https://github.com/lucidrains/imagen-pytorch

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch
https://github.com/lucidrains/imagen-pytorch

artificial-intelligence deep-learning imagination-machine text-to-image text-to-video

Last synced: about 2 months ago
JSON representation

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

• Host: GitHub
• URL: https://github.com/lucidrains/imagen-pytorch
• Owner: lucidrains
• License: mit
• Created: 2022-05-23T22:06:13.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-05-03T16:54:57.000Z (5 months ago)
• Last Synced: 2024-06-19T18:55:48.372Z (3 months ago)
• Topics: artificial-intelligence, deep-learning, imagination-machine, text-to-image, text-to-video
• Language: Python
• Homepage:
• Size: 1.18 MB
• Stars: 7,858
• Watchers: 112
• Forks: 746
• Open Issues: 100
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

• awesome-cv - imagen-pytorch - to-Image Neural Network, in Pytorch | (Repos / Tags: Object Classification `[ObjCls]`, Object Detection `[ObjDet]`, Object Segmentation `[ObjSeg]`, General Library `[GenLib]`, Text Reading / Object Character Recognition `[OCR]`, Action Recognition `[ActRec]`, Object Tracking `[ObjTrk]`, Data Augmentation `[DatAug]`, Simultaneous Localization and Mapping `[SLAM]`, Outlier/Anomaly/Novelty Detection `[NvlDet]`, Content-based Image Retrieval `[CBIR]`, Image Enhancement `[ImgEnh]`, Aesthetic Assessment `[AesAss]`, Explainable Artificial Intelligence `[XAI]`, Text-to-Image Generation `[TexImg]`, Pose Estimation `[PosEst]`, Video Matting `[VidMat]`, Eye Tracking `[EyeTrk]`)
• awesome-ARTificial - imagen-pytorch - Implementation of Imagen, Google's Text-to-Image Neural Network that beats DALL-E2, in Pytorch. (Uncategorized / Uncategorized)
• awesome - lucidrains/imagen-pytorch - Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch (Python)
• StarryDivineSky - lucidrains/imagen-pytorch - E2。 它是文本到图像合成的新 SOTA。在架构上上比 DALL-E2 简单得多。 它由一个级联 DDPM 组成，该 DDPM 以来自大型预训练 T5 模型（注意网络）的文本嵌入为条件。 它还包含用于改进分类器自由引导、噪声级调节和内存高效 unet 设计的动态裁剪。 (其他_机器视觉 / 网络服务_其他)