min(DALL·E) GitHub This is a fast, minimal port of Boris Dayma's DALL·E Mini (with mega weights). It has been stripped down for inference and converted to PyTorch. The only third party dependencies are numpy, requests, pillow and torch. To generate a 4x4 grid of DALL·E Mega images it takes: 89 sec with a T4 in Colab 48 sec with a P100 in Colab 13 sec with an A100 on Replicate Here's a more detailed breakdown of performance on an A100. Credit to @technobird22 and his NeoGen discord bot for the graph. The flax model and code for converting it to torch can be found here. Install Usage Load the model parameters once and reuse the model to generate multiple images. The required models will be downloaded to models root if they are not already there. Set the dtype to torch.float16 to save GPU memory. If you have an Ampere architecture GPU you can use torch.bfloat16 . Set the device to either "cuda" or "cpu". Once everything has finished initializing, call generate image with some text as many times as you want. Use a positive seed for reproducible results. Higher values for supercondition factor result in better agreement with the text but a narrower variety of generated images. Every ima…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy