Add image2video microservice (Stable Video Diffusion)

comps/__init__.py

@@ -20,6 +20,9 @@
     GraphDoc,
     LVMDoc,
     LVMVideoDoc,
+    ImagePath,
+    ImagesPath,
+    VideoPath,
     ImageDoc,
     TextImageDoc,
     MultimodalDoc,

comps/cores/mega/constants.py

@@ -29,6 +29,8 @@ class ServiceType(Enum):
     LVM = 12
     KNOWLEDGE_GRAPH = 13
     WEB_RETRIEVER = 14
+    IMAGE2VIDEO = 15
+    TEXT2IMAGE = 16
 
 
 class MegaServiceEndpoint(Enum):

comps/cores/proto/docarray.py

@@ -217,3 +217,15 @@ class LVMVideoDoc(BaseDoc):
     chunk_duration: float
     prompt: str
     max_new_tokens: conint(ge=0, le=1024) = 512
+
+
+class ImagePath(BaseDoc):
+    image_path: str
+
+
+class ImagesPath(BaseDoc):
+    images_path: DocList[ImagePath]
+
+
+class VideoPath(BaseDoc):
+    video_path: str

comps/image2video/Dockerfile

@@ -0,0 +1,18 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+FROM python:3.11-slim
+
+# Set environment variables
+ENV LANG=en_US.UTF-8
+
+COPY comps /home/comps
+
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r /home/comps/image2video/requirements.txt
+
+ENV PYTHONPATH=$PYTHONPATH:/home
+
+WORKDIR /home/comps/image2video
+
+ENTRYPOINT ["python", "image2video.py"]

comps/image2video/README.md

@@ -0,0 +1,66 @@
+# Image-to-Video Microservice
+
+Image-to-Video is a task that generate video conditioning on the provided image(s). This microservice supports image-to-video task by using Stable Video Diffusion (SVD) model.
+
+# 🚀1. Start Microservice with Python (Option 1)
+
+## 1.1 Install Requirements
+
+```bash
+pip install -r requirements.txt
+pip install -r svd/requirements.txt
+```
+
+## 1.2 Start SVD Service
+
+```bash
+# Start SVD service
+cd svd/
+python svd_server.py
+```
+
+## 1.3 Start Image-to-Video Microservice
+
+```bash
+cd ..
+# Start the OPEA Microservice
+python image2video.py
+```
+
+# 🚀2. Start Microservice with Docker (Option 2)
+
+## 2.1 Build Images
+
+### 2.1.1 SVD Server Image
+
+```bash
+cd ../..
+docker build -t opea/svd:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/image2video/svd/Dockerfile .
+```
+
+### 2.1.2 Image-to-Video Service Image
+
+```bash
+docker build -t opea/image2video:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/image2video/Dockerfile .
+```
+
+## 2.2 Start SVD and Image-to-Video Service
+
+### 2.2.1 Start SVD server
+
+```bash
+docker run --ipc=host -p 9368:9368 -e http_proxy=$http_proxy -e https_proxy=$https_proxy opea/svd:latest
+```
+
+### 2.2.2 Start Image-to-Video service
+
+```bash
+ip_address=$(hostname -I | awk '{print $1}')
+docker run -p 9369:9369 --ipc=host -e http_proxy=$http_proxy -e https_proxy=$https_proxy -e SVD_ENDPOINT=http://$ip_address:9368 opea/image2video:latest
+```
+
+### 2.2.3 Test
+
+```bash
+http_proxy="" curl http://localhost:9369/v1/image2video -XPOST -d '{"images_path":[{"image_path":"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png"}]}' -H 'Content-Type: application/json'
+```

comps/image2video/__init__.py

@@ -0,0 +1,2 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0

comps/image2video/image2video.py

@@ -0,0 +1,47 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+
+import json
+import os
+import time
+
+import requests
+
+from comps import (
+    ImagesPath,
+    ServiceType,
+    VideoPath,
+    opea_microservices,
+    register_microservice,
+    register_statistics,
+    statistics_dict,
+)
+
+
+@register_microservice(
+    name="opea_service@image2video",
+    service_type=ServiceType.IMAGE2VIDEO,
+    endpoint="/v1/image2video",
+    host="0.0.0.0",
+    port=9369,
+    input_datatype=ImagesPath,
+    output_datatype=VideoPath,
+)
+@register_statistics(names=["opea_service@image2video"])
+async def image2video(input: ImagesPath):
+    start = time.time()
+    images_path = [img.image_path for img in input.images_path]
+    inputs = {"images_path": images_path}
+    video_path = requests.post(url=f"{svd_endpoint}/generate", data=json.dumps(inputs), proxies={"http": None}).json()[
+        "video_path"
+    ]
+
+    statistics_dict["opea_service@image2video"].append_latency(time.time() - start, None)
+    return VideoPath(video_path=video_path)
+
+
+if __name__ == "__main__":
+    svd_endpoint = os.getenv("SVD_ENDPOINT", "http://localhost:9368")
+    print("Image2video server started.")
+    opea_microservices["opea_service@image2video"].start()

