vpick-image-generatorMulti-model AI image generation on a visual canvas. Supports Midjourney (relaxed/fast/turbo, v7.0, 4-image grid), Grok Imagine (6 images per call, auto I2I),...
Install via ClawdBot CLI:
clawdbot install snoopyrain/vpick-image-generatorGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
upload → https://example.com/reference.jpgCalls external URL not in known-safe list
https://vpick-doc.10xboost.org/guide/mcp-connection.htmlAI Analysis
The skill sends user prompts and uploaded images to third-party AI providers via VPick's documented server, which is consistent with its stated purpose of image generation. While there's an unknown data sink reference to 'example.com' in the signals, this appears to be placeholder/example text rather than actual malicious exfiltration.
Audited Apr 16, 2026 · audit v1.0
Generated May 9, 2026
Marketing teams can use VPick to quickly generate visual concepts for ad campaigns, social media posts, and product mockups. With support for multiple models like Midjourney and nano-banana-2, they can iterate on styles and compositions in minutes.
Animators and game designers can generate character references from white-background prompts, ensuring clean isolation for later use in video generation or multi-shot sequences. Multiple angles (front, side, 3/4) can be created consistently.
Content creators can use Grok Imagine's budget-friendly bulk generation to produce up to 6 images per call, enabling high-volume visual assets for platforms like Instagram or TikTok. Aspect ratio controls ensure platform-optimized output.
Designers can explore multiple visual directions for products by combining text prompts with reference images (up to 10) for style or subject guidance. Seedream 5.0 HD provides ultra-high-resolution renders for detailed reviews.
Filmmakers and videographers can generate storyboard frames using consistent character references across scenes. The generated images can be directly connected to video generation nodes for seamless pre-visualization.
Offer new users $1 free credit upon signup, then charge per image generation at varying rates per model. This lowers the barrier to entry while monetizing heavy users.
License VPick's infrastructure to agencies or enterprises that want to embed AI image generation into their own tools, with custom branding and billing integration.
Provide dedicated instances with custom workflows (e.g., automated batch generation, team collaboration) for large organizations needing consistent visual content at scale.
💬 Integration Tip
Start by connecting a Text node to the Image Generator node to dynamically feed prompts, then upload reference images via URL and link them using @NodeLabel syntax.
Scored May 9, 2026
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.
Create, inspect, process, and optimize image files and visual assets with reliable format choice, resizing, compression, color-profile, metadata, and platfor...
使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。
Generate images using Qwen Image API (Alibaba Cloud DashScope). Use when users request image generation with Chinese prompts or need high-quality AI-generated images from text descriptions.