{"name":"MOSS-Image","repo":"OpenMOSS/MOSS-Image","url":"https://midorreal.com/project/openmoss-moss-image","repository":"https://github.com/OpenMOSS/MOSS-Image","description":"Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning.","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/OpenMOSS/MOSS-Image","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/OpenMOSS/MOSS-Image","checked":"22 Nov 2026"},"homepage":{"value":"http://openmoss.ai/MOSS-Image/","source":"http://openmoss.ai/MOSS-Image/","checked":"22 Nov 2026"},"releases":{"value":"0","source":"https://github.com/OpenMOSS/MOSS-Image/releases","checked":"21 Nov 2026"},"contributors":{"value":"8","source":"https://github.com/OpenMOSS/MOSS-Image/graphs/contributors","checked":"21 Nov 2026"},"archived":{"value":"no","source":"https://github.com/OpenMOSS/MOSS-Image","checked":"22 Nov 2026"}},"stars":3017.0,"writeup":{"what_it_is":"MOSS-Image is the official repository for MOSS-Image, a 5B-parameter base diffusion transformer (DiT) model for text-to-image generation. The project also includes a fine-tuned variant, MOSS-Image-SFT, along with inference code, a Diffusers pipeline, and ComfyUI support.","audience":"Developers and researchers working with text-to-image generation and fine-tuning.","claims":[{"kind":"specific","claim":"Accepts text prompts of up to 4K tokens","excerpt":"Accept text prompts of up to 4K tokens.","status":"not_checked"},{"kind":"specific","claim":"Uses a 5B-parameter backbone","excerpt":"Efficient image generation with a 5B backbone.","status":"not_checked"},{"kind":"specific","claim":"Supports layout control over text and visual elements","excerpt":"Control the placement of text and visual elements.","status":"not_checked"},{"kind":"broad","claim":"Generates clear, accurate text within images","excerpt":"Generate clear, accurate text within images.","status":"too_broad"},{"kind":"broad","claim":"Can be adapted to custom tasks and domains through fine-tuning","excerpt":"Adapt the base model to custom tasks and domains.","status":"too_broad"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-17"},"why_now":null,"owner_supplied":null,"score":{"verdict":"too_early","hype":79,"reality":27,"gap":52,"momentum":0.2,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":{"estimate":true,"lean":"too_close","gap_low":16,"gap_high":58,"rule":"early-2.0"},"changes":[{"date":"2026-10-16T01:18:13+00:00","text":"Repository created","source":"https://github.com/OpenMOSS/MOSS-Image"}],"cite":"MOSS-Image is a GitHub project at https://github.com/OpenMOSS/MOSS-Image written mainly in Python, described there as \"Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text rendering, layout generation, and efficient fine-tuning\".","attribution":"Data from Mid or Real, https://midorreal.com/project/openmoss-moss-image, checked 22 November 2026. Attribution with a link is required.","still_real":null}