Aran Komatsuzaki    @arankomatsuzaki    11/25/2021      

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion Achieves SotA results on text-to-image generation, text-to-video generation, video prediction, etc. Outperforms DALL-E in text2image. abs: https://t.co/LgrUVjCAEB repo: https://t.co/xlLetCJi1P
  
    96         493










 
  Related  

/MachineLearning    @slashML    12/4/2021      

(Paper Overview) NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion https://t.co/MlHTNnJDYk
  
    1         2



AK    @ak92501    11/25/2021      

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion abs: https://t.co/lwYYEzc5PZ presents a unified multimodal pretrained model that can generate new or manipulate existing visual data (i.e., images and videos) for various visual synthesis tasks
  
    1         1



AK    @ak92501    11/30/2021      

LAFITE: Towards Language-Free Training for Text-to-Image Generation abs: https://t.co/9Ola1jdct6 competitive results in zero-shot text-to-image generation on MS-COCO, only 1% of the model size and training data size relative to the recently proposed large DALL-E model
  
    1         1



Aran Komatsuzaki    @arankomatsuzaki    11/30/2021      

LAFITE : Towards Language-Free Training for Text-to-Image Generation Obtains competitive results in zero-shot text-to-image generation on the MS-COCO, yet with around only 1% of the model size and language-free training data size relative to DALL-E. https://t.co/mNtwBzzDR0
  
          6