MOSS Image SFT
MOSS-Image-SFT is a supervised fine-tuned text-to-image model in the MOSS-Image family from OpenMOSS, derived from It uses the same architecture and inference pipeline, supporting natural-language prompts, tag sequences, and JSON layouts for controlling text placement and object arrangement. In this example, SFT produces clearer text grouping and a more organized whiteboard layout.
MOSS Image SFT launched on 11 October 2026. It ranked #90 on Daily Launch on 29 October 2026 with a Launch Score of 25, from trending score 225 on Hugging Face. It moved down 32 places from the day before.
What is MOSS Image SFT?
MOSS Image SFT is a model by OpenMOSS-Team on Hugging Face. It is released under the Apache 2.0 license.
How to get MOSS Image SFT
pip install "diffusers>=0.38" "transformers>=5.3" "accelerate>=1.10" "safetensors>=0.6" "Pillow>=10"From its model card on Hugging Face
More steps and the source are in its model card on Hugging Face.