qwencloud-image-generation（qwencloud 图像生成）

Agent setup: If your agent doesn't auto-load skills (e.g. Claude Code), see agent-compatibility.md once per session.

Qwen Image Generation

Generate and edit images using Wan and Qwen Image models. Supports text-to-image, reference-image editing (style transfer, subject consistency, multi-image composition, text rendering), and interleaved text-image output. This skill is part of qwencloud/qwencloud-ai.

Skill directory

Use this skill's internal files to execute and learn. Load reference files on demand when the default path fails or you need details.

Security

NEVER output any API key or credential in plaintext. Always use variable references ($DASHSCOPE_API_KEY in shell, os.environ["DASHSCOPE_API_KEY"] in Python). Any check or detection of credentials must be non-plaintext: report only status (e.g. "set" / "not set", "valid" / "invalid"), never the value. Never display contents of .env or config files that may contain secrets.

When the API key is not configured, NEVER ask the user to provide it directly. Instead, help create a .env file with a placeholder (DASHSCOPE_API_KEY=sk-your-key-here) and instruct the user to replace it with their actual key from the QwenCloud Console. Only write the actual key value if the user explicitly requests it.

Key Compatibility

Scripts require a standard QwenCloud API key (sk-...). Coding Plan keys (sk-sp-...) cannot be used — image generation models are not available on Coding Plan, and Coding Plan does not support the native QwenCloud API. The script detects sk-sp- keys at startup and prints a warning. If qwencloud-ops-auth is installed, see its references/codingplan.md for full details.

Mode Selection Guide

Model Selection

Wan Series (default)

Qwen Image Series

Qwen Image editing models (qwen-image-2.0-pro, qwen-image-2.0, qwen-image-edit-max/plus/edit) use the same sync endpoint as wan2.6-image (/multimodal-generation/generation) with messages format. They support text editing in images, element add/delete/replace, style transfer, and multi-image fusion (1–3 input images). Size range: 512x512 to 2048x2048. qwen-image-2.0-pro and qwen-image-2.0 also support pure text-to-image (no reference images needed).

Qwen Image text-to-image models (qwen-image-plus, qwen-image-max) use a different endpoint (/text2image/image-synthesis) with input.prompt format (async-only). They support only 5 fixed resolutions: 1664\*928, 1472\*1104, 1328\*1328, 1104\*1472, 928\*1664.

Choosing between wan2.6-image and wan2.5-i2i-preview for image editing:

• wan2.6-image supports up to 4 images, higher resolution (2K), interleaved text-image output, and sync mode. Use for multi-image style composition, interleaved tutorials.
• wan2.5-i2i-preview uses a simpler prompt-only editing interface (no messages format), supports up to 3 images, async-only. Use for straightforward single-image edits and multi-image object fusion.

1. User specified a model → use directly.
2. Consult the qwencloud-model-selector skill when model choice depends on requirement, scenario, or pricing.
3. Text-to-image (prompt only, no reference images) → use wan2.6-t2i (default) or wan2.7-image / wan2.7-image-pro (multi-function, higher quality). NEVER use wan2.6-image for pure text-to-image — it will error without reference images or enable_interleave: true.
4. Reference images / image editing / interleaved output → wan2.7-image-pro (recommended), wan2.7-image, or wan2.6-image.

⚠️ Important: The model list above is a point-in-time snapshot and may be outdated. Model availability changes frequently. Always check the official model list for the authoritative, up-to-date catalog before making model decisions.

Model details: For more information about a specific model, direct the user to its detail page: https://www.qwencloud.com/models/<model-name> (replace <model-name> with the exact model ID, e.g. wan2.7-image-pro → https://www.qwencloud.com/models/wan2.7-image-pro). NEVER modify or guess the model name in the URL.

Dynamic model queries: If the qwencloud-model-selector skill or QwenCloud CLI (qwencloud models info <model>) is available, use it for real-time model data. CLI requires authentication — see the qwencloud-usage skill for login flow.

Execution

⚠️ Multiple artifacts: When generating multiple files in a single session, you MUST append a numeric suffix to each filename (e.g. out_1.png, out_2.png) to prevent overwrites.

