Update app.py

app.py

@@ -41,12 +41,12 @@ t2i_pipe = StableDiffusionPipeline.from_single_file(
     requires_safety_checker = False
 )
     
-if SAFETY_CHECKER == "True":
-    i2i_pipe = AutoPipelineForImage2Image.from_pretrained(
-        "stabilityai/sdxl-turbo",
-        torch_dtype=torch_dtype,
-        variant="fp16" if torch_dtype == torch.float16 else "fp32",
-    )
+# if SAFETY_CHECKER == "True":
+#     i2i_pipe = AutoPipelineForImage2Image.from_pretrained(
+#         "stabilityai/sdxl-turbo",
+#         torch_dtype=torch_dtype,
+#         variant="fp16" if torch_dtype == torch.float16 else "fp32",
+#     )
     # t2i_pipe = AutoPipelineForText2Image.from_pretrained(
     #     #"stabilityai/sdxl-turbo",
     #     # "wanghuging/demo_model",
@@ -55,13 +55,13 @@ if SAFETY_CHECKER == "True":
     #     torch_dtype=torch_dtype,
     #     variant="fp16" #if torch_dtype == torch.float16 else "fp32",
     # )
-else:
-    i2i_pipe = AutoPipelineForImage2Image.from_pretrained(
-        "stabilityai/sdxl-turbo",
-        safety_checker=None,
-        torch_dtype=torch_dtype,
-        variant="fp16" if torch_dtype == torch.float16 else "fp32",
-    )
+# else:
+#     i2i_pipe = AutoPipelineForImage2Image.from_pretrained(
+#         "stabilityai/sdxl-turbo",
+#         safety_checker=None,
+#         torch_dtype=torch_dtype,
+#         variant="fp16" if torch_dtype == torch.float16 else "fp32",
+#     )
     # t2i_pipe = AutoPipelineForText2Image.from_pretrained(
     #     #"stabilityai/sdxl-turbo",
     #     # "wanghuging/demo_model",
@@ -76,8 +76,8 @@ else:
 t2i_pipe.safety_checker = lambda images, clip_input: (images, False)
 t2i_pipe.to(device=torch_device, dtype=torch_dtype).to(device)
 t2i_pipe.set_progress_bar_config(disable=True)
-i2i_pipe.to(device=torch_device, dtype=torch_dtype).to(device)
-i2i_pipe.set_progress_bar_config(disable=True)
+# i2i_pipe.to(device=torch_device, dtype=torch_dtype).to(device)
+# i2i_pipe.set_progress_bar_config(disable=True)
 
 
 
@@ -89,6 +89,7 @@ def resize_crop(image, size=512):
 
 
 async def predict(init_image, prompt, strength, steps, seed=1231231):
+    init_image = None
     if init_image is not None:
         init_image = resize_crop(init_image)
         generator = torch.manual_seed(seed)
@@ -146,7 +147,7 @@ css = """
 }
 """
 with gr.Blocks(css=css) as demo:
-    init_image_state = gr.State()
+    # init_image_state = gr.State()
     with gr.Column(elem_id="container"):
         gr.Markdown(
             """# Derm-T2IM Text to Image Skin Cancer
@@ -161,14 +162,19 @@ with gr.Blocks(css=css) as demo:
                 scale=5,
                 container=False,
             )
+            neg_prompt = gr.Textbox(
+                placeholder="Insert your negative prompt here:",
+                scale=5,
+                container=False,
+            )
             generate_bt = gr.Button("Generate", scale=1)
         with gr.Row():
-            with gr.Column():
-                image_input = gr.Image(
-                    sources=["upload", "webcam", "clipboard"],
-                    label="Webcam",
-                    type="pil",
-                )
+            # with gr.Column():
+            #     image_input = gr.Image(
+            #         sources=["upload", "webcam", "clipboard"],
+            #         label="Webcam",
+            #         type="pil",
+            #     )
             with gr.Column():
                 image = gr.Image(type="filepath")
                 with gr.Accordion("Advanced options", open=False):
@@ -180,7 +186,7 @@ with gr.Blocks(css=css) as demo:
                         step=0.001,
                     )
                     steps = gr.Slider(
-                        label="Steps", value=2, minimum=1, maximum=10, step=1
+                        label="Steps", value=2, minimum=1, maximum=25, step=1
                     )
                     seed = gr.Slider(
                         randomize=True,
@@ -211,7 +217,7 @@ with gr.Blocks(css=css) as demo:
         #     ```
         #     """
         #     )
-
+        image_input = None
         inputs = [image_input, prompt, strength, steps, seed]
         generate_bt.click(fn=predict, inputs=inputs, outputs=image, show_progress=False)
         prompt.input(fn=predict, inputs=inputs, outputs=image, show_progress=False)