What can I use MOSS-Image-Base for?

Give a scene description or tag list to generate a picture; Specify visible text and object positions in a structured layout to generate an arranged composition; Change text, element descriptions or placement boxes in a layout to adjust the resulting image

Can I run MOSS-Image-Base on my computer?

The Python quick start requires Python 3.10 or later, an NVIDIA GPU with CUDA support, and a compatible PyTorch 2.9 or later build. GPU memory requirements and operating system compatibility are not documented.

What do I need to use MOSS-Image-Base?

Python 3.10 or later, compatible PyTorch 2.9 or later, and an NVIDIA GPU with CUDA support.

MOSS-Image-Base: Generate images with planned text and object placement

Model details

Original model OpenMOSS-Team/MOSS-Image-Base

Make/edit images

Input Text Output Image

Follow the model card setup

Ways to use it Run locally

Creator exampleSee the source example

What it does

MOSS-Image-Base turns written instructions into images. It accepts ordinary descriptions, tag lists or structured layouts that specify the scene, visible text, objects and their positions. Structured layouts use JSON, a text format for named fields, to describe the intended arrangement rather than leaving all placement to a general caption.

How to use it

Open the model page for the Python quick start, or search for MOSS Image in ComfyUI Manager and install its native plugin. Supply a written image idea as the prompt. For more explicit placement, prepare a layout describing text and objects. In the documented Gradio interface, paste that layout into the Prompt field and choose matching image dimensions to generate the picture.

Common use cases

Give a scene description or tag list to generate a picture.
Specify visible text and object positions in a structured layout to generate an arranged composition.
Change text, element descriptions or placement boxes in a layout to adjust the resulting image.

Can I use this?

Setup details on the source page

Requirements The Python quick start requires Python 3.10 or later, an NVIDIA GPU with CUDA support, and a compatible PyTorch 2.9 or later build. Model files and custom pipeline code download and cache automatically; a complete local model directory is also supported.

Caveat The source labels layout prompts experimental. GPU memory requirements and operating system compatibility are not documented.

Worth knowing Layout prompts are experimental. Operating system compatibility is not documented. Licensed under Apache License 2.0.

Why it's here

Not trending this week

Last seen on the Hugging Face trending list on 26 October 2026. It stays on BuildTube so you can still find it.

644 people have liked it on Hugging Face.
It was downloaded 12,383 times in the last 30 days.

Numbers checked on 8 November 2026; not refreshed since.

Behind it

View model page

BuildTube has not run or verified this project. Everything above is written from what the creator published.

Made this?

Quick questions

What is MOSS-Image-Base?: MOSS-Image-Base turns written instructions into images.
What can I use MOSS-Image-Base for?: Give a scene description or tag list to generate a picture; Specify visible text and object positions in a structured layout to generate an arranged composition; Change text, element descriptions or placement boxes in a layout to adjust the resulting image
Can I run MOSS-Image-Base on my computer?: The Python quick start requires Python 3.10 or later, an NVIDIA GPU with CUDA support, and a compatible PyTorch 2.9 or later build. GPU memory requirements and operating system compatibility are not documented.
What do I need to use MOSS-Image-Base?: Python 3.10 or later, compatible PyTorch 2.9 or later, and an NVIDIA GPU with CUDA support.
What license does MOSS-Image-Base use?: Licensed under Apache License 2.0.

More from this week

P-H3-Image-Comfy Make and edit 8-megapixel images in ComfyUI
Turn short text requests into 8-megapixel images and edit pictures on your own graphics card.
Added 7 Nov
Idol Turn one picture of an object into a 3D Gaussian splat
Idol turns one photo, render or generated image of an object into a 3D Gaussian splat file.
Runs in a terminalAdded 2 Nov
agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
+13,858 stars this weekAdded 3 Nov

Related projects

MOSS-Image-SFT Generate images with text and objects placed where you say
Same topic: diffusers
Added 21 Oct
Qwen-Image-2.1-viggle-turbo Make images about 5x faster with a distilled Qwen model
Same topic: diffusers
Needs a model setupAdded 1 Oct
Qwen-Image-2.1-GGUF Run Qwen’s image model on your laptop, compressed
Same topic: text-to-image
Needs a model setupAdded 1 Oct
Qwen-Image-2.1-Turbo Generate and edit images with an eight-step Qwen model
Same topic: diffusers
Needs a model setupAdded 10 Oct
Qwen-Image-2.1 Generate and edit images, including transparent layers, from text
Same topic: diffusers
Needs a model setupAdded 25 Sept
NVIDIA-Nemotron-3.5-Transcribe-30B-A4B Transcribe hour-long recordings (34B)
Same topic: safetensors
Needs a model setupAdded 30 Oct

Explore by topic

Post this

For makers

Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.

README badge (Markdown)

[![Featured on BuildTube](https://buildtube.app/badge/hf-openmoss-team-moss-image-base.svg)](https://buildtube.app/p/hf-openmoss-team-moss-image-base/)

Embed card (HTML)

<iframe src="https://buildtube.app/embed/hf-openmoss-team-moss-image-base/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="MOSS-Image-Base on BuildTube"></iframe>