Tried diffusers v0.27.0’s LEDITS++ with Google Colab free tier T4
Tried to run diffusers LEDITS++ on Google Colab T4. Unfortunately, the result wasn’t good as well as Hugging Face’s sample. I guess the reason might be that I resized the original image into 512x512 for GPU memory’s limitation.
What is LEDITS++?
>We are adding support to the real image editing technique called LEDITS++: Limitless Image Editing using Text-to-Image Models, a parameter-free method, requiring no fine-tuning nor any optimization.
To edit real images, the LEDITS++ pipelines first invert the image DPM-solver++ scheduler that facilitates editing with as little as 20 total diffusion steps for inversion and inference combined. LEDITS++ guidance is defined such that it both reflects the direction of the edit (if we want to push away from/towards the edit concept) and the strength of the effect. The guidance also includes a masking term focused on relevant image regions which, for multiple edits especially, ensures that the corresponding guidance terms for each concept remain mostly isolated, limiting interference.
https://github.com/huggingface/diffusers/releases/tag/v0.27.0
Original image
tomato
iPhone
base ball
Google Colab notebook
