This model is converted with https://github.com/huggingface/diffusers/blob/main/scripts/convert_original_stable_diffusion_to_diffusers.py.

However, the tokenizer in the diffuser model is wrong, for proper usage, see description at https://medium.com/@enryu9000/TODO, and instructions/examples at TODO.
Also, the original checkpoint in the Latent Diffusion format is available.