Words that belong in the picture.
Create posters, labels, and visual stories with Chinese or English lettering. Always proofread generated text before sharing. Open the text-in-image generator
Let your ideas take shape.

This bilingual menu prompt is already filled in below. Edit it or generate the preview.
Want to work from an existing image? Join image-editing early access.
Generated with MOSS-Image SFT in this studio. 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 toolkitCreate posters, labels, and visual stories with Chinese or English lettering. Always proofread generated text before sharing. Open the text-in-image generator
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.
The hosted studio generates new images from text and JSON layouts today. Tell us whether style changes, selective repainting, text replacement, or composition-preserving edits should come next.
Join image-editing early accessMOSS-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.
When the service confirms a technical failure, safety rejection, or response without a usable image, the reserved credit is restored 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 generation. Completed images are copied to private Cloudflare R2 storage and require your signed-in account to access. You can permanently delete saved images from your account; see the Privacy page for details.