Merge pull request #6 from nateraw/package-try-2

Fix packaging issues
nateraw · Sep 7, 2022 · e2ddeab · e2ddeab
2 parents 7d349cf + 4af0cc2
commit e2ddeab
Show file tree

Hide file tree

Showing 9 changed files with 357 additions and 54 deletions.
diff --git a/.github/workflows/python-publish.yml b/.github/workflows/python-publish.yml
@@ -0,0 +1,31 @@
+# This workflows will upload a Python Package using Twine when a release is created
+# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
+
+name: Upload Python Package
+
+on:
+  release:
+    types: [created]
+
+jobs:
+  deploy:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.x'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install setuptools wheel twine
+    - name: Build and publish
+      env:
+        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
+        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
+      run: |
+        python setup.py sdist bdist_wheel
+        twine upload dist/*
diff --git a/README.md b/README.md
@@ -26,40 +26,42 @@ The app is built with [Gradio](https://gradio.app/), which allows you to interac
     - Set the `num_walk_steps` - for testing you can use a small number like 3 or 5, but to get great results you'll want to use something larger (60-200 steps). 
     - You can (and should) use the `name` input to separate out where the images/videos are saved. (Note that currently ffmpeg will not overwrite if you already made a video with the same name. You'll have to use ffmpeg to create the video yourself if the app fails to do so.)
 
-### The Script
+### Python Package
 
 #### Setup
 
+Install the package
+
 ```
-git clone https://github.com/nateraw/stable-diffusion-videos
-cd stable-diffusion-videos
-pip install -r requirements.txt
+pip install stable_diffusion_videos
 ```
 
