#image-generation #ai #models #candle #prompt #generate #interface

rwuerstchen

A simple interface for RWuerstchen image generation models models

5 unstable releases

0.3.2 Aug 14, 2024
0.3.0 Aug 13, 2024
0.2.1 Feb 28, 2024
0.2.0 Feb 18, 2024
0.1.0 Dec 16, 2023

#843 in Images

Download history 12/week @ 2024-08-26 1/week @ 2024-09-02 6/week @ 2024-09-09 172/week @ 2024-09-16 106/week @ 2024-09-23 104/week @ 2024-09-30 34/week @ 2024-10-07 69/week @ 2024-10-14 33/week @ 2024-10-21 46/week @ 2024-10-28 23/week @ 2024-11-04 24/week @ 2024-11-11 55/week @ 2024-11-18 38/week @ 2024-11-25 46/week @ 2024-12-02 72/week @ 2024-12-09

216 downloads per month
Used in 2 crates (via kalosm-vision)

MIT/Apache

180KB
4K SLoC

RWuerstchen

RWuerstchen is a rust wrapper for library for Wuerstchen implemented in the Candle ML framework.

RWuerstchen generates images efficiently from text prompts.

Usage

use futures_util::StreamExt;
use rwuerstchen::*;
#[tokio::main]
async fn main() -> Result<(), anyhow::Error> {
    let model = Wuerstchen::builder().build().await?;
    let settings = WuerstchenInferenceSettings::new(
        "a cute cat with a hat in a room covered with fur with incredible detail",
    );
    if let Ok(mut images) = model.run(settings) {
        while let Some(image) = images.next().await {
            if let Some(buf) = image.generated_image() {
                buf.save(&format!("{}.png",image.sample_num()))?;
            }
        }
    }
    Ok(())
}

Dependencies

~35–56MB
~1M SLoC