MOSS-Image
Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.
The Lens
By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.
Updated Oct 2026
MOSS-Image is an open text-to-image model built for what image generators usually botch: readable text inside the picture. Posters, signs, sticky notes, Chinese included. You can also hand it a JSON layout saying where the title and each object go. It's from OpenMOSS, and code and weights are both Apache-2.0, so it's free for commercial work.
Running it locally means Python, PyTorch and an NVIDIA GPU. The weights are roughly 27 GB at bf16, over half of it the text encoder, and the Gradio app can offload to CPU for smaller cards at the cost of speed. ComfyUI supports it natively, and community trainers already do LoRA fine-tuning.
The model has no paid tier. MOSI, the team behind it, sells API access, but hasn't published an image price yet. Solo and small teams: free if you own a decent NVIDIA card. Larger teams: free, but test it against FLUX and Qwen-Image first.
The catch: it's days old and the quality claims are the lab's own. The default is 50 sampling steps, so it isn't fast, and the community is already patching vertical color banding in the SFT model. Loading it also runs custom code via trust_remote_code=True.
Free vs Self-Hosted vs Paid
fully freeFree: Two checkpoints, MOSS-Image-Base and MOSS-Image-SFT, on Hugging Face and ModelScope. The pipeline code on GitHub and the model weights are both Apache-2.0, so commercial use is allowed. Features: text rendering inside images, JSON layout control with bounding boxes, prompts up to 4K tokens, and a hosted demo on Hugging Face Spaces.
Self-hosted: pip install -r requirements.txt, then load it through Diffusers with trust_remote_code=True, or run the Gradio app. Weights total about 27 GB at bf16 (transformer about 10 GB, text encoder about 17 GB, VAE under 1 GB, measured from the Hugging Face file listing). Gradio offers GPU resident, Component and Sequential memory modes for smaller GPUs. Native ComfyUI support, day-0 support in SGLang and vLLM-Omni, and LoRA or full fine-tuning through DiffSynth-Studio and KohakuMossTrainer.
Paid: No paid tier for the model. The MOSI API Platform hosts MOSS-Image via Playground and API with credit-based billing, but as of 2026-10-21 its pricing page lists only voice and transcription prices (for example ¥2.00, about $0.28, per 10,000 characters for TTS), with no image price published.
Free, Apache-2.0 weights included, so commercial use costs nothing beyond your own GPU. The hosted MOSI API exists but hasn't published an image price yet.
What to do by team size
- Solo
- free; one NVIDIA GPU, ComfyUI is the easiest front end
- Small team
- free; Apache-2.0 weights cover client and commercial work
- Medium team
- free; serve it through ComfyUI, SGLang or vLLM-Omni as a shared service
- Large team
- free; fine-tune on your own assets, but run your own evals against FLUX and Qwen-Image first
Get tools like this every Wednesday
One featured tool, three on the radar. No fluff.
A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores
Trust Signals
License: Apache License 2.0
Code and model weights are both Apache 2.0.
Commercial use: ✓ Yes
About
- Owner
- OpenMOSS (SII) (Organization)
- Stars
- 1,504
- Forks
- 74