Vaibhav Bansal

Thank you for making this repository to imitate OpenAI DALLE. I was thinking that it would be efficient if we just used pre-existing sota text-to-text language model for the transformer...

DeepSpeed integration for training on local cheaper GPUs.

3

This is an awesome repository that you've made. It would be helpful if you'd integrate DeepSpeed for ZeRO-Infinity NVME offload, for beginners like me😅, as Im only having a 1660ti...

"Math input error", improve math/0601063

3

This is a great conversion of the PDFs to html5 web pages, but there are a lot of math input errors in documents presented here on ar5iv website, in this...

[colab-link](https://colab.research.google.com/drive/14LGwr_rqI9g4Sc4pgwIiqh21Pj0rIB26?usp=sharing) updated simplified notebook with image interpolation (by simply using a bigger grid), saving/ loading pre-trained siren net and retraining siren net on different prompt. and added super resolution from...

As the paper says, > In evaluation, and under known temporal or computational limitations, N can be set naively as a constant (or not set any limit, i.e. N →...