SwinIR VS dalle-playground

003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR-L_x4_GAN.pth

I was trying to get a new upscaler working, as someone pointed me to one that did a good job of preserving and creating new details: https://github.com/JingyunLiang/SwinIR

SwinIR: https://github.com/JingyunLiang/SwinIR

Upscalers that I use SwinIR https://github.com/JingyunLiang/SwinIR https://github.com/AUTOMATIC1111/stable-diffusion-webui (Use 'extras' tab for the upscaler function) Topaz Gigapixel AI https://www.topazlabs.com/gigapixel-ai

You could try out chaiNNer, it is a free local/offline application. There are a lot of (upscaling) models which you can download an use with it. You can for example try out SwinIR-L (link will start a model download) or any other model you like depending on your input images.

the relative attention bias can be made non-square in the original implementation, there is a parameter window_size, at 7, that is forced to (7,7) directly, but you can change it easily. https://github.com/JingyunLiang/SwinIR/blob/main/models/network_swinir.py

Use SwinIR medium model to upscale by 2 times. This will result in a video of 2048x1152.

Built on dalle-playground because it is simple and I like it.

[1] https://github.com/saharmor/dalle-playground

If you decide to abandon the idea of running locally and want to run in the cloud instead, https://github.com/saharmor/dalle-playground has a Google Colab notebook that's relatively easy to run (although Google Colab's free tier is relatively limited).

Next, we want the code in the https://github.com/hrichardlee/dalle-playground repo, and we want to construct a pip environment from the backend/requirements.txt file in that repo. We were almost able to use the saharmor/dalle-playground repo as-is, but we had to make one change to add the jax[cuda] package to the requirements.txt file. In case you haven’t seen jax before, jax is a machine-learning library from Google, roughly equivalent to Tensorflow or PyTorch. It combines Autograd for automatic differentiation and XLA (accelerated linear algebra) for JIT-compiling numpy-like code for Google’s TPUs or Nvidia’s CUDA API for GPUs. The CUDA support requires explicitly selecting the [cuda] option when we install the package.

Is their any way to run DALLE-2 inside of a docker container similarly to this DALLE-PLAYGROUND repo on github?

I know there are open source projects like dalle-playground. Would it literally be enough to host this app on an EC2 instance with the mini model?