Model Hub
Browse, search, and download AI models.
Efficient-Large-Model
Sana_1600M_4Kpx_BF16_diffusers
SANA 1600M 4K — NVIDIA Labs efficient text-to-image diffusion model that generates ultra-high-resolution images up to 4096×4096px using a deep-compression autoencoder and a linear-attention transformer for fast inference. BF16 weights.
Text-to-ImageDiffusion4K ResolutionLinear Attention+2
412.0 GiB
NVIDIA Open Model