Comfyui Moss Image: Text-to-Image and Layout-to-Image
freeTrialImage.bannerPity

Report

Output
Layout preview

freeTrialImage.bannerPity

freeTrialImage.upgradeUnlock

  • ✓freeTrialImage.benefitHd
  • ✓freeTrialImage.benefitWatermark
  • ✓freeTrialImage.benefitUnlimited

Comfyui Moss Image

Run Comfyui Moss Image inside ComfyUI with native JSON layout prompts, bounding boxes, Base or SFT checkpoints, and 4K-token text rendering.

AI Tools

Explore AI tools

placeholder hero

What Makes Comfyui Moss Image Stand Out in ComfyUI

This compact 5B text-to-image model adds native JSON layout control, reliable text rendering, and flexible anime or photoreal styles to ComfyUI.

  • Structured JSON Prompts with Bounding Boxes
    Define object positions and sizes, rendered text, and scene elements by placing bounding boxes directly in a structured JSON prompt.
  • Long 4K-Token Prompts on a 5B Backbone
    Run prompts up to 4K tokens on a compact 5B backbone; Base and SFT checkpoints share one sampling interface for easy switching.
  • Crisp Text Across Anime and Photoreal Looks
    Get clear rendered text with versatile anime and photorealistic styles that suit illustration, photography, and design work.

How to Run Comfyui Moss Image in ComfyUI

Follow three simple steps, from installing the plugin to rendering a finished layout.

FAQ

Comfyui Moss Image: Frequently Asked Questions

Answers to common questions about running MOSS-Image layouts in ComfyUI.

1

Do I need the official ComfyUI repository?

No. Search MOSS-Image in ComfyUI Manager to find the native plugin; integration into the official ComfyUI repository is still in progress.

2

How is MOSS-Image-Base different from SFT?

Both checkpoints use the same architecture and sampling interface; in the reference example, SFT delivers clearer text grouping and a cleaner whiteboard layout.

3

How Do Bounding Boxes Control a Layout Prompt?

Every box defines an element's position and size; edit the text, element descriptions, and boxes to reshape both content and composition.

4

What Prompt Length and Visual Styles Are Supported?

Use prompts up to 4K tokens, with anime and photorealistic styles demonstrated across text, illustration, photography, and visual design.

5

Which Memory Modes Help on Low-VRAM Machines?

Advanced settings include GPU resident, Component, and Sequential modes; choose Sequential or lower the image size when memory is tight, and note that Compile DiT is off by default and unavailable in Sequential.

6

Can I Fine-Tune the Weights Under Apache-2.0?

Yes. The 5B backbone can be fine-tuned for custom tasks and domains, and the model weights are Apache-2.0 licensed; pipeline code and third-party components retain their own licenses.

Start Using Comfyui Moss Image in ComfyUI

Add the plugin through ComfyUI Manager, load the example workflow, and render a JSON layout prompt with Base or SFT checkpoints.