Update README.md

README.md

@@ -7,5 +7,26 @@ inference: false
 ---
 # SDXL-VAE-FP16-Fix
 
-SDXL-VAE-FP16-Fix is a version of the SDXL VAE decoder which was modified to work in fp16 precision without generating NaNs.
-SDXL-VAE-FP16-Fix is potentially useful for running the SDXL VAE on platforms where bf16 is not available.
+SDXL-VAE-FP16-Fix is the [SDXL VAE](https://huggingface.co/stabilityai/sdxl-vae), but modified to run in fp16 precision without generating NaNs.
+
+```python
+from diffusers import DiffusionPipeline, AutoencoderKL
+import torch
+
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16, variant="fp16").to("cuda")
+fixed_vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix").half().to("cuda")
+
+prompt = "An astronaut riding a green horse"
+latents = pipe(prompt=prompt, output_type="latent").images
+
+for vae in (pipe.vae, fixed_vae):
+    for dtype in (torch.float32, torch.float16):
+        with torch.no_grad(), torch.cuda.amp.autocast(dtype=torch.float16, enabled=(dtype==torch.float16)):
+            print(dtype, "sdxl-vae" if vae == pipe.vae else "sdxl-vae-fp16-fix")
+            display(pipe.image_processor.postprocess(vae.decode(latents / vae.config.scaling_factor).sample)[0])
+```
+
+| VAE                   | Decoding in `float32` precision | Decoding in `float16` precision |
+| --------------------- | ------------------------------- | ------------------------------- |
+| SDXL-VAE              | ✅ ![](./images/orig-fp32.png)  | ⚠️ ![](./images/orig-fp16.png)  |
+| SDXL-VAE-FP16-Fix     | ✅ ![](./images/fix-fp32.png)   | ✅ ![](./images/fix-fp16.png)   |