
Moss Image
An open text-to-image model from the OpenMOSS team, supporting English and Chinese text rendering, with free credits upon registration and commercial licensing in paid plans.
About Moss Image
Moss Image is an open text-to-image model from the OpenMOSS team (the research team behind the MOSS language model). Built on a 5B-parameter diffusion Transformer, it generates images from prompts. The official website offers an online generation service: new accounts receive free credits upon registration, so you can try multiple prompts without adding a payment card; paid plans cover larger-scale generation and commercial use. The model supports rendering both English and Chinese text, making it suitable for scenarios that require text within the image. Note that the paid plans on this site cover commercial licensing for the generated images; the model weights are released by OpenMOSS under the Apache-2.0 license, so if you want to self-host or redistribute the moss model itself, please review the license terms first.
Best for
Best use cases
Want to test prompt results with a small amount of free credits before deciding whether to pay
Need to create posters or promotional images with English or Chinese text in the picture
Need to use generated images for commercial purposes
Heavy users or teams that need to generate images in batches
Features
Text-to-Image Generation
Generate images from prompts with a 5B-parameter diffusion Transformer.
English and Chinese Text Rendering
Supports rendering English and Chinese text within generated images.
Pros
- Free credits upon registration—try it without adding a payment card
- Supports rendering both English and Chinese text
- Paid plans include a commercial license and watermark-free generation
- Subscription can be canceled anytime
Cons
- Subscription credits do not roll over: credits reset at the start of each billing cycle and must be used within the current cycle (one-time credit packs remain valid for one year from purchase).
Pricing Plans
Starter
- 10,000 credits per year
- MOSS Image text-to-image
- English and Chinese text rendering
- 2 concurrent generations
- Private generation
- No watermark
- Priority processing queue
- Priority support
- Commercial license
Unlimited
- 120,000 credits per year
- MOSS Image text-to-image
- English and Chinese text rendering
- 8 concurrent generations
- Private generation
- No watermark
- Priority processing queue
- Priority support
- Commercial license
* Pricing information is for reference only. Please refer to the latest announcement on Moss Image's official website.