What datasets were used to train SD3 Medium?

Question

Answers ( 1 )

    0
    2025-04-01T07:40:54+00:00

    The model was **pre-trained on 1 billion images** and **fine-tuned** with:
    - 30 million high-aesthetic images
    - 3 million preference-based images
    This ensures nuanced style adaptation and prompt fidelity.

Leave an answer