mirror of
https://github.com/GoogleCloudPlatform/vertex-ai-samples.git
synced 2026-09-28 16:11:56 +00:00
Compare commits
3
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Gary Wei
|
950a4aff2d | ||
|
Holt SkinnerandGitHub
|
7ea4669471 | ||
|
Mend RenovateandGitHub
|
d24204a2f8 |
@@ -3,7 +3,7 @@ ipython
|
||||
jupyter
|
||||
nbconvert
|
||||
black==24.4.2
|
||||
pyupgrade==3.16.0
|
||||
pyupgrade==3.17.0
|
||||
isort==5.13.2
|
||||
flake8==7.1.0
|
||||
nbqa==1.8.5
|
||||
|
||||
@@ -1,291 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"id": "Ug_ZXeBdbFI4"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Copyright 2024 Google LLC\n",
|
||||
"#\n",
|
||||
"# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
|
||||
"# you may not use this file except in compliance with the License.\n",
|
||||
"# You may obtain a copy of the License at\n",
|
||||
"#\n",
|
||||
"# https://www.apache.org/licenses/LICENSE-2.0\n",
|
||||
"#\n",
|
||||
"# Unless required by applicable law or agreed to in writing, software\n",
|
||||
"# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
|
||||
"# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
|
||||
"# See the License for the specific language governing permissions and\n",
|
||||
"# limitations under the License."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "Jr2jRuqabG1m"
|
||||
},
|
||||
"source": [
|
||||
"# Vertex AI Model Garden - Text To Video\n",
|
||||
"\n",
|
||||
"<table align=\"left\"><tbody><tr>\n",
|
||||
" <td>\n",
|
||||
" <a href=\"https://console.cloud.google.com/vertex-ai/colab/import/https:%2F%2Fraw.githubusercontent.com%2FGoogleCloudPlatform%2Fvertex-ai-samples%2Fmain%2Fnotebooks%2Fcommunity%2Fmodel_garden%2Fmodel_garden_pytorch_text_to_video.ipynb\">\n",
|
||||
" <img alt=\"Google Cloud Colab Enterprise logo\" src=\"https://lh3.googleusercontent.com/JmcxdQi-qOpctIvWKgPtrzZdJJK-J3sWE1RsfjZNwshCFgE_9fULcNpuXYTilIR2hjwN\" width=\"32px\"><br> Run in Colab Enterprise\n",
|
||||
" </a>\n",
|
||||
" </td>\n",
|
||||
" <td>\n",
|
||||
" <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/model_garden/model_garden_pytorch_text_to_video.ipynb\">\n",
|
||||
" <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\"><br>\n",
|
||||
" View on GitHub\n",
|
||||
" </a>\n",
|
||||
" </td>\n",
|
||||
"</tr></tbody></table>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "wLLfRT_6bTZO"
|
||||
},
|
||||
"source": [
|
||||
"## Overview\n",
|
||||
"\n",
|
||||
"This notebook demonstrates deploying the pre-trained [Text To Video](https://huggingface.co/docs/diffusers/main/en/api/pipelines/text_to_video) model on Vertex AI for online prediction.\n",
|
||||
"\n",
|
||||
"### Objective\n",
|
||||
"\n",
|
||||
"- Upload the model to [Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/introduction).\n",
|
||||
"- Deploy the model on [Endpoint](https://cloud.google.com/vertex-ai/docs/predictions/using-private-endpoints).\n",
|
||||
"- Run online predictions for text-to-video.\n",
|
||||
"\n",
|
||||
"### Costs\n",
|
||||
"\n",
|
||||
"This tutorial uses billable components of Google Cloud:\n",
|
||||
"\n",
|
||||
"* Vertex AI\n",
|
||||
"* Cloud Storage\n",
|
||||
"\n",
|
||||
"Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"id": "c8b29e68bb87"
|
||||
},
|
||||
"source": [
|
||||
"## Run the notebook"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "dbf16ae5574d"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title Setup Google Cloud project\n",
|
||||
"\n",
|
||||
"# @markdown 1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
|
||||
"\n",
|
||||
