tanner/min-dalle-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

pre converting params to torch allows mega to run in standard colab runtime

Browse Source
This commit is contained in:
Brett Kuprel
2022-06-30 14:54:08 -04:00
parent de97fcf06b
commit b913b58353
5 changed files with 54 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
Vendored
+1 -1
View File
@@ -5,7 +5,7 @@
This is a minimal implementation of Boris Dayma's [DALL·E Mini](https://github.com/borisdayma/dalle-mini). It has been stripped to the bare essentials necessary for doing inference, and converted to PyTorch. To run the torch model, the only third party dependencies are numpy and torch. Flax is used to convert the weights (which can be saved with `torch.save` once the model is loaded), and wandb is only used to download the models.
It currently takes **7.3 seconds** to generate an avocado armchair with DALL·E Mega in PyTorch on Colab (with nonexpendable model in high RAM runtime)
It currently takes **7.3 seconds** to generate an avocado armchair with DALL·E Mega in PyTorch on Colab
### Setup