Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see
Model versions and lifecycle.
Edit image content using a mask with Imagen v.002
Stay organized with collections
Save and categorize content based on your preferences.
This sample demonstrates how to use the Imagen model for mask-based image editing. Specify a targeted mask area and specify the edits using a text prompt.
Code sample
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],[],[],[],null,["# Edit image content using a mask with Imagen v.002\n\nThis sample demonstrates how to use the Imagen model for mask-based image editing. Specify a targeted mask area and specify the edits using a text prompt.\n\nCode sample\n-----------\n\n### Python\n\n\nBefore trying this sample, follow the Python setup instructions in the\n[Vertex AI quickstart using\nclient libraries](/vertex-ai/docs/start/client-libraries).\n\n\nFor more information, see the\n[Vertex AI Python API\nreference documentation](/python/docs/reference/aiplatform/latest).\n\n\nTo authenticate to Vertex AI, set up Application Default Credentials.\nFor more information, see\n\n[Set up authentication for a local development environment](/docs/authentication/set-up-adc-local-dev-environment).\n\n\n import https://cloud.google.com/python/docs/reference/vertexai/latest/\n from vertexai.preview.vision_models import https://cloud.google.com/python/docs/reference/vertexai/latest/vertexai.preview.generative_models.Image.html, https://cloud.google.com/python/docs/reference/vertexai/latest/vertexai.preview.vision_models.ImageGenerationModel.html\n\n # TODO(developer): Update and un-comment below lines\n # PROJECT_ID = \"your-project-id\"\n # input_file = \"input-image.png\"\n # mask_file = \"mask-image.png\"\n # output_file = \"output-image.png\"\n # prompt = \"\" # The text prompt describing what you want to see.\n\n https://cloud.google.com/python/docs/reference/vertexai/latest/.init(project=PROJECT_ID, location=\"us-central1\")\n\n model = https://cloud.google.com/python/docs/reference/vertexai/latest/vertexai.preview.vision_models.ImageGenerationModel.html.https://cloud.google.com/python/docs/reference/vertexai/latest/vertexai.preview.vision_models.ImageGenerationModel.html#vertexai_preview_vision_models_ImageGenerationModel_from_pretrained(\"imagegeneration@002\")\n base_img = https://cloud.google.com/python/docs/reference/vertexai/latest/vertexai.preview.generative_models.Image.html.https://cloud.google.com/python/docs/reference/vertexai/latest/vertexai.preview.generative_models.Image.html#vertexai_preview_generative_models_Image_load_from_file(location=input_file)\n mask_img = https://cloud.google.com/python/docs/reference/vertexai/latest/vertexai.preview.generative_models.Image.html.https://cloud.google.com/python/docs/reference/vertexai/latest/vertexai.preview.generative_models.Image.html#vertexai_preview_generative_models_Image_load_from_file(location=mask_file)\n\n images = model.https://cloud.google.com/python/docs/reference/vertexai/latest/vertexai.preview.vision_models.ImageGenerationModel.html#vertexai_preview_vision_models_ImageGenerationModel_edit_image(\n base_image=base_img,\n mask=mask_img,\n prompt=prompt,\n # Optional parameters\n seed=1,\n # Controls the strength of the prompt.\n # -- 0-9 (low strength), 10-20 (medium strength), 21+ (high strength)\n guidance_scale=21,\n number_of_images=1,\n )\n\n images[0].save(location=output_file, include_generation_parameters=False)\n\n # Optional. View the edited image in a notebook.\n # images[0].show()\n\n print(f\"Created output image using {len(images[0]._image_bytes)} bytes\")\n # Example response:\n # Created output image using 971614 bytes\n\nWhat's next\n-----------\n\n\nTo search and filter code samples for other Google Cloud products, see the\n[Google Cloud sample browser](/docs/samples?product=generativeaionvertexai)."]]