Update app.py

app.py

@@ -1,73 +1,63 @@
 import gradio as gr
 import numpy as np
-
-import spaces
 import torch
-import spaces
 import random
-
-from diffusers import FluxFillPipeline
+from diffusers import FluxInpaintPipeline
 from PIL import Image
-
+import spaces
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 2048
 
-pipe = FluxFillPipeline.from_pretrained("black-forest-labs/FLUX.1-Fill-dev", torch_dtype=torch.bfloat16).to("cuda")
+# Load pipeline with VAE enabled
+pipe = FluxInpaintPipeline.from_pretrained(
+    "black-forest-labs/FLUX.1-Fill-dev", 
+    torch_dtype=torch.bfloat16
+).to("cuda")
 pipe.load_lora_weights("alvdansen/flux-koda")
-# pipe.enable_sequential_cpu_offload()
-# pipe.enable_fp16()
 pipe.enable_lora()
-# pipe.vae.enable_slicing()
-# pipe.vae.enable_tiling()
+pipe.vae.enable_slicing()  # Enable slicing for better memory efficiency
+pipe.vae.enable_tiling()  # Enable tiling for larger images
 
 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
 
-    # 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
+    if original_aspect_ratio > 1:
         width = FIXED_DIMENSION
         height = round(FIXED_DIMENSION / original_aspect_ratio)
-    else:  # Taller than wide
+    else:
         height = FIXED_DIMENSION
         width = round(FIXED_DIMENSION * original_aspect_ratio)
 
-    # 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
 
-    # 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
 
-@spaces.GPU(durations=300)
-def infer(edit_images, prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
-    # pipe.enable_xformers_memory_efficient_attention()
-
+@spaces.GPU
+def infer(edit_images, prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28):
     image = edit_images["background"]
     width, height = calculate_optimal_dimensions(image)
     mask = edit_images["layers"][0]
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
-    image = pipe(
+
+    # Run the inpainting pipeline
+    output = pipe(
         prompt=prompt,
         image=image,
         mask_image=mask,
@@ -76,23 +66,15 @@ def infer(edit_images, prompt, seed=42, randomize_seed=False, width=1024, height
         guidance_scale=guidance_scale,
         num_inference_steps=num_inference_steps,
         generator=torch.Generator(device='cuda').manual_seed(seed),
-        # lora_scale=0.75 // not supported in this version
-    ).images[0]
+    )
 
-    output_image_jpg = image.convert("RGB")
+    output_image = output.images[0]
+    output_image_jpg = output_image.convert("RGB")
     output_image_jpg.save("output.jpg", "JPEG")
 
     return output_image_jpg, seed
-    # return image, seed
 
-examples = [
-    "photography of a young woman,  accent lighting,  (front view:1.4),  "
-    # "a tiny astronaut hatching from an egg on the moon",
-    # "a cat holding a sign that says hello world",
-    # "an anime illustration of a wiener schnitzel",
-]
-
-css="""
+css = """
 #col-container {
     margin: 0 auto;
     max-width: 1000px;
@@ -100,87 +82,44 @@ css="""
 """
 
 with gr.Blocks(css=css) as demo:
-
     with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""# FLUX.1 [dev]
-        """)
+        gr.Markdown("# FLUX.1 [dev]")
         with gr.Row():
             with gr.Column():
                 edit_image = gr.ImageEditor(
-                    label='Upload and draw mask for inpainting',
-                    type='pil',
+                    label="Upload and draw mask for inpainting",
+                    type="pil",
                     sources=["upload", "webcam"],
-                    image_mode='RGB',
-                    layers=False,
+                    image_mode="RGB",
+                    layers=True,
                     brush=gr.Brush(colors=["#FFFFFF"]),
-                    # height=600
                 )
-                prompt = gr.Text(
+                prompt = gr.Textbox(
                     label="Prompt",
                     show_label=False,
                     max_lines=2,
                     placeholder="Enter your prompt",
-                    container=False,
                 )
                 run_button = gr.Button("Run")
 
             result = gr.Image(label="Result", show_label=False)
 
         with gr.Accordion("Advanced Settings", open=False):
-
             seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
+                label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0
             )
-
             randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+            guidance_scale = gr.Slider(
+                label="Guidance Scale", minimum=1, maximum=30, step=0.5, value=3.5
+            )
+            num_inference_steps = gr.Slider(
+                label="Number of inference steps", minimum=1, maximum=50, step=1, value=28
+            )
 
-            with gr.Row():
-
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,
-                    visible=False
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,
-                    visible=False
-                )
-
-            with gr.Row():
-
-                guidance_scale = gr.Slider(
-                    label="Guidance Scale",
-                    minimum=1,
-                    maximum=30,
-                    step=0.5,
-                    value=50,
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=28,
-                )
-
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn = infer,
-        inputs = [edit_image, prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result, seed]
+    run_button.click(
+        fn=infer,
+        inputs=[edit_image, prompt, seed, randomize_seed, guidance_scale, num_inference_steps],
+        outputs=[result, seed],
     )
 
 demo.launch()