added
Enhanced Image Generation Model Selection
about 1 month ago
Our Multimodal Dialog API and Image Generation API now support selecting different generation models.
Base Model: The standard model, optimized for fast and high-quality image generation across a wide range of use cases.
Large Model: A more advanced model leveraging newer architecture, providing higher quality results, less artifacts and better prompt following.
To specify your preferred model, set the model_name
parameter in either the image generation API or image settings for multimodal responses to be base
or large
.