increae res

app.py

@@ -22,16 +22,16 @@ pipe.enable_lora()
 # vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev", subfolder="vae")
 # processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
 
-preprocess = transforms.Compose(
-    [
-        transforms.Resize(
-            (vae.config.sample_size, vae.config.sample_size),
-            interpolation=transforms.InterpolationMode.BILINEAR,
-        ),
-        transforms.ToTensor(),
-        transforms.Normalize([0.5], [0.5]),
-    ]
-)
+# preprocess = transforms.Compose(
+#     [
+#         transforms.Resize(
+#             (vae.config.sample_size, vae.config.sample_size),
+#             interpolation=transforms.InterpolationMode.BILINEAR,
+#         ),
+#         transforms.ToTensor(),
+#         transforms.Normalize([0.5], [0.5]),
+#     ]
+# )
 #
 # image_np = image[0].cpu().numpy()  # Move to CPU and convert to NumPy
 
@@ -42,49 +42,49 @@ preprocess = transforms.Compose(
 
 # image = Image.fromarray(image_np)
 
-def calculate_optimal_dimensions(image: Image.Image):
-    # Extract the original dimensions
-    original_width, original_height = image.size
+# def calculate_optimal_dimensions(image: Image.Image):
+#     # Extract the original dimensions
+#     original_width, original_height = image.size
 
-    # Set constants
-    MIN_ASPECT_RATIO = 9 / 16
-    MAX_ASPECT_RATIO = 16 / 9
-    FIXED_DIMENSION = 1024
+#     # Set constants
+#     MIN_ASPECT_RATIO = 9 / 16
+#     MAX_ASPECT_RATIO = 16 / 9
+#     FIXED_DIMENSION = 1024
 
-    # Calculate the aspect ratio of the original image
-    original_aspect_ratio = original_width / original_height
+#     # Calculate the aspect ratio of the original image
+#     original_aspect_ratio = original_width / original_height
 
-    # Determine which dimension to fix
-    if original_aspect_ratio > 1:  # Wider than tall
-        width = FIXED_DIMENSION
-        height = round(FIXED_DIMENSION / original_aspect_ratio)
-    else:  # Taller than wide
-        height = FIXED_DIMENSION
-        width = round(FIXED_DIMENSION * original_aspect_ratio)
+#     # Determine which dimension to fix
+#     if original_aspect_ratio > 1:  # Wider than tall
+#         width = FIXED_DIMENSION
+#         height = round(FIXED_DIMENSION / original_aspect_ratio)
+#     else:  # Taller than wide
+#         height = FIXED_DIMENSION
+#         width = round(FIXED_DIMENSION * original_aspect_ratio)
 
-    # Ensure dimensions are multiples of 8
-    width = (width // 8) * 8
-    height = (height // 8) * 8
+#     # Ensure dimensions are multiples of 8
+#     width = (width // 8) * 8
+#     height = (height // 8) * 8
 
-    # Enforce aspect ratio limits
-    calculated_aspect_ratio = width / height
-    if calculated_aspect_ratio > MAX_ASPECT_RATIO:
-        width = (height * MAX_ASPECT_RATIO // 8) * 8
-    elif calculated_aspect_ratio < MIN_ASPECT_RATIO:
-        height = (width / MIN_ASPECT_RATIO // 8) * 8
+#     # Enforce aspect ratio limits
+#     calculated_aspect_ratio = width / height
+#     if calculated_aspect_ratio > MAX_ASPECT_RATIO:
+#         width = (height * MAX_ASPECT_RATIO // 8) * 8
+#     elif calculated_aspect_ratio < MIN_ASPECT_RATIO:
+#         height = (width / MIN_ASPECT_RATIO // 8) * 8
 
-    # Ensure width and height remain above the minimum dimensions
-    width = max(width, 576) if width == FIXED_DIMENSION else width
-    height = max(height, 576) if height == FIXED_DIMENSION else height
+#     # Ensure width and height remain above the minimum dimensions
+#     width = max(width, 576) if width == FIXED_DIMENSION else width
+#     height = max(height, 576) if height == FIXED_DIMENSION else height
 
-    return width, height
+#     return width, height
 
 @spaces.GPU(durations=300)
-def infer(edit_images, prompt, prompt_2, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
+def infer(edit_images, prompt, prompt2, width, height, seed=42, randomize_seed=False, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
     # pipe.enable_xformers_memory_efficient_attention()
 
     image = edit_images["background"]
-    width, height = calculate_optimal_dimensions(image)
+    # width, height = calculate_optimal_dimensions(image)
     mask = edit_images["layers"][0]
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
@@ -93,7 +93,7 @@ def infer(edit_images, prompt, prompt_2, seed=42, randomize_seed=False, width=10
     image = pipe(
         # mask_image_latent=vae.encode(controlImage),
         prompt=prompt,
-        prompt_2=prompt_2,
+        prompt_2=prompt2,
         image=image,
         mask_image=mask,
         height=height,
@@ -147,7 +147,7 @@ with gr.Blocks(css=css) as demo:
                     placeholder="Enter your prompt",
                     container=False,
                 )
-                prompt = gr.Text(
+                prompt2 = gr.Text(
                     label="Prompt2",
                     show_label=False,
                     max_lines=2,
@@ -208,10 +208,28 @@ with gr.Blocks(css=css) as demo:
                     value=28,
                 )
 
+            with gr.Row():
+
+                width = gr.Slider(
+                    label="width",
+                    minimum=512,
+                    maximum=3072,
+                    step=1,
+                    value=1024,
+                )
+
+                num_inference_steps = gr.Slider(
+                    label="height",
+                    minimum=512,
+                    maximum=3072,
+                    step=1,
+                    value=1024,
+                )
+
     gr.on(
         triggers=[run_button.click, prompt.submit],
         fn = infer,
-        inputs = [edit_image, prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        inputs = [edit_image, prompt, prompt2, width, height, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
         outputs = [result, seed]
     )