jimeng-image-gen即梦 AI 图片生成技能(火山引擎图片生成 4.0)。当用户想要 AI 生成图片、文生图、图生图、 字体设计、海报制作时使用。支持场景: - "帮我生成一张图片:..." - "用即梦画一张 16:9 的科技感壁纸" - "字体设计:新年快乐,红色背景" - "把这张图的背景换成星空" - "生成一组表情包" -...
Install via ClawdBot CLI:
clawdbot install ken0521/jimeng-image-genGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://visual.volcengineapi.com?Action=CVSync2AsyncSubmitTask&Version=2022-08-3Calls external URL not in known-safe list
https://...AI Analysis
The skill sends user prompts and images to the documented, legitimate VolcEngine (ByteDance) API for image generation, which is consistent with its stated purpose. No credential harvesting, hidden instructions, or obfuscation is present. The primary risk is the standard dependency on a third-party service's data handling policies.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 22, 2026
Agencies and brands can use this skill to create high-quality 4K images for social media ads, promotional posters, and banner designs. It supports text-to-image for generating visuals from campaign slogans and image-to-image for editing existing assets, such as swapping backgrounds to match seasonal themes, reducing reliance on graphic designers.
Online sellers can generate product mockups, lifestyle images, and promotional graphics for listings and websites. The font design mode is ideal for creating sale banners with custom text like '618大促' and themed illustrations, while image-to-image helps modify product photos by changing backgrounds or adding effects to enhance visual appeal.
Content creators, bloggers, and media companies can produce custom images for articles, videos, and thumbnails. The skill enables generating tech-themed wallpapers, emoticon sets for social engagement, and artistic visuals like Chinese landscape paintings, supporting various aspect ratios to fit different platforms and devices.
Designers and freelancers can leverage this for rapid prototyping, font-based artwork, and client projects such as logo concepts or event posters. It offers cost control with --force-single for budget-friendly iterations and handles tasks like background replacement, streamlining workflows in graphic design and illustration.
Volcengine charges based on the number of generated images, with users paying per output. This model encourages efficiency through features like --force-single to limit costs, making it scalable for both small projects and high-volume needs without upfront fees, aligning with cloud-based AI service trends.
Businesses can integrate this skill into their internal tools or customer-facing platforms, such as marketing automation software or e-commerce sites. By embedding AI image generation, they offer enhanced services, potentially charging clients for premium features or upselling custom visuals, driving value through automation and creativity.
Offering a free tier with limited usage or lower resolutions (e.g., 2K) to attract developers and small businesses, then monetizing through paid plans for higher limits, 4K output, and priority support. This fosters adoption in the Chinese market, encouraging community contributions and plugin development for broader tool integration.
💬 Integration Tip
Ensure Node.js is installed and set the JIMENG_ACCESS_KEY and JIMENG_SECRET_KEY environment variables securely before use to authenticate with Volcengine's API.
Scored Jun 19, 2026
Generate images using multiple AI models — Midjourney (via Legnext.ai), Flux, Nano Banana Pro (Gemini), Ideogram, Recraft, and more via fal.ai. Intelligently...
Perform image manipulation tasks like background removal, resizing, format conversion, rounding corners, watermarking, and color adjustments using ImageMagic...
A specialized skill for generating high-quality, consistent children's bilingual picture books using 'banana nano'. Supports 18 visual styles across 4 catego...
从图片中提取表格数据并输出为表格和CSV格式;当用户需要从图片提取表格数据、识别表格内容或导出CSV时使用;触发条件:试验图片表格提取,图片表格提取,试验图片数据提取,提取图片数据,提取试验数据
Generate or edit images with Gemini using the Google GenAI SDK. Use when the user asks to create, transform, render, or save one or more images in an OpenCla...
提供图片生成能力:输入文本描述生成图片,可附加风格提示词。支持 1-4 张图片生成,按图片尺寸对应点数计费。Authorization 使用本系统发放的 Bearer Token。