Jimeng Text-to-Image Prompt Refinement
Paste the following prompt into your AI chat to install this skill:
Please install @user_c1d16043/jimeng-prompt-text2image according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem
Jimeng text-to-image prompts often fail because the description is flat: subject, scene, style, lighting, and composition are mixed together. Directly translated English prompts can be misread, hex values like #ff2121 may be rendered as literal text, and prompt order plus aspect ratio can change visual weighting.
How It Works
@user_c1d16043/jimeng-prompt-text2image focuses on drafting and refining prompts rather than executing image generation. It first identifies a scenario category such as portrait, landscape, product, or abstract art, then loads only the relevant vocabulary files, for example word-library/subject.md, word-library/lighting.md, and word-library/composition.md. When color is involved, it searches Chinese traditional, Pantone, RAL, or modern color schemes for natural color names, avoiding hex codes in the final prompt.
It also applies model-version guidance for Jimeng 2.1, 3.0, 3.1, 4.0, 4.5, and 5.0, using a workflow of scenario matching, component building, writing rules, and validation.
Boundaries
Use it for text-to-image prompt writing, optimization, and translation. It does not run image-generation CLI commands, create video prompts, or handle image-to-image editing prompts. Keep in mind that Jimeng is less reliable with negations, character consistency across generations, strong style keywords, and aspect-ratio-sensitive composition. Prefer Chinese prompts and natural color names.
Use Cases
- Draft a Jimeng e-commerce poster prompt by separating product details, background, lighting, and composition into actionable descriptions for a 16:9 banner while avoiding hex color values.
- Turn a client's Chinese-style portrait request into a Jimeng prompt using subject, lighting, and Chinese traditional color names instead of hex codes.
- Adapt an English landscape description into a Chinese Jimeng prompt, then reorder strong style keywords to control composition weight for 9:16.
- Refine a prompt for Jimeng 3.0 or 5.0 by applying version-specific style, material, and validation checklist guidance before image generation and avoid negations.
Best For
- E-commerce visual designer who needs to turn product benefits, scenes, and palettes into reusable Jimeng prompts.
- Freelance designer handling image-generation briefs who needs to convert client notes into structured text-to-image prompts.
- Brand content marketer producing posters, covers, and social visuals who needs consistent style and color wording.
- Visual engineer prototyping Jimeng outputs who needs to compare model versions and check color-name usage.
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.
Generate and validate JianYing drafts from storyboard JSON with narrated commentary, original-sound preservation, timing checks, and draft inspection.
Restyle a short video into a new visual style while preserving core elements such as characters, actions, and composition, suitable for various creative conversions like anime, illustration, ink wash, etc.