Update app.py

app.py

@@ -12,9 +12,7 @@ model_random = UNet2DModel(**model.config)
 model_random.save_pretrained("my_model")
 model_random = UNet2DModel.from_pretrained("my_model")
 import torch
-
 torch.manual_seed(0)
-
 noisy_sample = torch.randn(
     1, model.config.in_channels, model.config.sample_size, model.config.sample_size
 )
@@ -23,7 +21,6 @@ with torch.no_grad():
     noisy_residual = model(sample=noisy_sample, timestep=2).sample
 noisy_residual.shape
 from diffusers import DDPMScheduler
-
 scheduler = DDPMScheduler.from_config(repo_id)
 scheduler.config
 scheduler.save_config("my_scheduler")
@@ -34,48 +31,31 @@ less_noisy_sample = scheduler.step(
 less_noisy_sample.shape
 import PIL.Image
 import numpy as np
-
 def display_sample(sample, i):
     image_processed = sample.cpu().permute(0, 2, 3, 1)
     image_processed = (image_processed + 1.0) * 127.5
     image_processed = image_processed.numpy().astype(np.uint8)
-
     image_pil = PIL.Image.fromarray(image_processed[0])
     display(f"Image at step {i}")
     display(image_pil)
 model.to("cuda")
 noisy_sample = noisy_sample.to("cuda")
 import tqdm
-
 sample = noisy_sample
-
 for i, t in enumerate(tqdm.tqdm(scheduler.timesteps)):
-  # 1. predict noise residual
   with torch.no_grad():
       residual = model(sample, t).sample
-
-  # 2. compute less noisy image and set x_t -> x_t-1
   sample = scheduler.step(residual, t, sample).prev_sample
-
-  # 3. optionally look at image
   if (i + 1) % 50 == 0:
       display_sample(sample, i + 1)
 from diffusers import DDIMScheduler
-
 scheduler = DDIMScheduler.from_config(repo_id)
 scheduler.set_timesteps(num_inference_steps=50)
 import tqdm
-
 sample = noisy_sample
-
 for i, t in enumerate(tqdm.tqdm(scheduler.timesteps)):
-  # 1. predict noise residual
   with torch.no_grad():
       residual = model(sample, t).sample
-
-  # 2. compute previous image and set x_t -> x_t-1
   sample = scheduler.step(residual, t, sample).prev_sample
-
-  # 3. optionally look at image
   if (i + 1) % 10 == 0:
       display_sample(sample, i + 1)