Stable Diffusion v2.1, running 100% in Rust.

The first Rust-powered model on Replicate.

Using language models to generate Super Mario Bros levels

Emojis on Stable Diffusion via Dreambooth

Pop Audio-based Piano Cover Generation

Stable Diffusion, but NSFW images return the closest non-NSFW image instead of a black square.

Run any image through the Stable Diffusion content filter

Generate subtitles from an audio file, using OpenAI's Whisper model.