Merge pull request Tencent#23 from zsxkib/main

Thanks for your contribution! We believe Replicate API will help lower the barrier for users and contribute to the development of the MimicMotion  community.

This is our initial released version of the model and a newer version for generating greatly higher quality videos will be released very soon. We also hope to synchronize the updates on the Replicate API at that time.

We would be truly honored if MimicMotion can be introduced on Replicate websites.

.dockerignore

@@ -0,0 +1,28 @@
+# The .dockerignore file excludes files from the container build process.
+#
+# https://docs.docker.com/engine/reference/builder/#dockerignore-file
+
+# Replicate
+/models/
+/outputs/
+*.gif
+*.mp4
+*.jpg
+*.jpeg
+*.png
+*.webp
+MimicMotion.pth
+
+# Exclude Git files
+.git
+.github
+.gitignore
+
+# Exclude Python cache files
+__pycache__
+.mypy_cache
+.pytest_cache
+.ruff_cache
+
+# Exclude Python virtual environment
+/venv

.gitignore

@@ -158,3 +158,6 @@ _.*
 # models and outputs
 models/
 outputs/
+
+# Replicate
+.cog

README.md

@@ -1,6 +1,6 @@
 # MimicMotion
 
-<a href='http://tencent.github.io/MimicMotion'><img src='https://img.shields.io/badge/Project-Page-Green'></a> <a href='https://arxiv.org/abs/2406.19680'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>
+<a href='http://tencent.github.io/MimicMotion'><img src='https://img.shields.io/badge/Project-Page-Green'></a> <a href='https://arxiv.org/abs/2406.19680'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a> [![Replicate](https://replicate.com/zsxkib/mimic-motion/badge)](https://replicate.com/zsxkib/mimic-motion)
 
 MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
 <br/>

cog.yaml

@@ -0,0 +1,37 @@
+# Configuration for Cog ⚙️
+# Reference: https://cog.run/yaml
+
+build:
+  # set to true if your model requires a GPU
+  gpu: true
+  # cuda: "11.7"
+
+  # a list of ubuntu apt packages to install
+  system_packages:
+    - "libgl1-mesa-glx"
+    - "libglib2.0-0"
+
+  # python version in the form '3.11' or '3.11.4'
+  python_version: "3.11"
+
+  # a list of packages in the format <package-name>==<version>
+  python_packages:
+    - "torch>=2.3" # 2.3.1
+    - "torchvision>=0.18" # 0.18.1
+    - "diffusers>=0.29" # 0.29.2
+    - "transformers>=4.42" # 4.42.3
+    - "decord>=0.6" # 0.6.0
+    - "einops>=0.8" # 0.8.0
+    - "omegaconf>=2.3" # 2.3.0
+    - "opencv-python>=4.10" # 4.10.0.84
+    - "matplotlib>=3.9" # 3.9.1
+    - "onnxruntime>=1.18" # 1.18.1
+    - "accelerate>=0.32" # 0.32.0
+    - "av>=12.2" # 12.2.0, https://github.com/continue-revolution/sd-webui-animatediff/issues/377
+
+  # commands run after the environment is setup
+  run:
+    - curl -o /usr/local/bin/pget -L "https://github.com/replicate/pget/releases/download/v0.8.2/pget_linux_x86_64" && chmod +x /usr/local/bin/pget
+
+# predict.py defines how predictions are run on your model
+predict: "predict.py:Predictor"