fix

app.py

@@ -5,7 +5,7 @@ import numpy as np
 from diffusers import StableDiffusionDepth2ImgPipeline
 from pathlib import Path
 
-device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 dept2img = StableDiffusionDepth2ImgPipeline.from_pretrained(
     "stabilityai/stable-diffusion-2-depth",
     torch_dtype=torch.float16,
@@ -13,10 +13,14 @@ dept2img = StableDiffusionDepth2ImgPipeline.from_pretrained(
 
 
 def pad_image(input_image):
-    pad_w, pad_h = np.max(((2, 2), np.ceil(
-        np.array(input_image.size) / 64).astype(int)), axis=0) * 64 - input_image.size
+    pad_w, pad_h = (
+        np.max(((2, 2), np.ceil(np.array(input_image.size) / 64).astype(int)), axis=0)
+        * 64
+        - input_image.size
+    )
     im_padded = Image.fromarray(
-        np.pad(np.array(input_image), ((0, pad_h), (0, pad_w), (0, 0)), mode='edge'))
+        np.pad(np.array(input_image), ((0, pad_h), (0, pad_w), (0, 0)), mode="edge")
+    )
     w, h = im_padded.size
     if w == h:
         return im_padded
@@ -30,7 +34,17 @@ def pad_image(input_image):
         return new_image
 
 
-def predict(input_image, prompt, negative_prompt, steps, num_samples, scale, seed, strength, depth_image=None):
+def predict(
+    input_image,
+    prompt,
+    negative_prompt,
+    steps,
+    num_samples,
+    scale,
+    seed,
+    strength,
+    depth_image=None,
+):
     depth = None
     if depth_image is not None:
         depth_image = pad_image(depth_image)
@@ -56,32 +70,44 @@ def predict(input_image, prompt, negative_prompt, steps, num_samples, scale, see
         guidance_scale=scale,
         num_images_per_prompt=num_samples,
     )
-    return result['images']
+    return result["images"]
 
 
-block = gr.Blocks().queue()
-with block:
+css = """
+#gallery .fixed-height {
+    max-height: unset;
+}
+"""
+with gr.Blocks(css=css) as block:
     with gr.Row():
         with gr.Column():
             gr.Markdown("## Stable Diffusion 2 Depth2Img")
-            gr.HTML("<p><a href='https://huggingface.co/spaces/radames/stable-diffusion-depth2img?duplicate=true'><img src='https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14' alt='Duplicate Space'></a></p>")
-
+            gr.HTML(
+                "<p><a href='https://huggingface.co/spaces/radames/stable-diffusion-depth2img?duplicate=true'><img src='https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14' alt='Duplicate Space'></a></p>"
+            )
 
     with gr.Row():
         with gr.Column():
             input_image = gr.Image(type="pil")
-            depth_image = gr.Image(type="pil", label="Depth Image Optional")
+            with gr.Accordion("Depth Image Optional", open=False):
+                depth_image = gr.Image(type="pil")
             prompt = gr.Textbox(label="Prompt")
             negative_prompt = gr.Textbox(label="Negative Prompt")
 
             run_button = gr.Button("Run")
             with gr.Accordion("Advanced Options", open=False):
                 num_samples = gr.Slider(
-                    label="Images", minimum=1, maximum=4, value=1, step=1)
-                steps = gr.Slider(label="Steps", minimum=1,
-                                  maximum=50, value=50, step=1)
+                    label="Images", minimum=1, maximum=4, value=1, step=1
+                )
+                steps = gr.Slider(
+                    label="Steps", minimum=1, maximum=50, value=50, step=1
+                )
                 scale = gr.Slider(
-                    label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1
+                    label="Guidance Scale",
+                    minimum=0.1,
+                    maximum=30.0,
+                    value=9.0,
+                    step=0.1,
                 )
                 strength = gr.Slider(
                     label="Strength", minimum=0.0, maximum=1.0, value=0.9, step=0.01
@@ -93,26 +119,90 @@ with block:
                     step=1,
                     randomize=True,
                 )
-        with gr.Column():
-            gallery = gr.Gallery(label="Generated Images", show_label=False).style(grid=[2])
+        with gr.Column(scale=2):
+            with gr.Row():
+                gallery = gr.Gallery(
+                    label="Generated Images",
+                    show_label=False,
+                    elem_id="gallery",
+                )
     gr.Examples(
         examples=[
-            ["./examples/baby.jpg", "high definition photo of a baby astronaut space walking at the international space station with earth seeing from above in the background",
-             "", 50, 4, 9.0, 123123123, 0.8, None],
-            ["./examples/gol.jpg", "professional photo of a Elmo jumping between two high rises, beautiful colorful city landscape in the background",
-             "", 50, 4, 9.0, 1734133747, 0.9, None],
-            ["./examples/bag.jpg", "a photo of a bag of cookies in the bathroom", "low light, dark, blurry", 50, 4, 9.0, 1734133747, 0.9, "./examples/depth.jpg"],
-            ["./examples/smile_face.jpg", "a hand holding a very spherical orange", "low light, dark, blurry", 50, 4, 6.0, 961736534, 0.5, "./examples/smile_depth.jpg"]
-
+            [
+                "./examples/baby.jpg",
+                "high definition photo of a baby astronaut space walking at the international space station with earth seeing from above in the background",
+                "",
+                50,
+                4,
+                9.0,
+                123123123,
+                0.8,
+                None,
+            ],
+            [
+                "./examples/gol.jpg",
+                "professional photo of a Elmo jumping between two high rises, beautiful colorful city landscape in the background",
+                "",
+                50,
+                4,
+                9.0,
+                1734133747,
+                0.9,
+                None,
+            ],
+            [
+                "./examples/bag.jpg",
+                "a photo of a bag of cookies in the bathroom",
+                "low light, dark, blurry",
+                50,
+                4,
+                9.0,
+                1734133747,
+                0.9,
+                "./examples/depth.jpg",
+            ],
+            [
+                "./examples/smile_face.jpg",
+                "a hand holding a very spherical orange",
+                "low light, dark, blurry",
+                50,
+                4,
+                6.0,
+                961736534,
+                0.5,
+                "./examples/smile_depth.jpg",
+            ],
+        ],
+        inputs=[
+            input_image,
+            prompt,
+            negative_prompt,
+            steps,
+            num_samples,
+            scale,
+            seed,
+            strength,
+            depth_image,
         ],
-        inputs=[input_image, prompt, negative_prompt, steps,
-                num_samples, scale, seed, strength, depth_image],
         outputs=[gallery],
         fn=predict,
         cache_examples=True,
     )
-    run_button.click(fn=predict, inputs=[input_image, prompt, negative_prompt,
-                     steps, num_samples, scale, seed, strength, depth_image], outputs=[gallery])
-
+    run_button.click(
+        fn=predict,
+        inputs=[
+            input_image,
+            prompt,
+            negative_prompt,
+            steps,
+            num_samples,
+            scale,
+            seed,
+            strength,
+            depth_image,
+        ],
+        outputs=[gallery],
+    )
 
-block.launch(show_api=False)
+block.queue(api_open=False)
+block.launch(show_api=False)

requirements.txt

@@ -1,6 +1,6 @@
-gradio
-diffusers
-transformers
-torch
-accelerate
-xformers
+diffusers==0.24.0
+gradio==4.9.1
+numpy==1.26.2
+Pillow==10.1.0
+Pillow==10.1.0
+torch==2.1.2