Inline JSON request string")
    parser.add_argument("--file", help="Path to JSON request file")
    default_output_dir = Path(os.getenv("OUTPUT_DIR", "output")) / "ai-image-qwen-image" / "images"
    parser.add_argument(
        "--output",
        default=str(default_output_dir / "output.png"),
        help="Output image path",
    )
    parser.add_argument("--print-response", action="store_true", help="Print normalized response JSON")
    args = parser.parse_args()

    _load_env()
    _load_dashscope_api_key_from_credentials()
    if not os.environ.get("DASHSCOPE_API_KEY"):
        print(
            "Error: DASHSCOPE_API_KEY is not set. Configure it via env/.env or ~/.alibabacloud/credentials.",
            file=sys.stderr,
        )
        print("Example .env:\n  DASHSCOPE_API_KEY=your_key_here", file=sys.stderr)
        print(
            "Example credentials:\n  [default]\n  dashscope_api_key=your_key_here",
            file=sys.stderr,
        )
        sys.exit(1)

    req = load_request(args)
    result = call_generate(req)
    download_image(result["image_url"], Path(args.output))

    if args.print_response:
        print(json.dumps(result, ensure_ascii=True))


if __name__ == "__main__":
    main()