Skip to content
AX AI Daily
中EN
Trending storyDeveloping

OpenMOSS releases open-source image model MOSS-Image

1 report1 sourceupdated 2 hours ago

What happened

AI digest

On October 29, 2026, OpenMOSS released MOSS-Image, an open-source image generation model. It uses a 5B single-stream DiT, renders long Chinese and English text, takes prompts up to about 4K tokens, and supports editable JSON Layout. The release covers the architecture, prompt length, text rendering and layout editing. No follow-up updates, benchmark results or other release details were given.

Written by AI from the coverage · updated 2 hours ago

LatestOct 29 10:40
OpenMOSS releases MOSS-Image, with long Chinese and English text rendering and editable JSON layout.

Coverage

Follow the reports to see the story from different sides.

Oct 29
  1. AI HOT · Models
    OpenMOSS 发布开源图像生成模型 MOSS-Image，支持长文本渲染与可编辑布局

    OpenMOSS 发布开源图像生成模型 MOSS-Image，以 5B 单流 DiT 支持中英文长文本渲染、最长约 4K token 提示词及可编辑 JSON Layout。

Heat over time

Not enough continuous observations to draw a trend yet.