MeiGen AI Design
Lets ChatGPT, Claude or Cursor find visual ideas and make images and videos for you
by MeiGen
MOSS-Image Text to Image
by Comfy OrgWorkflowMake visuals
Makes a finished image from a one-line idea, including readable English or Chinese text
About MOSS-Image Text to Image
An official ComfyUI workflow that turns a one-line idea into a finished image with MOSS-Image, an open image model. A prompt helper expands your idea and the image is drawn on your own computer, with readable lettering.
For Poster and social-media makersConcept artistsHome-PC image makers
Made by Comfy Org
Comfy Org is a small San Francisco team that builds open-source tools for visual AI, including ComfyUI. This template uses MOSS-Image, an open model from OpenMOSS.
- Stars
- ★ 1.4k
- License
- MIT
- Cost
- Free
- Level
- Intermediate
- Platform
- comfyui
Examples
From the project's own repository.
Overview
This is an official ComfyUI workflow template for MOSS-Image, an open image model from OpenMOSS. You type a short idea, a built-in prompt helper expands it into a full scene description, and the model draws the image on your own computer. It can render English and Chinese lettering, such as a sign or a poster title, inside the picture. It suits people making posters, product shots or concept art who want to run the model locally.
A one-line request is enough because the template rewrites it into a detailed caption first and shows you the caption it used.
Try these first
Start with the first one: it is a small task you can check easily.
- A small cafe at night with a neon sign that reads "OPEN", photo styleFirst try · about 13 GB download
- A minimalist poster for a summer book fair with the title "Read Outside" at the top
- A tea shop banner with the words 新茶上市 in brush lettering
- Turn off the prompt helper and use this full caption as written: [paste caption]
Example prompts written by Agent Flows Hub.
How it works
From the creator's documentation.
| Step | What happens | Data goes to |
|---|---|---|
| 1 · Model files | ComfyUI lists the image model, text encoder and VAE files to download | Your computer |
| 2 · Your idea | You type a short description in the prompt box | Your computer |
| 3 · Prompt helper | Expands your idea into a full scene caption; you can switch it off | Your computer |
| 4 · Generate | MOSS-Image draws the picture on your graphics card, with English or Chinese lettering | Your computer |
| 5 · Save | ComfyUI saves the image and shows the caption it used | Your computer |
Good to know
Generate an image from a short text idea with the official MOSS-Image ComfyUI graph. A prompt helper expands the idea into a full caption, then the model draws the image and ComfyUI saves it.
Limits
- The template needs ComfyUI 0.42.0 or newer and the model files it lists. It uses faster sampling settings than the model makers' defaults; ComfyUI's notes suggest 50 steps and CFG 3 for results closer to theirs.
- Line breaks in rendered text may not land where you expect. Check spelling and layout of any lettering in the result.
Notes by Agent Flows Hub (original project name: image_moss_image_t2i (ComfyUI template)), written from the creator's documentation, not from running it ourselves. MOSS-Image in ComfyUI: official tutorial · MOSS-Image: pinned ComfyUI template
Stuck setting it up?
Tell us what happened. We take a look first; if it needs paid work, you get an estimate before anything starts.
More to make visuals
Other workflows
- Multiple Camera Angles App Re-creates one picture from a new camera angle you set with a 3D camera control
- Qwen Image Edit 2511 (Int8) Edits a photo from a plain instruction, built to keep the person's identity consistent
- Remove Background (BiRefNet) Removes the background from a photo and gives you a transparent cut-out and a mask
- SeedVR2 Image Upscale Enlarges a small or blurry photo into a sharper, higher-resolution image on your computer
- SeedVR2 Video Upscale Turns a grainy, low-resolution video clip into a cleaner, higher-resolution one
- Thread Writer (Langflow) Turns a project brief into a ready-to-post thread or single post for X (Twitter)