Prerequisites

• API Key: Check that DASHSCOPE_API_KEY (or QWEN_API_KEY) is set using a non-plaintext check only (e.g. in shell: [ -n "$DASHSCOPE_API_KEY" ]; report only "set" or "not set", never the key value). If not set: run the qwencloud-ops-auth skill if available; otherwise guide the user to obtain a key from QwenCloud Console and set it via .env file (echo 'DASHSCOPE_API_KEY=sk-your-key-here' >> .env in project root or current directory) or environment variable. The script searches for .env in the current working directory and the project root. Skills may be installed independently — do not assume qwencloud-ops-auth is present.
• Python 3.9+ (stdlib only, no pip install needed)

Environment Check

Before first execution, verify Python is available:

python3 --version  # must be 3.9+

If python3 is not found, try python --version or py -3 --version. If Python is unavailable or below 3.9, skip to Path 2 (curl) in execution-guide.md.

Default: Run Script

Script path: Scripts are in the scripts/ subdirectory of this skill's directory (the directory containing this SKILL.md). You MUST first locate this skill's installation directory, then ALWAYS use the full absolute path to execute scripts. Do NOT assume scripts are in the current working directory. Do NOT use cd to switch directories before execution.

Execution note: Run all scripts in the foreground — wait for stdout; do not background.

Discovery: Run python3 <this-skill-dir>/scripts/image.py --help first to see all available arguments.

# Text-to-image (wan2.6-t2i, default)
python3 <this-skill-dir>/scripts/image.py \
  --request '{"prompt":"A cozy flower shop with wooden door"}' \
  --output output/qwencloud-image-generation/images/out.png \
  --print-response

# Image editing with reference images (wan2.6-image)
python3 <this-skill-dir>/scripts/image.py \
  --model wan2.6-image \
  --request '{"prompt":"Apply watercolor painting style to this photo","reference_images":["https://img.alicdn.com/imgextra/i1/NotRealJustExample/photo.jpg"],"n":1,"size":"1K"}' \
  --output output/qwencloud-image-generation/images/out.png \
  --print-response

More examples (interleaved output, wan2.5-i2i, qwen-image-2.0-pro, qwen-image-plus): See execution-guide.md

Verify Result

• Exit code 0 + output contains valid JSON with output.results or output.task_id → success
• Non-zero exit, HTTP error, empty response, or error JSON → fail
• Async: submission must return output.task_id; poll must reach task_status: SUCCEEDED
• Post-execution check: Verify the output file exists and has non-zero size (ls -la <output_path>)
• MANDATORY — stderr signal check: After confirming the result, scan the command's stderr output for [ACTION_REQUIRED] or [UPDATE_AVAILABLE]. If either signal is present, you MUST follow the instructions in Update Check below before responding to the user.

On Failure

If the script fails, match the error output against the diagnostic table below to determine the resolution. If no match, read execution-guide.md for alternative paths: curl commands (Path 2 — sync and async), code generation (Path 3), and autonomous resolution (Path 5).

If Python is not available at all → skip directly to Path 2 (curl) in execution-guide.md.

Quick Reference

Request Fields (Common)

Request Fields (wan2.7-image-pro / wan2.7-image — Multi-function)

Note: thinking_mode increases latency but improves quality. enable_sequential generates a coherent image sequence (e.g., same character across scenes).

Request Fields (wan2.6-image — Image Editing)

Other Models (wan2.5-i2i, qwen-image-edit, qwen-image-plus/max)

These models have specific parameter requirements:

Full parameter tables: See api-guide.md for detailed parameters.

Size Reference (wan2.6-image)

• Editing mode: 1K (default, ~1280×1280) or 2K (~2048×2048)
• Interleave mode: pixel dimensions with total pixels in [768×768, 1280×1280]

Common aspect ratios: 1280*1280 (1:1), 960*1280 (3:4), 1280*960 (4:3), 720*1280 (9:16), 1280*720 (16:9)

