Feedback
😢 Every free AI generation costs us real GPU money. We pay out of pocket to keep this free for you.
💎 Upgrade to Pro and unlock:
- ✓HD Download
- ✓No Watermark
- ✓Unlimited Generations
MOSS-Image
MOSS-Image is OpenMOSS's text-to-image family: a 5B backbone, 4K-token prompts, and native JSON layout control for objects, text and boxes.
AI Tools
Explore AI tools
Free AI Image
Truly Free AI Image Generator
AI Image Editor
AI Photo Editor Online
Image Upscaler
Enhance image resolution effortlessly
AI Color Changer
Transform photo colors in seconds
AI Room Designer
Design your dream room with AI-powered 3D rendering
Skin Enhancer
Enhance skin texture naturally with AI
Face Editor
Enhance face texture naturally with AI
AI Clothes Changer
Why Use MOSS-Image
A 5B text-to-image family with native, text-driven layout control.
- Native Layout ControlGive each object and piece of rendered text its own box, so composition follows your JSON instead of guesswork.
- 5B Backbone, 4K TokensLong prompts fit comfortably, and the same weights can be adapted to your own tasks and domains.
- Base and SFT WeightsBoth checkpoints ship under Apache-2.0 with identical architecture; the SFT variant keeps whiteboard text tidier.
How to Run MOSS-Image
Three steps from environment setup to a controlled layout render.
MOSS-Image FAQ
Common questions about MOSS-Image prompts, checkpoints and setup.
What does native layout control let me specify?
A JSON prompt lists the scene, objects and rendered text, with a box for each element's position and size.
How do MOSS-Image-Base and MOSS-Image-SFT differ?
They share one architecture and sampling interface; SFT is fine-tuned on curated data and, in the project example, gives clearer text grouping and a tidier whiteboard layout.
How long can a MOSS-Image prompt be?
Up to 4K tokens, enough for a multi-element layout JSON.
What hardware and software do I need?
Python 3.10+ and an NVIDIA GPU with a matching PyTorch build. If memory is tight, switch to Sequential mode or reduce image size; Compile DiT is off by default and unavailable there.
Can I run MOSS-Image inside ComfyUI?
Yes. Search for MOSS-Image in ComfyUI Manager to install the native plugin, then load the example workflow; integration into the official ComfyUI repository is still in progress.
What license applies to the weights and code?
Model weights are released under Apache-2.0, while the pipeline code and third-party components keep their own licenses. For research use, cite the project repository.
Start Generating with MOSS-Image
Install the Diffusers pipeline or the ComfyUI plugin, then try a JSON layout prompt — or compile your idea with the MOSS-Image Prompt Enhancer first.