# Linear Diffusion Transformer

SANA-1.5 is an efficient text-to-image generation model based on the Linear Diffusion Transformer architecture, supporting 1024px high-resolution image generation.

Sana is an efficient text-to-image framework capable of generating images with resolutions up to 4096×4096, featuring fast synthesis of high-resolution, high-quality images

Sana is an efficient text-to-image framework capable of generating images with resolutions up to 4096×4096, supporting multilingual input.

Sana is an efficient text-to-image framework for high-resolution image generation, supporting up to 4096×4096 resolution images and capable of running quickly on laptop GPUs.

Sana is an efficient text-to-image framework capable of generating images up to 4096×4096 resolution, deployable on laptop GPUs.