"# @markdown 2. [Optional] [Create a Cloud Storage bucket](https://cloud.google.com/storage/docs/creating-buckets) for storing experiment outputs. Set the BUCKET_URI for the experiment environment. The specified Cloud Storage bucket (`BUCKET_URI`) should be located in the same region as where the notebook was launched. Note that a multi-region bucket (eg. \"us\") is not considered a match for a single region covered by the multi-region range (eg. \"us-central1\"). If not set, a unique GCS bucket will be created instead.\n",
|
||||
"\n",
|
||||
"import os\n",
|
||||
"import sys\n",
|
||||
"import uuid\n",
|
||||
"from datetime import datetime\n",
|
||||
"\n",
|
||||
"from google.cloud import aiplatform\n",
|
||||
"from IPython.display import HTML\n",
|
||||
"\n",
|
||||
"# Get the default cloud project id.\n",
|
||||
"PROJECT_ID = os.environ[\"GOOGLE_CLOUD_PROJECT\"]\n",
|
||||
"\n",
|
||||
"# Get the default region for launching jobs.\n",
|
||||
"REGION = os.environ[\"GOOGLE_CLOUD_REGION\"]\n",
|
||||
"\n",
|
||||
"# Enable the Vertex AI API and Compute Engine API, if not already.\n",
|
||||
"! gcloud services enable aiplatform.googleapis.com compute.googleapis.com\n",
|
||||
"\n",
|
||||
"# Cloud Storage bucket for storing the experiment artifacts.\n",
|
||||
"# A unique GCS bucket will be created for the purpose of this notebook. If you\n",
|
||||
"# prefer using your own GCS bucket, please change the value yourself below.\n",
|
||||
"now = datetime.now().strftime(\"%Y%m%d%H%M%S\")\n",
|
||||
"BUCKET_URI = \"gs://\" # @param {type: \"string\"}\n",
|
||||
"BUCKET_NAME = \"/\".join(BUCKET_URI.split(\"/\")[:3])\n",
|
||||
"\n",
|
||||
"# Create a unique GCS bucket for this notebook, if not specified by the user.\n",
|
||||
"if BUCKET_URI is None or BUCKET_URI.strip() == \"\" or BUCKET_URI == \"gs://\":\n",
|
||||
" BUCKET_URI = f\"gs://{PROJECT_ID}-tmp-{now}-{str(uuid.uuid4())[:4]}\"\n",
|
||||
" BUCKET_NAME = \"/\".join(BUCKET_URI.split(\"/\")[:3])\n",
|
||||
" ! gsutil mb -l {REGION} {BUCKET_URI}\n",
|
||||
"else:\n",
|
||||
" assert BUCKET_URI.startswith(\"gs://\"), \"BUCKET_URI must start with `gs://`.\"\n",
|
||||
" shell_output = ! gsutil ls -Lb {BUCKET_NAME} | grep \"Location constraint:\" | sed \"s/Location constraint://\"\n",
|
||||
" bucket_region = shell_output[0].strip().lower()\n",
|
||||
" if bucket_region != REGION:\n",
|
||||
" raise ValueError(\n",
|
||||
" \"Bucket region %s is different from notebook region %s\"\n",
|
||||
" % (bucket_region, REGION)\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"print(f\"Using this GCS Bucket: {BUCKET_URI}\")\n",
|
||||
"\n",
|
||||
"# Set up the default SERVICE_ACCOUNT.\n",
|
||||
"SERVICE_ACCOUNT = None\n",
|
||||
"shell_output = ! gcloud projects describe $PROJECT_ID\n",
|
||||
"project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
|
||||
"SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
|
||||
"\n",
|
||||
"print(\"Using this default Service Account:\", SERVICE_ACCOUNT)\n",
|
||||
"\n",
|
||||
"# Provision permissions to the SERVICE_ACCOUNT with the GCS bucket\n",
|
||||
"! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.admin $BUCKET_NAME\n",
|
||||
"\n",
|
||||
"aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)\n",
|
||||
"\n",
|
||||
"if \"google.colab\" in sys.modules:\n",
|
||||
" from google.colab import auth\n",
|
||||
"\n",
|
||||
" auth.authenticate_user(project_id=PROJECT_ID)\n",
|
||||
"\n",
|
||||
"# The pre-built serving docker image. It contains serving scripts and models.\n",
|
||||
"SERVE_DOCKER_URI = \"us-docker.pkg.dev/vertex-ai/vertex-vision-model-garden-dockers/pytorch-diffusers-serve-opt:20240605_1400_RC00\"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"def deploy_model(model_id, task):\n",
|
||||
" model_name = \"text-to-video\"\n",
|
||||
" endpoint = aiplatform.Endpoint.create(display_name=f\"{model_name}-endpoint\")\n",
|
||||
" serving_env = {\n",
|
||||
