Update to latest diffusers and enable CPU

Thanks for duplicating the Space, this is a fix to make it work on CPU, however it's very slow!
but you can always enable a GPU Hardware and switch back.

app.py

@@ -1,6 +1,117 @@
-from os import system
-system('git clone https://huggingface.co/stabilityai/stable-diffusion-2-depth && cd stable-diffusion-2-depth && git lfs fetch && git lfs pull')
-system('pip install -e stablediffusion')
-system('curl -LJ https://github.com/isl-org/DPT/releases/download/1_0/dpt_hybrid-midas-501f0c75.pt --create-dirs -o stablediffusion/midas_models/dpt_hybrid-midas-501f0c75.pt')
-system('curl -LJ https://github.com/isl-org/DPT/releases/download/1_0/dpt_large-midas-2f21e586.pt --create-dirs -o stablediffusion/midas_models/dpt_large-midas-2f21e586.pt')
-system('cd stablediffusion && python scripts/gradio/depth2img.py  configs/stable-diffusion/v2-midas-inference.yaml ../stable-diffusion-2-depth/512-depth-ema.ckpt')
+import gradio as gr
+import torch
+from PIL import Image
+import numpy as np
+from diffusers import StableDiffusionDepth2ImgPipeline
+from pathlib import Path
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+dept2img = StableDiffusionDepth2ImgPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-2-depth",
+    torch_dtype=torch.float16,
+).to(device)
+
+
+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
+    im_padded = Image.fromarray(
+        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
+    elif w > h:
+        new_image = Image.new(im_padded.mode, (w, w), (0, 0, 0))
+        new_image.paste(im_padded, (0, (w - h) // 2))
+        return new_image
+    else:
+        new_image = Image.new(im_padded.mode, (h, h), (0, 0, 0))
+        new_image.paste(im_padded, ((h - w) // 2, 0))
+        return new_image
+
+
+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)
+        depth_image = depth_image.resize((512, 512))
+        depth = np.array(depth_image.convert("L"))
+        depth = depth.astype(np.float32) / 255.0
+        depth = depth[None, None]
+        depth = torch.from_numpy(depth)
+    init_image = input_image.convert("RGB")
+    image = pad_image(init_image)  # resize to integer multiple of 32
+    image = image.resize((512, 512))
+    result = dept2img(
+        image=image,
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        depth_image=depth,
+        seed=seed,
+        strength=strength,
+        num_inference_steps=steps,
+        guidance_scale=scale,
+        num_images_per_prompt=num_samples,
+    )
+    return result['images']
+
+
+block = gr.Blocks().queue()
+with 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>")
+
+
+    with gr.Row():
+        with gr.Column():
+            input_image = gr.Image(source='upload', type="pil")
+            depth_image = gr.Image(
+                source='upload', type="pil", label="Depth image Optional", value=None)
+            prompt = gr.Textbox(label="Prompt")
+            negative_prompt = gr.Textbox(label="Negative Pompt")
+
+            run_button = gr.Button(label="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)
+                scale = gr.Slider(
+                    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
+                )
+                seed = gr.Slider(
+                    label="Seed",
+                    minimum=0,
+                    maximum=2147483647,
+                    step=1,
+                    randomize=True,
+                )
+        with gr.Column():
+            gallery = gr.Gallery(label="Generated images", show_label=False).style(
+                grid=[2], height="auto")
+    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"]
+
+        ],
+        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])
+
+
+block.launch(show_api=False)