Update app.py

app.py

@@ -95,7 +95,7 @@ def display_and_download_images(output_images, metadata):
             
 PIPELINE_NAMES = Literal["txt2img", "inpaint", "img2img"]
 
-DEFAULT_PROMPT = "sprinkled donut sitting on top of a purple cherry apple, colorful hyperrealism"
+DEFAULT_PROMPT = "sprinkled donut sitting on top of a green cherry and pink apple, colorful hyperrealism"
 DEFAULT_WIDTH, DEFAULT_HEIGHT = 512, 512
 OUTPUT_IMAGE_KEY = "output_img"
 LOADED_IMAGE_KEY = "loaded_image"
@@ -225,23 +225,30 @@ def generate(
 
 
 def prompt_and_generate_button(prefix, pipeline_name: PIPELINE_NAMES, **kwargs):
-    prompt = st.text_area(
-        "Prompt",
-        value=DEFAULT_PROMPT,
-        key=f"{prefix}-prompt",
-    )
-    negative_prompt = st.text_area(
-        "Negative prompt",
-        value="(disfigured), bad quality, ((bad art)), ((deformed)), ((extra limbs)), (((duplicate))), ((morbid)), (((ugly)), blurry, ((bad anatomy)), (((bad proportions))), cloned face, body out of frame, out of frame, bad anatomy, gross proportions, (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), (fused fingers), (too many fingers), (((long neck))), Deformed, blurry",
-        key=f"{prefix}-negative-prompt",
-    )
+    # Change 1: Prompt and Negative prompt to be on 1 line split like width and high (2 columns)
     col1, col2 = st.columns(2)
     with col1:
-        steps = st.slider("Number of inference steps", min_value=11, max_value=69, value=14, key=f"{prefix}-inference-steps")
+        prompt = st.text_area(
+            "Prompt",
+            value=DEFAULT_PROMPT,
+            key=f"{prefix}-prompt",
+        )
     with col2:
-        guidance_scale = st.slider(
-            "Guidance scale", min_value=0.0, max_value=20.0, value=7.5, step=0.5, key=f"{prefix}-guidance-scale"
+        negative_prompt = st.text_area(
+            "Negative prompt",
+            value="(disfigured), bad quality, ((bad art)), ((deformed)), ((extra limbs)), (((duplicate))), ((morbid)), (((ugly)), blurry, ((bad anatomy)), (((bad proportions))), (malformed limbs), ((missing arms)), ((missing legs)), (((extra arms))), (((extra legs))), (fused fingers), (too many fingers), (((long neck))), Deformed, blurry"
+            key=f"{prefix}-negative-prompt",
         )
+
+    # Change 2: Number of inference steps, Guidance scale, and Number of images to generate to be in a line, 3 columns
+    col1, col2, col3 = st.columns(3)
+    with col1:
+        steps = st.slider("Number of inference steps", min_value=11, max_value=69, value=14, key=f"{prefix}-inference-steps")
+    with col2:
+        guidance_scale = st.slider("Guidance scale", min_value=0.0, max_value=20.0, value=7.5, step=0.5, key=f"{prefix}-guidance-scale")
+    with col3:
+        num_images = st.slider("Number of images to generate", min_value=1, max_value=2, value=1, key=f"{prefix}-num-images")
+
     # Add a select box for the schedulers
     scheduler_name = st.selectbox(
         "Choose a Scheduler",
@@ -251,41 +258,35 @@ def prompt_and_generate_button(prefix, pipeline_name: PIPELINE_NAMES, **kwargs):
     )
     scheduler_class = AVAILABLE_SCHEDULERS[scheduler_name]  # Get the selected scheduler class
 
-
     pipe = get_pipeline(pipeline_name, scheduler_name=scheduler_name)        
-    
-   # enable_attention_slicing = st.checkbox('Enable attention slicing (enables higher resolutions but is slower)', key=f"{prefix}-attention-slicing", value=True)
-   # enable_xformers = st.checkbox('Enable xformers library (better memory usage)', key=f"{prefix}-xformers", value=True)
-    num_images = st.slider("Number of images to generate", min_value=1, max_value=4, value=1, key=f"{prefix}-num-images")
+
+    # enable_attention_slicing = st.checkbox('Enable attention slicing (enables higher resolutions but is slower)', key=f"{prefix}-attention-slicing", value=True)
+    # enable_xformers = st.checkbox('Enable xformers library (better memory usage)', key=f"{prefix}-xformers", value=True)
 
     images = []
 
-    
     if st.button("Generate images", key=f"{prefix}-btn"):
         with st.spinner("Generating image..."):
             images = generate(
                 prompt,
                 pipeline_name,
-                num_images=num_images,  # add this
+                num_images=num_images, # add this
                 negative_prompt=negative_prompt,
                 steps=steps,
                 guidance_scale=guidance_scale,
-                enable_attention_slicing=True,  # value always set to True
-                enable_xformers=True,  # value always set to True
+                enable_attention_slicing=True, # value always set to True
+                enable_xformers=True, # value always set to True
                 **kwargs,
             )
-
-    for i, image in enumerate(images):  # loop over each image
-        set_image(f"{OUTPUT_IMAGE_KEY}_{i}", image.copy())  # save each image with a unique key
-
-
-    image_indices = [int(key.split('_')[-1]) for key in st.session_state.keys() if OUTPUT_IMAGE_KEY in key]
-    cols = st.columns(len(image_indices) if image_indices else 1)  # create a column for each image or a single one if no images
-    for i in range(max(image_indices) + 1 if image_indices else 1):  # loop over each image index
-        output_image_key = f"{OUTPUT_IMAGE_KEY}_{i}"
-        output_image = get_image(output_image_key)
-        if output_image:
-            cols[i].image(output_image)
+        for i, image in enumerate(images): # loop over each image
+            set_image(f"{OUTPUT_IMAGE_KEY}_{i}", image.copy()) # save each image with a unique key
+        image_indices = [int(key.split('_')[-1]) for key in st.session_state.keys() if OUTPUT_IMAGE_KEY in key]
+        cols = st.columns(len(image_indices) if image_indices else 1) # create a column for each image or a single one if no images
+        for i in range(max(image_indices) + 1 if image_indices else 1): # loop over each image index
+            output_image_key = f"{OUTPUT_IMAGE_KEY}_{i}"
+            output_image = get_image(output_image_key)
+            if output_image:
+                cols[i].image(output_image)