Words that belong in the picture.
Explore Chinese and English lettering for posters, labels, and visual stories. Always proofread generated text before sharing. Chinese text guide →
Let your ideas take shape.
Your next creation starts with a few words.
Give your imagination somewhere to grow.
Concept illustrations, not model outputs. Select a card to try its prompt.
MOSS-Image is an image model from OpenMOSS. This independent studio brings its creative possibilities into a simple place to start.
Meet your new creative toolkitExplore Chinese and English lettering for posters, labels, and visual stories. Always proofread generated text before sharing. Chinese text guide →
Switch to JSON layout to describe where text and objects should go. A more intentional starting point for your composition. JSON Layout guide →
Start in the browser, then explore official weights and ComfyUI workflows when you want a more hands-on creative process.
Describe the subject, mood, and light. Add exact words in quotes if your image needs text.
Choose a canvas shape, or use a JSON layout to guide the placement of specific elements.
Generate, review, and download. Refine your prompt to explore another direction.
A first look at the studio.
Credits never expire.
Up to 160 with rollover.
About $0.15 per image.
Prices are in USD. Taxes may apply. Subscription credits follow the stated billing cycle; one-time pack credits do not expire. See the Refund Policy.
MOSS-Image is a 5B-parameter image-generation model family from OpenMOSS, with Base and SFT checkpoints. You can explore its official code and model cards through our guides. This site is independently operated.
Yes. A verified account starts with three images. Credit packs and subscriptions add more images when you need them, subject to the shared daily service budget.
One image credit is reserved when a request starts. A technical failure, missing image, or safety block restores that credit automatically. Artistic variation is part of image generation, so review every result.
Yes. JSON layout mode accepts a scene description and bounding boxes for text and objects. It validates your structure and canvas bounds before submitting.
Prompts and settings are sent to fal.ai for processing, and results are hosted by that provider. Account, quota, and billing records are handled separately; see the Privacy page.