# NOTICE — clip

The image encoder originates from LAION CLIP ViT-H/14 trained on LAION-2B
using OpenCLIP, by Romain Beaumont on Stability AI compute:
https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K

The upstream model card declares the MIT license. The original OpenCLIP
MIT permission and copyright notice are reproduced in LICENSE.md:
https://github.com/mlfoundations/open_clip/blob/main/LICENSE

Conversion into a Diffusers-compatible component does not remove the original
MIT attribution. EdenLive's Apache-2.0 code license does not replace the MIT
license applicable to this component. Processing and loading use the separately
licensed Hugging Face Transformers / Diffusers libraries.