MOSS-Image
Open-weight (Apache 2.0) 5B text-to-image model from MOSI and the OpenMOSS team, aimed at text-dense graphics and layouts.
Model idOpenMOSS-Team/MOSS-Image-SFT
PricePrice not published
Checked26 October 2026
Where it stands
2newer image generation models since its release
- GPT Image 2.6 Flare4 Nov 2026
- GPT Image 2.6 Sunburst4 Nov 2026
- Weights
- Weights are public under a permissive licence (Apache-2.0).
How to call it
5 ways to use MOSS-Image, with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face (SFT) | OpenMOSS-Team/MOSS-Image-SFT |
huggingface.co | |
| Hugging Face (Base) | OpenMOSS-Team/MOSS-Image-Base |
huggingface.co | |
| ComfyUI | Comfy-Org/MOSS-Image |
huggingface.co | |
| MOSI API platform | platform.mosi.cn | ||
| GitHub | github.com |
Pricing
Price not published.
No price source linked. Checked 26 October 2026.
Specs
- Input
- Text
- Output
- Images
- Context window
- Not published
- Max output
- Not published
- Open weights
- Yes
- Licence
- Apache-2.0
- Released
- 16 October 2026
- Status
- Current
- Type
- Image generation
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Dense bilingual text and JSON layouts
Renders long Chinese and English text and accepts structured JSON layouts with bounding boxes and prompts up to 4,096 tokens; the report claims the best open-weight score on its LongLongTextBench (96.3% text coverage).
Trained without AI-generated images
Found after launch
The team removed AI-generated images from training data, which community developers (e.g. Ostris) suggest explains its more natural look (Pandaily).
Notes
5B single-stream diffusion transformer trained from scratch, frozen Qwen3.5-9B text encoder, FLUX.2 small VAE decoder; trained on a domestic PPU compute platform (Pandaily). Diffusers pipeline needs trust_remote_code. Community 8-step and 4-step distillations, INT8/GGUF/MLX builds.