Add files

.dockerignore

@@ -0,0 +1 @@
+models

.gitignore

@@ -0,0 +1,162 @@
+models
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

.pre-commit-config.yaml

@@ -0,0 +1,50 @@
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.4.0
+  hooks:
+  - id: check-executables-have-shebangs
+  - id: check-json
+  - id: check-merge-conflict
+  - id: check-shebang-scripts-are-executable
+  - id: check-toml
+  - id: check-yaml
+  - id: end-of-file-fixer
+  - id: mixed-line-ending
+    args: ["--fix=lf"]
+  - id: requirements-txt-fixer
+  - id: trailing-whitespace
+- repo: https://github.com/myint/docformatter
+  rev: v1.7.5
+  hooks:
+  - id: docformatter
+    args: ["--in-place"]
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+    - id: isort
+      args: ["--profile", "black"]
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v1.5.1
+  hooks:
+    - id: mypy
+      args: ["--ignore-missing-imports"]
+      additional_dependencies: ["types-python-slugify", "types-requests", "types-PyYAML"]
+- repo: https://github.com/psf/black
+  rev: 23.7.0
+  hooks:
+    - id: black
+      language_version: python3.10
+      args: ["--line-length", "119"]
+- repo: https://github.com/kynan/nbstripout
+  rev: 0.6.1
+  hooks:
+    - id: nbstripout
+      args: ["--extra-keys", "metadata.interpreter metadata.kernelspec cell.metadata.pycharm"]
+- repo: https://github.com/nbQA-dev/nbQA
+  rev: 1.7.0
+  hooks:
+    - id: nbqa-black
+    - id: nbqa-pyupgrade
+      args: ["--py37-plus"]
+    - id: nbqa-isort
+      args: ["--float-to-top"]

.vscode/settings.json

@@ -0,0 +1,21 @@
+{
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.organizeImports": true
+        }
+    },
+    "black-formatter.args": [
+        "--line-length=119"
+    ],
+    "isort.args": ["--profile", "black"],
+    "flake8.args": [
+        "--max-line-length=119"
+    ],
+    "ruff.args": [
+        "--line-length=119"
+    ],
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": true
+}

Dockerfile

@@ -0,0 +1,54 @@
+FROM nvidia/cuda:11.7.1-cudnn8-devel-ubuntu22.04
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update && \
+    apt-get upgrade -y && \
+    apt-get install -y --no-install-recommends \
+    git \
+    git-lfs \
+    wget \
+    curl \
+    # python build dependencies \
+    build-essential \
+    libssl-dev \
+    zlib1g-dev \
+    libbz2-dev \
+    libreadline-dev \
+    libsqlite3-dev \
+    libncursesw5-dev \
+    xz-utils \
+    tk-dev \
+    libxml2-dev \
+    libxmlsec1-dev \
+    libffi-dev \
+    liblzma-dev \
+    # gradio dependencies \
+    ffmpeg && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:${PATH}
+WORKDIR ${HOME}/app
+
+RUN curl https://pyenv.run | bash
+ENV PATH=${HOME}/.pyenv/shims:${HOME}/.pyenv/bin:${PATH}
+ARG PYTHON_VERSION=3.10.12
+RUN pyenv install ${PYTHON_VERSION} && \
+    pyenv global ${PYTHON_VERSION} && \
+    pyenv rehash && \
+    pip install --no-cache-dir -U pip setuptools wheel
+
+COPY --chown=1000 ./requirements.txt /tmp/requirements.txt
+RUN pip install -r /tmp/requirements.txt
+
+COPY --chown=1000 . ${HOME}/app
+ENV PYTHONPATH=${HOME}/app \
+    PYTHONUNBUFFERED=1 \
+    GRADIO_ALLOW_FLAGGING=never \
+    GRADIO_NUM_PORTS=1 \
+    GRADIO_SERVER_NAME=0.0.0.0 \
+    GRADIO_THEME=huggingface \
+    SYSTEM=spaces
+CMD ["python", "app.py"]

