How to Use MOSS Image in Perplexity
MOSS Image creates text-heavy graphics such as bilingual posters, signs, and illustrated explainers. It runs MOSS-Image-SFT, with control over where text and objects appear through structured layout prompts.
Prompts to try with MOSS Image in Perplexity
Copy an example into Perplexity, or ask in your own words.
Use MOSS Image to make a 1024 × 1536 community book-swap poster. Put 'BOOK SWAP' on the first line and '旧书交换' on the second, with an illustration of stacked books underneath. Use dark lettering on a white background and leave the bottom quarter empty.
Create a 1024 × 1024 bakery notice with MOSS Image. Show exactly 'Fresh bread' above '每日新鲜面包', with a watercolor loaf centered below the text. Keep both lines separate and make the lettering the main focus.
Use MOSS Image to create a 1536 × 1024 classroom graphic showing a seed, a seedling, and a mature sunflower from left to right. Label them exactly 'Seed', 'Seedling', and 'Flower'. Use a simple illustrated style and keep the labels below their objects.
Make a 1024 × 1536 book cover concept with MOSS Image. The exact title is 'The Last Lighthouse' and the author is 'Maya Reed'. Show a photorealistic lighthouse in fog, put the title at the top on two lines, and place the author name at the bottom.
Use MOSS Image to create a 1536 × 1024 anime-style travel illustration of a quiet mountain railway at sunrise. Place the exact words 'Take the slow route' in the open sky, with 'Take the' on the first line and 'slow route' on the second.
How to set up MOSS Image in Perplexity
Pick the way that suits you. Each takes about two minutes.
Use the Perplexity connector
- Add a remote connector
In Perplexity, open Plugins in the sidebar (or Customize › Connectors if you don't see Plugins yet). Choose Add custom › Add MCP connector, then Remote. Name it Spiral and paste this MCP server URL:
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Select the Spiral card on the Plugins page to start sign-in. Spiral opens: sign in, pick the organization and click Authorize. No API key.
Use the Spiral skill
- Send Perplexity this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run MOSS Image
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "fal-ai/moss-image", "input": { "prompt": "A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small sticky note on the refrigerator door is handwritten in…" } }'
Then paste one of the prompts above: Perplexity finds MOSS Image on Spiral, shows the price and runs it.
MOSS Image providers and prices
Spiral runs MOSS Image through fal. Open a card for today's price, with every fee included.
$0.065 per megapixel. image_size presets count as 1 MP; custom sizes round up to whole megapixels. Billed on num_images, default 1.
Settings you can ask for
MOSS Image works from your prompt. Ask Perplexity for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | Negative prompt. When empty, guidance uses transformer layer skipping for the negative branch. | |
| Enable prompt expansion | on or off | on | Plan a structured layout from your prompt before generation. Preserves requested visible text and uses the selected image dimensions. If enhancement is unavailable, uses the original prompt. |
| Number of inference steps | 1 to 100 | 50 | Number of denoising steps. |
| Guidance scale | 0 to 10 | 3 | Classifier-free guidance scale. |
| Seed | a whole number | Random seed for reproducible generation. | |
| Number of images | 1 to 4 | 1 | Number of images to generate. |
| Output format | jpeg, png, or webp | jpeg | Output image format. |
Every API field of MOSS Image · Text to Image is on its tool page: open its card above.
What can you do with MOSS Image in Perplexity?
Turn a written idea into a poster, sign, or illustration with Chinese and English text placed inside the image. A chat app can help settle the wording and composition before asking for the graphic.
Bilingual event posters
Create a new poster from approved Chinese and English copy, with separate areas for the headline, illustration, date, and location.
Educational explainers
Turn a short explanation into an illustrated graphic with a title, labeled objects, and clearly separated reading sections. Check the labels against the source material.
Store signs and notices
Draft opening-hours signs, pickup instructions, and bilingual notices from exact text. Specify line breaks and the relative size of each message.
Product launch graphics
Generate promotional concepts from a written product description, a short headline, and a planned composition. Review the depicted product details before use.
Editorial illustrations
Create an article illustration from a written brief, using a photorealistic or anime treatment and deliberate space for a short title.
Book cover concepts
Explore cover compositions with an exact title, author name, and described scene. Specify the hierarchy and placement of the text before generating.
Social campaign concepts
Generate separate square and portrait concepts from the same approved message. Adapt the composition to each canvas rather than assuming a crop will preserve the text.
More on MOSS Image and Perplexity
Overview
MOSS Image in other agents
Questions about MOSS Image in Perplexity
Can Perplexity use MOSS Image?
Yes. Add Spiral to Perplexity as an MCP server, and Perplexity can find and run MOSS Image like any built-in tool.
How much does MOSS Image cost in Perplexity?
$0.065 per megapixel. `image_size` presets count as 1 MP; custom sizes round up to whole megapixels. Billed on `num_images`, default 1. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Perplexity plan is separate.
Do I need a fal account to use MOSS Image in Perplexity?
No. Spiral runs MOSS Image on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up MOSS Image in Perplexity?
About two minutes: add a remote connector, then sign in to Spiral and approve.
Does Perplexity wait while MOSS Image runs?
MOSS Image runs in the background. Perplexity starts the run, checks on it and gives you the image when it's ready.
What is MOSS Image useful for?
Consider MOSS Image for graphics where words and composition both matter: bilingual posters, signs, illustrated explainers, and promotional concepts. Chinese and English text rendering and controlled element placement are its documented specialties.
Can MOSS Image put Chinese and English in the same graphic?
MOSS Image specializes in both Chinese and English text rendering. Provide the exact copy for each language and describe where each text block should appear.
How should I prompt MOSS Image for a specific layout?
Describe the scene, exact visible text, and positions of the main elements. MOSS Image accepts natural language and structured JSON layouts, so an agent can turn a detailed brief into a layout prompt.
How large can MOSS Image outputs be?
Each dimension can range from 512 to 2048 pixels, rounded to a multiple of 16. A 1024 × 1536 poster or 1536 × 1024 landscape graphic fits those limits.
Can MOSS Image edit a photo or follow an uploaded reference?
MOSS Image does not directly condition generation on reference images or support image editing. Use it to generate a new composition from a text description.
Start using MOSS Image in Perplexity
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Perplexity:
set up https://spiral.ai/SKILL.md


