Update app.py

app.py

@@ -147,7 +147,10 @@ def latents_to_pil(latents):
 
 If you uncomment the cell below you'll see that in this case the `scheduler.add_noise` function literally just adds noise scaled by sigma: `noisy_samples = original_samples + noise * sigmas`
 """
-
+encoded = pil_to_latent(input_image)
+encoded.shape
+decoded = latents_to_pil(encoded)[0]
+decoded
 # ??scheduler.add_noise
 
 """Other diffusion models may be trained with different noising and scheduling approaches, some of which keep the variance fairly constant across noise levels ('variance preserving') with different scaling and mixing tricks instead of having noisy latents with higher and higher variance as more noise is added ('variance exploding').