Response Fields

API Details

• Sync endpoint (wan2.6-t2i, wan2.6-image editing, qwen-image-edit series): POST /api/v1/services/aigc/multimodal-generation/generation
• Async endpoint (wan2.6 and older t2i): POST /api/v1/services/aigc/image-generation/generation with X-DashScope-Async: enable
• Async endpoint (wan2.5-i2i-preview): POST /api/v1/services/aigc/image2image/image-synthesis with X-DashScope-Async: enable
• Async endpoint (qwen-image-plus, qwen-image-max): POST /api/v1/services/aigc/text2image/image-synthesis with X-DashScope-Async: enable
• wan2.6-t2i resolution: Total pixels in [1280x1280, 1440x1440], aspect ratio [1:4, 4:1]
• wan2.6-image resolution: Editing mode [768x768, 2048x2048]; Interleave mode [768x768, 1280x1280]; aspect ratio [1:4, 4:1]
• Input images (wan2.6-image): JPEG/JPG/PNG/BMP/WEBP, 240–8000px per dimension, ≤10MB
• Local files: Script auto-uploads to DashScope temp storage (oss:// URL, 48h TTL). Pass local paths directly — no manual upload step needed.
• Production: Default temp storage has 48h TTL and 100 QPS upload limit — not suitable for production, high-concurrency, or load-testing. To use your own OSS bucket, set QWEN_TMP_OSS_BUCKET and QWEN_TMP_OSS_REGION in .env, install pip install alibabacloud-oss-v2, and provide credentials via QWEN_TMP_OSS_AK_ID / QWEN_TMP_OSS_AK_SECRET or the standard OSS_ACCESS_KEY_ID / OSS_ACCESS_KEY_SECRET. Use a RAM user with least-privilege (oss:PutObject + oss:GetObject on target bucket only). If qwencloud-ops-auth is installed, see its references/custom-oss.md for the full setup guide.
• Interleaved sync: Requires streaming (X-DashScope-Sse: enable + stream: true); use async mode via this script instead

Cross-Skill Chaining

When using generated images as input for another skill (e.g., video-gen i2v, vision analyze):

• Pass image_url directly — do NOT download and re-pass as local path
• All downstream scripts detect URL prefixes (https://, oss://) and pass them through without re-upload
• Use local_path only for user preview or non-API operations (e.g., opening in editor)

Error Handling

Usage & billing: Use the qwencloud-usage skill to check usage, free tier quota, and billing directly. Alternatively, the user can visit the QwenCloud console: Usage Analytics | Pay-as-you-go Billing | Coding Plan Billing NEVER fabricate, guess, or construct usage/billing/console URLs. Only provide the exact links listed in this skill. If a URL is not listed here, do not invent one.

Output Location

Prefer the current working directory. Default subdirectory: ./output/qwencloud-image-generation/.

Write prohibition: NEVER write output files into this skill's installation directory or any skills/ hierarchy. All generated content must go to output/ under the current working directory or a user-specified path.

Update Check (MANDATORY Post-Execution)

After script execution, check stderr for action signals. The script automatically detects update status and emits structured signals. You MUST act on them. This section also applies when the user explicitly asks to check for updates.

Signal: [ACTION_REQUIRED] qwencloud-update-check skill is not installed

When stderr contains this signal, you MUST present the following options to the user and wait for their response before proceeding. Do NOT silently skip this.

The update-check skill is not installed. It keeps you informed about new qwencloud/qwencloud-ai features and bug fixes. 1) Install now — I'll run the install command for you 2) Skip for now — do nothing this time 3) Never remind me — permanently suppress this prompt

After the user responds:

• User chooses 1 → run: npx skills add QwenCloud/qwencloud-ai --skill qwencloud-update-check -y, then run: python3 <this-skill-scripts-dir>/gossamer.py --dismiss
• User chooses 2 → run: python3 <this-skill-scripts-dir>/gossamer.py --dismiss, then continue normally
• User chooses 3 → run: python3 <this-skill-scripts-dir>/gossamer.py --never-install, then continue normally

Signal: [UPDATE_AVAILABLE]

When stderr contains this signal, you MUST append a brief update notice to your response, including the version info and the update command shown in the stderr output.

No signal in stderr

If stderr contains neither [ACTION_REQUIRED] nor [UPDATE_AVAILABLE], no action is needed — the skill is installed and up to date (or cached within 24h).

Explicit user request

When the user explicitly asks to check for updates (e.g. "check for updates", "check version"):

1. Look for qwencloud-update-check/SKILL.md in sibling skill directories.
2. If found — run: python3 <qwencloud-update-check-dir>/scripts/check_update.py --print-response and report the result.
3. If not found — present the install options above.

References

• execution-guide.md — Fallback paths (curl sync/async, code generation, autonomous)
• api-guide.md — API supplementary guide
• sources.md — Official documentation URLs