ComfyUI Wiki · 工作流与开源创作分享·· 2026-10-16PicksAI score65
OpenMOSS releases 5B text-to-image model MOSS-Image, with same-day ComfyUI support
Text to image
AI briefing
OpenMOSS released the 5B text-to-image model family MOSS-Image on October 16, including two checkpoints: the pretrained version MOSS-Image-Base and the general-user-oriented MOSS-Image-SFT.
Why it matters
The 5B text-to-image model focuses on Chinese and English text rendering and JSON layout control, with same-day support from ComfyUI core nodes, which can be used to evaluate layout-oriented image generation workflows.
Open original comfyui-wiki.com
Image GenerationComfyUI & WorkflowsModel Releases#Model release#Image generation#ComfyUI & workflows#Hugging Face