About this model
A new open 5B image generator that writes clean text inside images, in English and Chinese, and follows very long, detailed prompts.
Official page · Code · Weights · AI Search video at 0:37
Every size and format published by OpenMOSS, largest first. Want one we don't host yet? Press Request: we add the most requested ones.
| Model | Parameters | Notes | |
|---|---|---|---|
| MOSS-Image SFT | 5B | fine-tuned, best looking | Hosted here |
| MOSS-Image Base | 5B | base model, for training LoRAs | |
| MOSS-Image Edit (LoRA) | 5B + LoRA | community image editing | |
| MOSS-Image 8-step DMD | 5B | community distillation, work in progress | |
| Kromoss | 5B | community fine-tune |
MOSS-Image is an AI image model by OpenMOSS. A new open 5B image generator that writes clean text inside images, in English and Chinese, and follows very long, detailed prompts.
Yes: every account gets one free try of this model, plus welcome credits. After that a run usually costs about 29 credits (1,000 credits = US$1), charged for the real GPU time.
Sign in, open this page, fill in the form and press the run button. It runs on our cloud GPUs: nothing to install, and it works on phones too.
License: Apache-2.0. Commercial use of the outputs is allowed by the license.
In the AI Search video at 0:37.
All models · Not affiliated with OpenMOSS or with AI Search.