nyu-visionx/Scale-RAE-Qwen1.5B_DiT2.4B
Text Generation • 4B • Updated • 4.26k
Scale RAE
Collection for "Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders"
-
-
nyu-visionx/Scale-RAE-Qwen1.5B_DiT2.4B-64ep
Text Generation • 4B • Updated • 227 -
nyu-visionx/Scale-RAE-Qwen7B_DiT9.8B
Text Generation • 17B • Updated • 48 • 1 -
nyu-visionx/Scale-RAE-Qwen7B_DiT9.8B-64ep
Text Generation • 17B • Updated • 11 -
nyu-visionx/Scale-RAE-Qwen1.5B_DiT2.4B-WebSSL
Text-to-Image • 4B • Updated • 52 -
nyu-visionx/siglip2_decoder
Image-to-Image • Updated • 62.1k -
nyu-visionx/webssl300m_decoder
Image-to-Image • Updated • 40 -
nyu-visionx/webmae_decoder
Updated • 4 -
nyu-visionx/scale-rae-data
Updated • 42.3k • 2