Update app.py

Changing "torch_dtype=torch.float16" to "torch.get_default_dtype()" provides compatibility with the free CPU on Huggingface.co
The renders take hundreds of minutes on the CPU, and generating more than one image at a time causes a connection error.
The image quality is excellent.

app.py

@@ -54,7 +54,7 @@ current_model_path = current_model.path
 if is_colab:
   pipe = StableDiffusionPipeline.from_pretrained(
       current_model.path,
-      torch_dtype=torch.float16,
+      torch_dtype=torch.get_default_dtype(),
       scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler"),
       safety_checker=lambda images, clip_input: (images, False)
       )
@@ -62,7 +62,7 @@ if is_colab:
 else:
   pipe = StableDiffusionPipeline.from_pretrained(
       current_model.path,
-      torch_dtype=torch.float16,
+      torch_dtype=torch.get_default_dtype(),
       scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler")
       )
     
@@ -120,14 +120,14 @@ def txt_to_img(model_path, prompt, n_images, neg_prompt, guidance, steps, width,
         if is_colab or current_model == custom_model:
           pipe = StableDiffusionPipeline.from_pretrained(
               current_model_path,
-              torch_dtype=torch.float16,
+              torch_dtype=torch.get_default_dtype(),
               scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler"),
               safety_checker=lambda images, clip_input: (images, False)
               )
         else:
           pipe = StableDiffusionPipeline.from_pretrained(
               current_model_path,
-              torch_dtype=torch.float16,
+              torch_dtype=torch.get_default_dtype(),
               scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler")
               )
           # pipe = pipe.to("cpu")
@@ -164,14 +164,14 @@ def img_to_img(model_path, prompt, n_images, neg_prompt, img, strength, guidance
         if is_colab or current_model == custom_model:
           pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
               current_model_path,
-              torch_dtype=torch.float16,
+              torch_dtype=torch.get_default_dtype(),
               scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler"),
               safety_checker=lambda images, clip_input: (images, False)
               )
         else:
           pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
               current_model_path,
-              torch_dtype=torch.float16,
+              torch_dtype=torch.get_default_dtype(),
               scheduler=DPMSolverMultistepScheduler.from_pretrained(current_model.path, subfolder="scheduler")
               )
           # pipe = pipe.to("cpu")