Duplicate from radames/stable-diffusion-depth2img

Co-authored-by: Radamés Ajna <[email protected]>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,5 @@
+**/midas_models/
+stable-diffusion-2-depth/
+__pycache__
+gradio_cached_examples
+venv/

Dockerfile

@@ -0,0 +1,52 @@
+FROM nvidia/cuda:11.3.1-cudnn8-devel-ubuntu18.04
+CMD nvidia-smi
+
+ENV DEBIAN_FRONTEND noninteractive
+RUN apt-get update && apt-get install -y \
+        git \
+        make build-essential libssl-dev zlib1g-dev \
+        libbz2-dev libreadline-dev libsqlite3-dev wget curl llvm \
+        libncursesw5-dev xz-utils tk-dev libxml2-dev libxmlsec1-dev libffi-dev liblzma-dev  \
+    	ffmpeg libsm6 libxext6 cmake libgl1-mesa-glx \
+		&& rm -rf /var/lib/apt/lists/*
+        && git lfs install
+
+
+RUN useradd -ms /bin/bash user
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+RUN curl https://pyenv.run | bash
+ENV PATH=$HOME/.pyenv/shims:$HOME/.pyenv/bin:$PATH
+RUN pyenv install 3.8.15 && \
+    pyenv global 3.8.15 && \
+    pyenv rehash && \
+    pip install --no-cache-dir --upgrade pip setuptools wheel
+
+ENV WORKDIR=/code
+WORKDIR $WORKDIR
+RUN chown -R user:user $WORKDIR
+RUN chmod -R 777 $WORKDIR
+
+COPY requirements.txt $WORKDIR/requirements.txt
+RUN pip install --no-cache-dir --upgrade -r $WORKDIR/requirements.txt
+RUN pip install ninja
+
+RUN curl https://github.com/isl-org/DPT/releases/download/1_0/dpt_hybrid-midas-501f0c75.pt --create-dirs -o $WORKDIR/midas_models/dpt_hybrid-midas-501f0c75.pt 
+RUN curl https://github.com/isl-org/DPT/releases/download/1_0/dpt_large-midas-2f21e586.pt --create-dirs -o $WORKDIR/midas_models/dpt_large-midas-2f21e586.pt
+
+COPY . .
+
+ARG TORCH_CUDA_ARCH_LIST=7.5+PTX
+
+USER root
+RUN chown -R user:user $HOME
+RUN chmod -R 777 $HOME
+RUN chown -R user:user $WORKDIR
+RUN chmod -R 777 $WORKDIR
+
+USER user
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -0,0 +1,13 @@
+---
+title: Stablediffusion Depth2img
+emoji: 🧊🖼
+colorFrom: green
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.11.0
+app_file: app.py
+pinned: false
+duplicated_from: radames/stable-diffusion-depth2img
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,117 @@
+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)

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+--extra-index-url https://download.pytorch.org/whl/cu113 
+diffusers[torch]
+git+https://github.com/huggingface/transformers@main