XunLMove cross-border work forward
中文

AI PROMPT GENERATOR / SD · MIDJOURNEY · FLUX

AI Image Prompt Generator

Pick tags, set weights, and get a prompt in the format your model expects, including product photos.

Generated locally · nothing uploaded
Picked tags

Recently copied

    YOUR NEXT STEP

    Finish your materials, then connect the rest of your work

    Use image and document features under their stated free limits. Create a company account for website monitoring, business inquiries and team notifications, or discuss your workflow with us.

    Create company accountExplore ProContact us

    New companies receive a 14-day Pro trial, with no card required. Trials exclude the paid monthly credit grant.

    Already have an account? Open your workspace →

    How to use it

    1. Choose your model and aspect ratio.
    2. Write the main subject, then pick scene, style, character, clothing and pose tags; press + on the important ones.
    3. Copy the prompt and negative prompt into Stable Diffusion, Midjourney or your image tool.

    Frequently asked questions

    How do prompts differ between models?

    Stable Diffusion expects comma-separated tags with weights such as (sunset:1.3) plus a negative prompt; Midjourney uses --ar for aspect ratio and --no to exclude things; Flux, DALL·E, GPT image and Gemini understand full sentences best; Chinese models work best with Chinese descriptions. The tool converts to the right format for the model you pick.

    How do weights work?

    Use + / − on a picked tag: 1.0 is neutral, 1.2–1.5 makes it stronger and below 1 weaker. Stable Diffusion gets (tag:1.3); Midjourney turns strong tags into ::2; natural-language models move strong tags to the front of the sentence.

    Can I use it for product photos?

    Yes. Switch to Product photo, enter the product, material and colour, and pick a white background, lifestyle, factory or festive scene to get a photorealistic prompt. To generate the images and ad copy directly, use XunL's AI ad images.

    Why are there no adult tags?

    The tool provides safe-for-work tags only; adult content and anything involving minors are not offered.

    AI image prompt generator practical guide and common questions

    What does an AI image prompt generator do?

    The same selection is converted per model: comma tags with (tag:weight) for Stable Diffusion, --ar, --no and ::2 for Midjourney, full English sentences for Flux / DALL·E / Gemini and Chinese for Chinese models; product mode writes a photorealistic description from the scene and angle.

    Who is this for, and when is it useful?

    Designers, marketers and online sellers using Stable Diffusion, Midjourney, Flux or Chinese image models who are unsure how to write prompts and want good images quickly.

    How do I use this AI image prompt generator?

    Choose the model and aspect ratio, write the subject, pick and weight tags for scene, style, character, clothing and pose from nearly 700 bilingual tags, or use product-photo mode with product, material and scene, then copy the prompt and negative prompt.

    How should I interpret the results?

    A prompt sets direction but does not guarantee the result, and repeated runs differ; syntax can change as models update. Only safe-for-work tags are offered.

    Where is the work performed, and which services receive data?

    Prompts are assembled in your browser with no AI call or upload; recently copied prompts stay on this device.