Report
😢 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
Comfyui Moss Image
Run Comfyui Moss Image inside ComfyUI: native JSON layout prompts with bounding boxes, Base and SFT checkpoints, 4K-token prompts, and crisp text rendering.
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
What Comfyui Moss Image Brings to ComfyUI
A compact 5B text-to-image family with native JSON layout control, strong text rendering, and anime or photoreal styles.
- Native JSON Layout ControlBounding boxes in a structured JSON prompt set the position and size of objects, rendered text, and scene elements.
- 4K-Token Prompts, 5B BackbonePrompts of up to 4K tokens run on a compact 5B backbone, with Base and SFT checkpoints sharing one sampling interface.
- Text Rendering in Anime and Photoreal StylesStrong rendered text plus versatile anime and photorealistic looks, shown across illustration, photography, and design.
How to Run Comfyui Moss Image
Three steps from plugin install to a finished layout render.
Comfyui Moss Image FAQ
Common questions about running MOSS-Image layouts in ComfyUI.
Does it need the official ComfyUI repository?
No — the native plugin is found by searching MOSS-Image in ComfyUI Manager, while integration into the official ComfyUI repository is still in progress.
What separates MOSS-Image-Base from SFT?
Both checkpoints share one architecture and sampling interface; the reference example shows SFT giving clearer text grouping and a tidier whiteboard layout.
How do bounding boxes shape a layout prompt?
Each box gives an element's position and size, and you can edit text, element descriptions, and boxes to restructure content and composition.
Which prompt length and visual styles are supported?
Prompts of up to 4K tokens, with anime and photorealistic styles shown across text, illustration, photography, and visual design.
What memory modes help on low-VRAM machines?
Advanced settings offer GPU resident, Component, and Sequential modes; choose Sequential or reduce image size when memory runs short, and note Compile DiT is off by default and unavailable in Sequential.
Can the weights be fine-tuned under Apache-2.0?
Yes — the 5B backbone supports fine-tuning for custom tasks and domains and the model weights are Apache-2.0 licensed, while pipeline code and third-party components keep their own licenses.
Try Comfyui Moss Image in ComfyUI
Install the plugin from ComfyUI Manager, open the example workflow, and run a JSON layout prompt with Base or SFT.