AI Image Generator
Paste the following prompt into your AI chat to install this skill:
Install @user_289e1438/image-skill following https://skillhub.cn/install/skillhub.md.
About this skill
What problem it solves
This skill addresses a small but common workflow gap: a user has a brief visual idea, while direct image-generation prompts often miss light, composition, material, mood, and scene details. image-skill chains requirement interpretation, prompt expansion, image retrieval, and delivery into one reusable execution path, reducing manual English prompt polishing, API URL assembly, and image download steps.
How it works
The core flow is:
- Interpret the request: read the subject, style, mood, and scene the user wants.
- Expand the description: rewrite a short input into coherent English scene language, adding light, color, composition, texture, and background details so it can be used as a model prompt.
- Build the request: fill the English description into https://image.pollinations.ai/prompt/{prompt}?width=1024&height=1024&seed=100&model=flux&nologo=true, where width and height are fixed at 1024, seed is fixed at 100, the model is flux, and the logo is disabled.
- Download and return: fetch the generated image, send it to the user, and optionally include the expanded English description.
Boundaries and notes
It is useful for quick concept art, visual drafts, illustration-style mockups, or demo imagery. It is better suited for turning a one-line idea into a viewable visual than replacing a full image-generation pipeline. Keep in mind:
- It depends on the external image.pollinations.ai service being available, and output quality is affected by the flux model.
- The current configuration fixes size and seed, so it is not a general-purpose parameter-control setup for precise reproducibility.
- Prompt quality drives generation quality; if the input is too vague, the result may still deviate from intent.
Use Cases
- Turn a one-line product visual request into an English prompt and generate a 1024x1024 draft image.
- Prepare presentation illustrations by expanding a short theme into English light, composition, and mood details, then fetch the image.
- Create preview images from subject or scene keywords in content production and include the expanded prompt for later edits.
- Produce concept visuals before prototype review using the fixed Flux API link, download the image, and send it to stakeholders.
Best For
- Engineers preparing product demos who need to turn brief scene notes into reviewable image drafts quickly.
- Front-end engineers building content pages who need themed atmospheric illustrations for articles.
- Product managers in prototype reviews who need to expand concept notes into English scene prompts and fetch images.
- Developers maintaining internal creative tools who need to convert short user inputs into image API requests and return results.
Related Skills
Generate an interactive HTML product detail page from images and copy, with multi-product carousel, inline text editing, design controls, and PDF/JPG/PSD export support.
Enter a material name to get preview and download links for free, commercially usable video assets, with paid platform options, pricing, and search suggestions when results are limited.
A local CLI for Dreamina image and video generation, including credit checks, async submission, result queries, and task history review.
Generate and validate JianYing drafts from storyboard JSON with narrated commentary, original-sound preservation, timing checks, and draft inspection.