Developing story · 2 episodes · 11 Oct to 26 Oct
OpenMOSS Pushes AI Text-to-Image Frontiers
The saga follows OpenMOSS's release of successive text-to-image models, beginning with MOSS-Image-SFT and advancing to the larger 5B DiT-based MOSS-Image. With the latest 5B model now available, OpenMOSS has positioned itself as a leading contender in open-source AI image generation, setting the stage for further scaling and applications.
-
OpenMOSS releases MOSS-Image, a 5B DiT model for text rendering
OpenMOSS announced MOSS‑Image, a 5‑billion‑parameter DiT model focused on text and layout. The weights were uploaded to Hugging Face on October 11, the technical report on October 16, and ComfyUI…
1 source -
OpenMOSS releases MOSS-Image-SFT text-to-image model
OpenMOSS has released MOSS-Image-SFT, a supervised fine-tuned text-to-image model derived from the MOSS-Image-Base architecture. The release supports natural-language prompts, tag sequences, and…
1 source primary source
Who and what