How can I generate images using a safetensors file?

Can I load it directly in the StableDiffustionPipeline or I need to convert it to a diffuser format before using it for image generation ?

Update: Looks like it is still in proposal phase [Proposal] Support loading from safetensors if file is present. (#1357) 路 sliard/diffusers@0390f70 路 GitHub