-#### Usage
+Authenticate with Hugging Face
 
-If you would prefer to use the `stable_diffusion_walk.py` script directly, you can do so by running:
-
-Run with `num_steps` set to 3 or 5 for testing, then up it to something like 60-200 for better results.
-
-```bash
-python stable_diffusion_walk.py \
-    --prompts "['a cat', 'a dog', 'a horse']" \
-    --seeds 903,123,42 \
-    --output_dir dreams \
-    --name animals_test \
-    --guidance_scale 8.5 \
-    --num_steps 5 \
-    --height 512 \
-    --width 512 \
-    --num_inference_steps 50 \
-    --scheduler klms \
-    --disable_tqdm \
-    --make_video \
-    --use_lerp_for_text \
-    --do_loop
+```
+huggingface-cli login
 ```
 
+#### Usage
+
+```python
+from stable_diffusion_videos import walk
+
+walk(
+    prompts=['a cat', 'a dog'],
+    seeds=[42, 1337],
+    output_dir='dreams',     # Where images/videos will be saved
+    name='animals_test',     # Subdirectory of output_dir where images/videos will be saved
+    guidance_scale=8.5,      # Higher adheres to prompt more, lower lets model take the wheel
+    num_steps=5,             # Change to 60-200 for better results...3-5 for testing
+    num_inference_steps=50, 
+    scheduler='klms',        # One of: "klms", "default", "ddim"
+    disable_tqdm=False,      # Set to True to disable tqdm progress bar
+    make_video=True,         # If false, just save images
+    use_lerp_for_text=True,  # Use lerp for text embeddings instead of slerp
+    do_loop=False,           # Change to True if you want last prompt to loop back to first prompt
+)
+```
 
 ## Credits
 

diff --git a/requirements.txt b/requirements.txt
@@ -1,5 +1,5 @@
 transformers
-git+https://github.com/huggingface/diffusers@f085d2f5c6569a1c0d90327c51328622036ef76e
+diffusers==0.2.4
 scipy
 fire
 gradio
diff --git a/setup.py b/setup.py
@@ -0,0 +1,28 @@
+from setuptools import find_packages, setup
+
+
+def get_version() -> str:
+    rel_path = "stable_diffusion_videos/__init__.py"
+    with open(rel_path, "r") as fp:
+        for line in fp.read().splitlines():
+            if line.startswith("__version__"):
+                delim = '"' if '"' in line else "'"
+                return line.split(delim)[1]
+    raise RuntimeError("Unable to find version string.")
+
+
+with open("requirements.txt", "r") as f:
+    requirements = f.read().splitlines()
+
+setup(
+    name="stable_diffusion_videos",
+    version=get_version(),
+    author="Nathan Raw",
+    author_email="[email protected]",
+    description=(
+        "Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts."
+    ),
+    license="Apache",
+    install_requires=requirements,
+    packages=find_packages(),
+)
diff --git a/stable_diffusion_videos.ipynb b/stable_diffusion_videos.ipynb
@@ -5,7 +5,7 @@
     "colab": {
       "provenance": [],
       "collapsed_sections": [],
-      "authorship_tag": "ABX9TyN/ZOFCUNqBdfOYeo31y+2Q",
+      "authorship_tag": "ABX9TyMDsciHN/HhWLYEdURcy00d",
       "include_colab_link": true
     },
     "kernelspec": {
@@ -26,7 +26,7 @@
         "colab_type": "text"
       },
       "source": [
-        "<a href=\"https://colab.research.google.com/github/nateraw/stable-diffusion-videos/blob/main/stable_diffusion_videos.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+        "<a href=\"https://colab.research.google.com/github/nateraw/stable-diffusion-videos/blob/package-try-2/stable_diffusion_videos.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
       ]
     },
     {
@@ -47,7 +47,7 @@
         "Enjoy 🤗"
       ],
       "metadata": {
-        "id": "B4V57sVzLHu3"
+        "id": "z4GhhH25OdYq"
       }
     },
     {
@@ -56,21 +56,19 @@
         "## Setup"
       ],
       "metadata": {
-        "id": "0L9zhmONL81f"
+        "id": "dvdCBpWWOhW-"
       }
     },
     {
       "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": null,
       "metadata": {
-        "id": "klUR9ie1DVm-"
+        "id": "Xwfc0ej1L9A0"
       },
       "outputs": [],
       "source": [
-        "%%capture\n",
-        "! git clone https://github.com/nateraw/stable-diffusion-videos\n",
-        "%cd /content/stable-diffusion-videos/\n",
-        "! pip install -r requirements.txt\n",
+        "# ! pip install stable_diffusion_videos\n",
+        "! pip install git+https://github.com/nateraw/stable-diffusion-videos@package-try-2\n",
         "! git config --global credential.helper store"
       ]
     },
@@ -82,7 +80,7 @@
         "You have to be a registered user in 🤗 Hugging Face Hub, and you'll also need to use an access token for the code to work. For more information on access tokens, please refer to [this section of the documentation](https://huggingface.co/docs/hub/security-tokens)."
       ],
       "metadata": {
-        "id": "BoTBdktZDs8B"
+        "id": "dR5iVGYbOky5"
       }