comps/image2video/requirements.txt

@@ -0,0 +1,11 @@
+datasets
+docarray[full]
+fastapi
+opentelemetry-api
+opentelemetry-exporter-otlp
+opentelemetry-sdk
+prometheus-fastapi-instrumentator
+pydantic==2.7.2
+pydub
+shortuuid
+uvicorn

comps/image2video/svd/Dockerfile

@@ -0,0 +1,22 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+FROM python:3.11-slim
+
+# Set environment variables
+ENV LANG=en_US.UTF-8
+
+ARG ARCH="cpu"
+
+COPY comps /home/comps
+
+RUN apt-get update && apt-get install python3-opencv -y && \
+    pip install --no-cache-dir --upgrade pip && \
+    if [ ${ARCH} = "cpu" ]; then pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu; fi && \
+    pip install --no-cache-dir -r /home/comps/image2video/svd/requirements.txt
+
+ENV PYTHONPATH=$PYTHONPATH:/home
+
+WORKDIR /home/comps/image2video/svd
+
+ENTRYPOINT ["python", "svd_server.py"]

comps/image2video/svd/requirements.txt

@@ -0,0 +1,7 @@
+accelerate
+diffusers
+fastapi
+opencv-python
+torch
+transformers
+uvicorn

comps/image2video/svd/svd_server.py

@@ -0,0 +1,55 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+"""Stand-alone Stable Video Diffusion FastAPI Server."""
+
+import argparse
+import os
+import time
+
+import torch
+import uvicorn
+from diffusers import StableVideoDiffusionPipeline
+from diffusers.utils import export_to_video, load_image
+from fastapi import FastAPI, Request
+from fastapi.responses import JSONResponse, Response
+
+app = FastAPI()
+
+
+@app.post("/generate")
+async def generate(request: Request) -> Response:
+    print("SVD generation begin.")
+    request_dict = await request.json()
+    images_path = request_dict.pop("images_path")
+
+    start = time.time()
+    images = [load_image(img) for img in images_path]
+    images = [image.resize((1024, 576)) for image in images]
+
+    generator = torch.manual_seed(args.seed)
+    frames = pipe(images, decode_chunk_size=8, generator=generator).frames[0]
+    video_path = os.path.join(os.getcwd(), args.video_path)
+    export_to_video(frames, video_path, fps=7)
+    end = time.time()
+    print(f"SVD video output in {video_path}, time = {end-start}s")
+    return JSONResponse({"video_path": video_path})
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--host", type=str, default="0.0.0.0")
+    parser.add_argument("--port", type=int, default=9368)
+    parser.add_argument("--model_name_or_path", type=str, default="stabilityai/stable-video-diffusion-img2vid-xt")
+    parser.add_argument("--video_path", type=str, default="generated.mp4")
+    parser.add_argument("--seed", type=int, default=42)
+
+    args = parser.parse_args()
+    pipe = StableVideoDiffusionPipeline.from_pretrained(args.model_name_or_path)
+    print("Stable Video Diffusion model initialized.")
+
+    uvicorn.run(
+        app,
+        host=args.host,
+        port=args.port,
+        log_level="debug",
+    )

tests/test_image2video.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+set -x
+
+WORKPATH=$(dirname "$PWD")
+ip_address=$(hostname -I | awk '{print $1}')
+
+function build_docker_images() {
+    cd $WORKPATH
+    echo $(pwd)
+    docker build --no-cache -t opea/svd:latest -f comps/image2video/svd/Dockerfile .
+    if [ $? -ne 0 ]; then
+        echo "opea/svd built fail"
+        exit 1
+    else
+        echo "opea/svd built successful"
+    fi
+    docker build --no-cache -t opea/image2video:latest -f comps/image2video/Dockerfile .
+    if [ $? -ne 0 ]; then
+        echo "opea/image2video built fail"
+        exit 1
+    else
+        echo "opea/image2video built successful"
+    fi
+}
+
+function start_service() {
+    unset http_proxy
+    docker run -d --name="test-comps-image2video-svd" -e http_proxy=$http_proxy -e https_proxy=$https_proxy -p 9368:9368 --ipc=host opea/svd:latest
+    docker run -d --name="test-comps-image2video" -e SVD_ENDPOINT=http://$ip_address:9368 -e http_proxy=$http_proxy -e https_proxy=$https_proxy -p 9369:9369 --ipc=host opea/image2video:latest
+    sleep 3m
+}
+
+function validate_microservice() {
+    result=$(http_proxy="" curl http://localhost:9369/v1/image2video -XPOST -d '{"images_path":[{"image_path":"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/svd/rocket.png"}]}' -H 'Content-Type: application/json')
+    if [[ $result == *"generated.mp4"* ]]; then
+        echo "Result correct."
+    else
+        echo "Result wrong."
+        docker logs test-comps-tts-speecht5
+        docker logs test-comps-tts
+        exit 1
+    fi
+
+}
+
+function stop_docker() {
+    cid=$(docker ps -aq --filter "name=test-comps-image2video*")
+    if [[ ! -z "$cid" ]]; then docker stop $cid && docker rm $cid && sleep 1s; fi
+}
+
+function main() {
+
+    stop_docker
+
+    build_docker_images
+    start_service
+
+    validate_microservice
+
+    stop_docker
+    echo y | docker system prune
+
+}
+
+main