Name: qwencloud-image-generation
Author: qwencloud

[QwenCloud] Generate and edit images using Wan and Qwen Image models. Supports text-to-image, image editing (style transfer, subject consistency, text rendering), and interleaved text-image output. TRIGGER when: user wants to create illustrations, product images, artistic designs, posters, text-to-i

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. Location Purpose scripts/image.py Default execution — sync/async, upload, download references/execution guide.md Fallback: curl (sync/async), code generation references/prompt guide.md Prompt formulas, style keywords, negative prompt, prompt extend decision references/api guide.md API supplement references/sources.md Official documentation URLs Security NEVER output any API key or credential in plaintext. Always use variable references ( $QWENCLOUD API KEY in shell, os.environ["QWENCLOUD API KEY"] in Python). The scripts accept QWENCLOUD API KEY , then QWEN API KEY , then DASHSCOPE API KEY . 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 ( QWENCLOUD API KEY=sk your key here ) and instruct the user to replace it with their actual key from the [QwenCloud Console](https://home.qwencloud.com/api keys). Only write the actual key value if the user explicitly requests it. Key Compatibility Scripts support both standard QwenCloud API keys ( sk ... ) and Token Plan keys ( sk sp ... ). Token Plan keys are automatically routed to the Token Plan endpoint for supported image models — see the [Token Plan model catalog](https://alioth intl.alicdn.com/skills info/models/references/qwencloud token plan models.md). If CDN access fails, use the [local fallback](cdn/references/qwencloud token plan models.md). Token Plan: do not use curl; always use the bundled Python script. Coding Plan keys (also sk sp prefix but purchased via Coding Plan subscription) cannot be used — image generation models are not available on Coding Plan. The script detects key type at startup and routes accordingly. If qwencloud ops auth is installed, see its references/codingplan.md for full details. Detect the API key type without exposing the key: Output Meaning token plan Token Plan key detected ( sk sp prefix) payg Standard PAYG key detected not set No API key found in environment Mode Selection Guide Before choosing a mode, fetch and read the current [QwenCloud image generation model catalog](https://alioth intl.alicdn.com/skills info/models/references/qwencloud image generation models.md). It contains the mode to model recommendations, model list, basic model information, compatibility notes, and default model. If CDN access fails, use the [local fallback](cdn/references/qwencloud image generation models.md). Model Selection 🚫 CRITICAL — Never override user specified parameters. If the user explicitly specifies a model (in prompt or request JSON), you MUST use exactly that model. Do NOT: Replace it with a "better suited" or newer model (e.g., swapping the user's wan2.6 t2i for wan2.7 image because the task "looks like a multi function job") Add parameters the user did not ask for ( thinking mode , color palette , bbox list , style hints) "Optimize" any explicit user choice Mode/Model guidance below applies only when the user has NOT specified a model . If the user specified model cannot achieve what they asked for (e.g. a hard API constraint), execute their choice as given if possible; otherwise surface the constraint to the user and let THEM decide — do not silently switch. Use the image generation model catalog linked above for current model families, defaults, recommendations, compatibility, and limits. 1. User specified a model → MANDATORY: use that exact model — do not substitute, do not "optimize", do not add unrequested parameters. 2. Consult the qwencloud model selector skill when model choice depends on requirement, scenario, or pricing. 3. No model specified → choose the current default or task specific recommendation from the model catalog. If the user's requested operation conflicts with a model's documented hard constraint, explain the constraint and let the user decide; never silently replace an explicitly selected model. ⚠️ Important : The model catalog is a point in time snapshot and may be outdated. Model availability changes frequently. Always check the [official model list](https://www.qwencloud.com/models) 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 QWENCLOUD API KEY , QWEN API KEY , then DASHSCOPE API KEY using a non plaintext check only (e.g. in shell: [ n "$QWENCLOUD 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](https://home.qwencloud.com/api keys) and set it via .env file ( echo 'QWENCLOUD 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. Note : The script auto loads .env from the current directory and the project root (in addition to any exported environment variable). A shell check showing $QWENCLOUD API KEY as "not set" does NOT mean the script will fail — it may still find the key in .env . Treat the shell check as informational only; the authoritative test is simply running the script (it exits with a clear error if no key is found anywhere). Python 3.9+ (stdlib only, no pip install needed ) Environment Check Before first execution, verify Python is available: If python3 is unavailable or below 3.9, PAYG may use Path 2 (curl) ; Token Plan must install Python 3.9+ instead. 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. More examples (interleaved output, wan2.5 i2i, qwen image 2.0 pro, qwen image plus): See [execution guide.md](references/execution guide.md) Argument Description request '{...}' JSON request body file path.json Load request from file async Force async mode; the script auto enables it where its implementation uses async. It is ignored for sync only models such as qwen image max model ID Override model (check the model catalog above for the current default) output path Save image to path (or directory for multi image output). When writing multiple images to the same directory, files are automatically named using the unique identifier from the OSS URL, preventing overwrites across runs. Explicit file paths still take priority; use distinct filenames across calls to avoid overwriting print response Print response JSON to stdout 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]( update check mandatory post execution) 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](references/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 → PAYG may use Path 2 (curl); Token Plan must install Python 3.9+. Error Pattern Diagnosis Resolution command not found: python3 Python not on PATH Try python or py 3 ; install Python 3.9+ if missing Python 3.9+ required Script version check failed Upgrade Python to 3.9+ SyntaxError near type hints Python < 3.9 Upgrade Python to 3.9+ QWENCLOUD API KEY/QWEN API KEY/DASHSCOPE API KEY not found Missing API key Obtain key from [QwenCloud Console](https://home.qwencloud.com/api keys); add to .env : echo 'QWENCLOUD API KEY=sk ...' .env ; or run qwencloud ops auth if available HTTP 401 Invalid or mismatched key Run qwencloud ops auth (non plaintext check only); verify key is valid SSL: CERTIFICATE VERIFY FAILED SSL cert issue (proxy/corporate) macOS: run Install Certificates.command ; else set SSL CERT FILE env var URLError / ConnectionError Network unreachable Check internet; set HTTPS PROXY if behind proxy HTTP 429 Rate limited Wait and retry with backoff HTTP 5xx Server error Retry with backoff PermissionError Can't write output Use output to specify writable directory Quick Reference Request Fields (Common) Field Type Description prompt string Text description of the image to generate (required; NOT for image translation) negative prompt string Content to avoid in the image (max 500 chars) size string Resolution; use the model catalog for cataloged limits and the API guide or official documentation for model specific values not listed there seed int Random seed for reproducibility [0, 2147483647] model string Model ID; check the model catalog above for the current default and supported models prompt extend bool Enable prompt rewriting (default: true; image editing mode only) enable thinking bool qwen image 3.0 only — enhanced reasoning (default: true). Only effective when prompt extend=true prompt extend mode string qwen image 3.0 only — direct (DPE, default) or agent (APE; t2i only) Request Fields (wan2.7 image pro / wan2.7 image — Multi function) Field Type Description reference images string[] 0–9 image URLs or local paths reference image string Single