Add details on wuerstchen. (#911)

README.md

@@ -71,6 +71,11 @@ We also provide a some command line based examples using state of the art models
 
 <img src="https://github.com/huggingface/candle/raw/main/candle-examples/examples/stable-diffusion/assets/stable-diffusion-xl.jpg" width="200">
 
+- [Wuerstchen](./candle-examples/examples/wuerstchen/): another text to
+  image generative model.
+
+<img src="https://github.com/huggingface/candle/raw/main/candle-examples/examples/wuerstchen/assets/cat.jpg" width="200">
+
 - [yolo-v3](./candle-examples/examples/yolo-v3/) and
   [yolo-v8](./candle-examples/examples/yolo-v8/): object detection and pose
   estimation models.
@@ -142,6 +147,7 @@ If you have an addition to this list, please submit a pull request.
         - Bert.
     - Whisper (multi-lingual support).
     - Stable Diffusion v1.5, v2.1, XL v1.0.
+    - Wurstchen v2.
     - Computer Vision Models.
         - DINOv2.
         - EfficientNet.

candle-examples/examples/wuerstchen/README.md

@@ -0,0 +1,27 @@
+# candle-wuerstchen: Efficient Pretraining of Text-to-Image Models
+
+![anthropomorphic cat dressed as a fire fighter](./assets/cat.jpg)
+
+The `wuerstchen` example is a port of the [diffusers
+implementation](https://github.com/huggingface/diffusers/tree/19edca82f1ff194c07317369a92b470dbae97f34/src/diffusers/pipelines/wuerstchen) for Würstchen v2.
+The candle implementation reproduces the same structure/files for models and
+pipelines. Useful resources:
+
+- [Official implementation](https://github.com/dome272/Wuerstchen).
+- [Arxiv paper](https://arxiv.org/abs/2306.00637).
+- Blog post: [Introducing Würstchen: Fast Diffusion for Image Generation](https://huggingface.co/blog/wuerstchen).
+
+## Getting the weights
+
+The weights are automatically downloaded for you from the [HuggingFace
+Hub](https://huggingface.co/) on the first run. There are various command line
+flags to use local files instead, run with `--help` to learn about them.
+
+## Running some example.
+
+```bash
+cargo run --example wuerstchen --release --features cuda,cudnn -- \
+  --prompt "Anthropomorphic cat dressed as a fire fighter"
+```
+
+The final image is named `sd_final.png` by default.