It is a mix of of mixing and training focused on multiple people in realistic images. While it's not quite perfect at photorealism, and might struggle a bit with super complex scenes or hands, our focus was to make is possible to easily prompt for multiple people.
Does well with 'DPM++ 3M SDE Karras' at 1024x1024 for most people.
Works well with LORAs.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.