" \"MODEL_ID\": model_id,\n",
|
||||
" \"TASK\": task,\n",
|
||||
" \"DEPLOY_SOURCE\": \"notebook\",\n",
|
||||
" }\n",
|
||||
" model = aiplatform.Model.upload(\n",
|
||||
" display_name=model_name,\n",
|
||||
" serving_container_image_uri=SERVE_DOCKER_URI,\n",
|
||||
" serving_container_ports=[7080],\n",
|
||||
" serving_container_predict_route=\"/predictions/diffusers_serving\",\n",
|
||||
" serving_container_health_route=\"/ping\",\n",
|
||||
" serving_container_environment_variables=serving_env,\n",
|
||||
" )\n",
|
||||
" model.deploy(\n",
|
||||
" endpoint=endpoint,\n",
|
||||
" machine_type=\"g2-standard-8\",\n",
|
||||
" accelerator_type=\"NVIDIA_L4\",\n",
|
||||
" accelerator_count=1,\n",
|
||||
" deploy_request_timeout=1800,\n",
|
||||
" )\n",
|
||||
" return model, endpoint"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "fc3a118f0927"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title Upload and deploy models\n",
|
||||
"\n",
|
||||
"# @markdown This section uploads the model to Model Registry and deploys it on the Endpoint. It takes ~15 minutes to finish.\n",
|
||||
"# @markdown Click \"Show Code\" to see more details.\n",
|
||||
"\n",
|
||||
"model, endpoint = deploy_model(\n",
|
||||
" model_id=\"damo-vilab/text-to-video-ms-1.7b\", task=\"text-to-video\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "a927dfe74a71"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title Predict\n",
|
||||
"\n",
|
||||
"# @markdown Once deployment succeeds, you can send requests to the endpoint with text prompts to generate videos.\n",
|
||||
"\n",
|
||||
"# @markdown When deployed on one L4 GPU (the default machine type), the averaged inference time of a request is ~15 seconds.\n",
|
||||
"\n",
|
||||
"# @markdown Example:\n",
|
||||
"\n",
|
||||
"# @markdown ```\n",
|
||||
"# @markdown Prompt: Spiderman is surfing\n",
|
||||
"# @markdown ```\n",
|
||||
"\n",
|
||||
"# @markdown You may adjust the parameters below to achieve best video quality.\n",
|
||||
"\n",
|
||||
"prompt = \"Spiderman is surfing\" # @param {type: \"string\"}\n",
|
||||
"number_inference_steps = 25 # @param {type:\"number\"}\n",
|
||||
"\n",
|
||||
"instances = [\n",
|
||||
" {\"prompt\": prompt, \"number_inference_steps\": number_inference_steps},\n",
|
||||
"]\n",
|
||||
"response = endpoint.predict(instances=instances)\n",
|
||||
"\n",
|
||||
"html = \"\"\n",
|
||||
"for video in response.predictions:\n",
|
||||
" html += \"<video controls>\"\n",
|
||||
" html += f'<source src=\"data:video/mp4;base64,{video}\" type=\"video/mp4\">'\n",
|
||||
" html += \"</video>\"\n",
|
||||
"HTML(html)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"cellView": "form",
|
||||
"id": "2ccf3714dbe9"
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# @title Clean up resources\n",
|
||||
"\n",
|
||||
"# @markdown Delete the experiment models and endpoints to recycle the resources\n",
|
||||
"# @markdown and avoid unnecessary continouous charges that may incur.\n",
|
||||
"\n",
|
||||
"try:\n",
|
||||
" # Undeploy model and delete endpoint.\n",
|
||||
" endpoint.delete(force=True)\n",
|
||||
"\n",
|
||||
" # Delete model.\n",
|
||||
" model.delete()\n",
|
||||
"\n",
|
||||
"except Exception as e:\n",
|
||||
" print(e)\n",
|
||||
"\n",
|
||||
"# Delete bucket.\n",
|
||||
"delete_bucket = False # @param {type:\"boolean\"}\n",
|
||||
"if delete_bucket:\n",
|
||||
" ! gsutil -m rm -r $BUCKET_NAME"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"colab": {
|
||||
"name": "model_garden_pytorch_text_to_video.ipynb",
|
||||
"toc_visible": true
|
||||
},
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"name": "python3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 0
|
||||
}
|
||||
Reference in New Issue
Block a user