Good things take shape
Text prompt · 816 × 1024 px
View prompt and settings ↗WORDS, IMAGES & COMPOSITION
MOSS Image AI Poster Generator
Create a poster by describing the scene and quoting the words that belong in the image. Use a text prompt for a simple composition or a JSON layout to specify separate regions for a headline and subject.
Real MOSS-Image SFT examples
These are selected images generated with this studio’s model service. Open a case for its original PNG, actual input and generation settings.
A Chinese flower-shop poster
Text prompt · 816 × 1024 px
View prompt and settings ↗
A headline and vase, placed with JSON
JSON layout · 1024 × 1024 px
View prompt and settings ↗
Make room for play
Text prompt · 816 × 1024 px
View prompt and settings ↗Write a poster brief that includes the actual copy
An event poster needs more than a visual style. Include the event name, date, location and any supporting line you want rendered. Keep each text block short, and distinguish the exact words from instructions about their appearance.
A clean flat graphic poster, warm ivory background, very large elegant black serif typography reading exactly "GOOD THINGS TAKE SHAPE" arranged in four balanced lines, a single burnt orange circle in the lower right, refined Swiss editorial composition, no other words, no mockup.How to create a poster
1. Name the poster and its audience
Say whether you need an event announcement, a product promotion or an editorial poster. Describe the focal subject and the setting. A flat poster and a photographed poster mockup are different requests; state which one you want.
2. Quote the headline and supporting lines
Put the intended headline in quotes. Give the date and location their own lines, and describe their relative size. Avoid putting optional wording into the prompt unless you want it visible in the image.
3. Choose text prompting or a JSON layout
A text prompt can describe a large title above one subject. For multiple text blocks, use JSON text items with separate boxes. Keep object descriptions separate from the words to render.
4. Generate, proofread and download
Review the full-size image for spelling, unwanted words, line breaks and important dates. Adjust a crowded brief before trying again. Download the PNG once the result meets your needs.
What to check before using the image
- Does the headline match the words you entered, including punctuation?
- Are the date and location readable at the intended display size?
- Does the subject leave enough space around the text?
The original result is the evidence for a case. A prompt describes the intended output; it does not guarantee every character or position in another generation.
Text prompts and JSON layouts
Natural-language prompts describe the scene and exact words together. A JSON layout separates the scene summary from text and object items, each with a requested box. This studio’s layout mode uses a 1024 × 1024 canvas and centered [top, left, bottom, right] coordinates.
See the layout workflow for a complete JSON example, or the prompt guide for wording tips. Format references: OpenMOSS project and official user guide.
Free image and credit rates
Your first Standard image is free, without a visible watermark and with no sign-in or card required. The published credit rates are 1 credit per Standard image and 2 per HD image. Review pack prices and output sizes before choosing a pack.
Questions about posters
Can I make a poster without writing JSON?
Yes. Start with a text prompt, quote the headline and describe where it belongs. JSON is an option when you need to specify multiple text or object regions.
Can MOSS Image AI put Chinese and English on one poster?
You can request both languages and explain which should be larger. Review every line in the result; language support does not guarantee perfect spelling or placement.
Does loading an example generate an image immediately?
No. It fills the prompt and settings. You can edit the input before pressing Generate image. Your first Standard image is free.