README.md

@@ -1,11 +1,9 @@
 ---
-title: I2VGen XL
-emoji: 📉
+title: I2VGen-XL
+emoji: 🔥
 colorFrom: green
 colorTo: pink
-sdk: gradio
-sdk_version: 3.41.0
-app_file: app.py
+sdk: docker
 pinned: false
 ---
 

app.py

@@ -0,0 +1,85 @@
+#!/usr/bin/env python
+
+import os
+import pathlib
+import tempfile
+
+import gradio as gr
+import torch
+from huggingface_hub import snapshot_download
+from modelscope.outputs import OutputKeys
+from modelscope.pipelines import pipeline
+
+DESCRIPTION = """# I2VGen-XL
+
+I2VGen-XL can generate videos that are semantically similar to the input image and text. The generated videos are high-definition (1280 * 720), wide-screen (16:9), temporally coherent, and have good texture.
+"""
+
+if torch.cuda.is_available():
+    model_cache_dir = os.getenv("MODEL_CACHE_DIR", "./models")
+
+    image2video_model_dir = pathlib.Path(model_cache_dir) / "MS-Image2Video"
+    snapshot_download(repo_id="damo-vilab/MS-Image2Video", repo_type="model", local_dir=image2video_model_dir)
+    image_to_video_pipe = pipeline(
+        task="image-to-video", model=image2video_model_dir.as_posix(), model_revision="v1.1.0", device="cuda:0"
+    )
+
+    video2video_model_dir = pathlib.Path(model_cache_dir) / "MS-Vid2Vid-XL"
+    snapshot_download(repo_id="damo-vilab/MS-Vid2Vid-XL", repo_type="model", local_dir=video2video_model_dir)
+    video_to_video_pipe = pipeline(
+        task="video-to-video", model=video2video_model_dir.as_posix(), model_revision="v1.1.0", device="cuda:0"
+    )
+else:
+    image_to_video_pipe = None
+    video_to_video_pipe = None
+
+
+def image_to_video(image_path: str) -> str:
+    output_file = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
+    image_to_video_pipe(image_path, output_video=output_file.name)[OutputKeys.OUTPUT_VIDEO]
+    return output_file.name
+
+
+def video_to_video(video_path: str, text: str) -> str:
+    p_input = {"video_path": video_path, "text": text}
+    output_file = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
+    video_to_video_pipe(p_input, output_video=output_file.name)[OutputKeys.OUTPUT_VIDEO]
+    return output_file.name
+
+
+with gr.Blocks(css="style.css") as demo:
+    gr.Markdown(DESCRIPTION)
+    with gr.Box():
+        gr.Markdown('Step 1: Upload an image and click the "Generate video" button.')
+        with gr.Row():
+            with gr.Column():
+                input_image = gr.Image(label="Input image", type="filepath", height=300)
+                i2v_button = gr.Button("Generate video")
+            with gr.Column():
+                output_video_1 = gr.Video(label="Output video 1", interactive=False, height=300)
+    with gr.Box():
+        gr.Markdown(
+            'Step 2: Add an English text description of the video content and click the "Generate high-resolution video" button.'
+        )
+        with gr.Row():
+            with gr.Column():
+                text_description = gr.Textbox(label="Text description")
+                v2v_button = gr.Button("Generate high-resolution video")
+            with gr.Column():
+                output_video_2 = gr.Video(label="Output video 2", height=300)
+
+    i2v_button.click(
+        fn=image_to_video,
+        inputs=input_image,
+        outputs=output_video_1,
+        api_name="image-to-video",
+    )
+    v2v_button.click(
+        fn=video_to_video,
+        inputs=[output_video_1, text_description],
+        outputs=output_video_2,
+        api_name="video-to-video",
+    )
+
+if __name__ == "__main__":
+    demo.queue(max_size=10, api_open=False).launch()

requirements.txt

@@ -0,0 +1,15 @@
+easydict==1.10
+einops==0.6.1
+fairscale==0.4.13
+gradio==3.41.0
+huggingface_hub==0.16.4
+imageio==2.31.1
+modelscope==1.8.4
+open_clip_torch==2.20.0
+opencv-python-headless==4.8.0.76
+pytorch-lightning==2.0.7
+rotary-embedding-torch==0.2.7
+scipy==1.11.2
+torch==2.0.1
+torchsde==0.2.5
+xformers==0.0.20

style.css

@@ -0,0 +1,10 @@
+h1 {
+  text-align: center;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: #fff;
+  background: #1565c0;
+  border-radius: 100vh;
+}