     },
     {
@@ -93,7 +91,7 @@
         "notebook_login()"
       ],
       "metadata": {
-        "id": "8jVV1OLBDZ8o"
+        "id": "GmejIGhFMTXG"
       },
       "execution_count": null,
       "outputs": []
@@ -104,7 +102,17 @@
         "## Run the App 🚀"
       ],
       "metadata": {
-        "id": "TbW39aWzIdsn"
+        "id": "H7UOKJhVOonb"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Optional - Connect Google Drive\n",
+        "\n"
+      ],
+      "metadata": {
+        "id": "GjfrKeeR2NQZ"
       }
     },
     {
@@ -115,19 +123,43 @@
         "This step will take a couple minutes the first time you run it."
       ],
       "metadata": {
-        "id": "jCWuRT78Jt0L"
+        "id": "g71hslP8OntM"
       }
     },
     {
       "cell_type": "code",
       "source": [
-        "# in case you restarted runtime, we need to be in this directory\n",
-        "%cd /content/stable-diffusion-videos/\n",
+        "from stable_diffusion_videos import interface"
+      ],
+      "metadata": {
+        "id": "bgSNS368L-DV"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "#@title Connect to Google Drive to Save Outputs\n",
+        "\n",
+        "#@markdown If you want to connect Google Drive, click the checkbox below and run this cell. You'll be prompted to authenticate.\n",
+        "\n",
+        "#@markdown If you just want to save your outputs in this Colab session, don't worry about this cell\n",
         "\n",
-        "from app import interface"
+        "connect_google_drive = True #@param {type:\"boolean\"}\n",
+        "\n",
+        "#@markdown Then, in the interface, use this path as the `output` in the Video tab to save your videos to Google Drive:\n",
+        "\n",
+        "#@markdown > /content/gdrive/MyDrive/stable_diffusion_videos\n",
+        "\n",
+        "\n",
+        "if connect_google_drive:\n",
+        "    from google.colab import drive\n",
+        "\n",
+        "    drive.mount('/content/gdrive')"
       ],
       "metadata": {
-        "id": "a6Eey_-YDvFc"
+        "id": "kidtsR3c2P9Z"
       },
       "execution_count": null,
       "outputs": []
@@ -147,10 +179,12 @@
         "2. Generate videos using the \"Videos\" tab\n",
         "    - Using the images you found from the step above, provide the prompts/seeds you recorded\n",
         "    - Set the `num_walk_steps` - for testing you can use a small number like 3 or 5, but to get great results you'll want to use something larger (60-200 steps). \n",
-        "    - You can (and should) use the `name` input to separate out where the images/videos are saved. "
+        "    - You can (and should) use the `name` input to separate out where the images/videos are saved. \n",
+        "\n",
+        "💡 **Pro tip** - Click the link that looks like `https://<id-number>.gradio.app` below , and you'll be able to view it in full screen."
       ],
       "metadata": {
-        "id": "Po9vuzMnJzka"
+        "id": "VxjRVNnMOtgU"
       }
     },
     {
@@ -159,7 +193,80 @@
         "interface.launch()"
       ],
       "metadata": {
-        "id": "fflAEZaLIYGP"
+        "id": "8es3_onUOL3J"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "---"
+      ],
+      "metadata": {
+        "id": "mFCoTvlnPi4u"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Use `walk` programatically\n",
+        "\n",
+        "The other option is to not use the interface, and instead use `walk` programatically. Here's how you would do that..."
+      ],
+      "metadata": {
+        "id": "SjTQLCiLOWeo"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "First we define a helper fn for visualizing videos in colab"
+      ],
+      "metadata": {
+        "id": "fGQPClGwOR9R"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from IPython.display import HTML\n",
+        "from base64 import b64encode\n",
+        "\n",
+        "def visualize_video_colab(video_path):\n",
+        "    mp4 = open(video_path,'rb').read()\n",
+        "    data_url = \"data:video/mp4;base64,\" + b64encode(mp4).decode()\n",
+        "    return HTML(\"\"\"\n",
+        "    <video width=400 controls>\n",
+        "        <source src=\"%s\" type=\"video/mp4\">\n",
+        "    </video>\n",
+        "    \"\"\" % data_url)"
+      ],
+      "metadata": {
+        "id": "GqTWc8ZhNeLU"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Walk! 🚶‍♀️"
+      ],
+      "metadata": {
+        "id": "Vd_RzwkoPM7X"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from stable_diffusion_videos import walk\n",
+        "\n",
+        "video_path = walk(['a cat', 'a dog'], [42, 1337], num_steps=3, make_video=True)\n",
+        "visualize_video_colab(video_path)"
+      ],
+      "metadata": {
+        "id": "Hv2wBZXXMQ-I"
       },
       "execution_count": null,
       "outputs": []