qwen-image-skillGenerate images using Alibaba Cloud Bailian Qwen-Image and Z-Image models (通义千图文生图 + 人像照片模型)
Install via ClawdBot CLI:
clawdbot install irron/qwen-image-skill基于阿里云百炼的文图生成技能，智能识别场景自动选择最佳模型：
export DASHSCOPE_API_KEY="sk-xxx"DASHSCOPE_API_KEY: sk-xxx地域注意：北京和新加坡地域 API Key 不互通
| 模型 | 描述 | 最佳场景 |
|------|------|----------|
| qwen-image-max | 最佳质量，减少AI痕迹，文字渲染优秀 | 漫画、插画、图文设计、风景、静物 |
| qwen-image-plus | 质量与速度平衡 | 通用场景 |
| qwen-image | 基础模型 | 快速生成 |
| z-image-turbo | 人像专精，胶片质感，真实感强 | 人像照片、人像写真、film grain效果 |
| 尺寸 | 比例 | 说明 |
|------|------|------|
| 1664*928 | 16:9 | 横向宽屏（通用默认）|
| 1472*1104 | 4:3 | 标准比例 |
| 1328*1328 | 1:1 | 方形 |
| 1104*1472 | 3:4 | 竖向 |
| 928*1664 | 9:16 | 手机竖屏 |
| 1120*1440 | 4:5 | 人像推荐 |
直接写提示词，自动识别场景并选择最佳模型：
# 人像类 → 自动使用 z-image-turbo
python scripts/generate.py "短发少女，清新自然风格，微笑"
# 通用类 → 自动使用 qwen-image-max
python scripts/generate.py "七龙珠孙悟空对战比克大魔王，漫画风格"
# 含film grain关键词 → 自动使用 z-image
python scripts/generate.py "胶片感，Kodak Portra 400风格的人像"python scripts/generate.py "prompt" \
--model z \ # 强制指定模型 (z/qwen/auto)
--size 1328*1328 \ # 图片尺寸
--prompt-extend \ # 开启提示词扩展
--no-watermark \ # 禁用水印
--output my-image.png # 输出路径以下关键词会触发自动选择 z-image-turbo：
人物类：人、女、男、少女、帅哥、美女、肖像、人物、face、facial
照片/胶片类：photo、photograph、film grain、analog、Kodak、胶片、portra、cinematic、photorealistic、真实、写真人像
python scripts/generate.py "东亚年轻女性，户外雪地场景，film grain效果，胶片质感"python scripts/generate.py "七龙珠孙悟空对战比克大魔王，漫画风格，能量波爆炸，天空背景"python scripts/generate.py "一副对联，上联：智启千问，下联：机道为善，横批：人机共生"--prompt-extend 可以让AI自动优化你的描述Qwen-Image Skill - 国产文生图利器 🇨🇳
Generated Mar 1, 2026
Generates high-quality, photorealistic portraits with film grain effects, ideal for creating profile pictures, artistic portraits, or marketing visuals. It automatically selects the z-image-turbo model for enhanced facial details and skin textures.
Produces comic-style images with complex text rendering, suitable for creating manga panels, promotional artwork, or educational materials. It uses qwen-image-max for superior Chinese character integration and artistic styles.
Creates visually appealing images for advertisements, posters, or social media posts, leveraging automatic model selection for optimal quality. Supports multiple aspect ratios to fit various media formats.
Enables users to generate custom images based on descriptive prompts, useful for hobbyists, content creators, or small businesses needing unique visuals. Features like prompt extension help refine outputs.
Offers tiered subscription plans for API usage, charging based on the number of image generations or model calls. This provides recurring revenue and scales with user demand for image creation services.
Provides a free tier with limited generations and premium features like higher resolution or advanced models for a per-image fee. This attracts a broad user base while monetizing heavy usage.
Sells customized licenses to businesses for integrating the skill into their platforms, such as marketing tools or design software. Includes support, SLAs, and bulk pricing for high-volume needs.
💬 Integration Tip
Ensure the DASHSCOPE_API_KEY is securely configured via environment variables or TOOLS.md, and test with sample prompts to verify automatic model selection works as expected.
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Capture frames or clips from RTSP/ONVIF cameras.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。
AI image generation powered by CellCog. Create images, edit photos, consistent characters, product photography, reference-based images, sets of images, style transfer. Professional image creation with AI.