rust-stable-diffusion-v1-5

This repository hosts weights for a Rust based version of Stable Diffusion. These weights have been directly adapted from the runwayml/stable-diffusion-v1-5 weights, they can be used with the diffusers-rs crate.

To do so, checkout the diffusers-rs repo, copy the weights in the data/ directory and run the following command:

cargo run --example stable-diffusion --features clap -- --prompt "A rusty robot holding a fire torch."

This is for the image-to-text pipeline, example using the image-to-image and inpainting pipelines can be found in the crate readme.

License

The license is unchanged, see the original version. In line with paragraph 4, the original copyright is preserved: Copyright (c) 2022 Robin Rombach and Patrick Esser and contributors

The model details section below is copied from the runwayml version, refer to the original repo for use restrictions, limitations, bias discussion etc.

Model Details

• Developed by: Robin Rombach, Patrick Esser

• Model type: Diffusion-based text-to-image generation model

• Language(s): English

• License: The CreativeML OpenRAIL M license is an Open RAIL M license, adapted from the work that BigScience and the RAIL Initiative are jointly carrying in the area of responsible AI licensing. See also the article about the BLOOM Open RAIL license on which our license is based.

• Model Description: This is a model that can be used to generate and modify images based on text prompts. It is a Latent Diffusion Model that uses a fixed, pretrained text encoder (CLIP ViT-L/14) as suggested in the Imagen paper.

• Resources for more information: GitHub Repository, Paper.

• Cite as:

  @InProceedings{Rombach_2022_CVPR,
      author    = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
      title     = {High-Resolution Image Synthesis With Latent Diffusion Models},
      booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      month     = {June},
      year      = {2022},
      pages     = {10684-10695}
  }
  

Weight Extraction

The weights have been converted by downloading them from the runwayml/stable-diffusion-v1.5 repo, and then running the following commands in the diffusers-rs repo.

After downloading the files, use Python to convert them to npz files.

import numpy as np
import torch
model = torch.load("./vae.bin")
np.savez("./vae.npz", **{k: v.numpy() for k, v in model.items()})
model = torch.load("./unet.bin")
np.savez("./unet.npz", **{k: v.numpy() for k, v in model.items()})

Convert these .npz files to .ot files via tensor-tools.

cargo run --release --example tensor-tools cp ./data/vae.npz ./data/vae.ot
cargo run --release --example tensor-tools cp ./data/unet.npz ./data/unet.ot