AI Agent Hub
Back to skills
Jimeng Text-to-Image Prompt Refinement icon

Jimeng Text-to-Image Prompt Refinement

Design & Media Updated 2026.08.30

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.