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.
Locations: Learn which regions support image editing models.
Safety filtering: Understand how safety filters are applied to your input and output images.
Model versions: Review the available image models and their specific limits.
Types of available editing tools
You can edit Imagen-generated or existing images using one of two methods: mask-based editing or mask-free editing.
Mask-based editing: With this method, you specify a targeted area (a mask) to edit, while the rest of the image remains unchanged. This method is ideal for location-specific edits, such as the following:
Mask-free editing: This method lets you edit an entire image using only a text prompt, without defining a specific area. It is best for global edits that affect the entire image or when the precise location of the change is not important. For more information, see Edit images using text prompts.
When you send an image editing request, Imagen checks both your input data and the generated output for offensive material. As a result, the service might block offensive input from a text prompt or a base image. The service might also block offensive output images, which affects the number of generated images you receive in a response.
[[["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"]],["Last updated 2025-08-27 UTC."],[],[],null,["# Edit images overview\n\nImagen on Vertex AI lets you edit Imagen-generated or existing\nimages. You can specify part of the image to modify in addition to a text\ndescription of the updates (mask-base editing), or you can use a text prompt to\nupdate the entire image (mask-free editing).\n\nTypes of available editing tools\n--------------------------------\n\nThe following are types of editing that Imagen supports:\n\n- **Mask-based editing** - Lets you specify a targeted area to apply edits to.\n This method of editing is good for edits that apply to only parts of an\n image. Mask-based editing is useful for the following types of image edits:\n\n - [Insert objects into an image](/vertex-ai/generative-ai/docs/image/edit-insert-objects)\n - [Remove objects from an image](/vertex-ai/generative-ai/docs/image/edit-remove-objects)\n - [Expand the content of an image](/vertex-ai/generative-ai/docs/image/edit-outpainting)\n - [Replace the background of an image](/vertex-ai/generative-ai/docs/image/edit-product-image)\n- **Mask-free editing** - Lets you edit an image without a mask (specific\n area). This method of editing is good for edits that belong to the entire\n image, or when the location of the edits is not as important for your use\n case. For location-specific editing, use mask-based editing.\n\n For more information, see [Edit images using text prompts](/vertex-ai/generative-ai/docs/image/edit-images).\n\nLocations\n---------\n\nA location is a [region](/about/locations) you can specify in a request to\ncontrol where data is stored at rest. For a list of available regions, see [Generative AI on Vertex AI locations](/vertex-ai/generative-ai/docs/learn/locations-genai).\n\nSafety filtering\n----------------\n\nBoth input data and output content are checked for offensive material when you\nsend an image editing request to Imagen. This means offensive\ninput data from a text prompt or from a base image you provide can be blocked.\nSimilarly, offensive output images might also be blocked, affecting the number\nof generated images you get in a response.\n\nFor more information about safety filtering and blocked content handling, see\n[Responsible AI and usage guidelines for\nImagen](/vertex-ai/generative-ai/docs/image/responsible-ai-imagen#safety-filters).\n\nModel versions\n--------------\n\nThere are multiple image generation models that you can use. Each model may have\nlimits that are specific to that model. For more\ninformation, see [Imagen\nmodels](/vertex-ai/generative-ai/docs/models#imagen-models).\n\nWhat's next\n-----------\n\n- [Insert objects into an image](/vertex-ai/generative-ai/docs/image/edit-insert-objects)\n- [Remove objects from an image](/vertex-ai/generative-ai/docs/image/edit-remove-objects)\n- [Expand the content of an image](/vertex-ai/generative-ai/docs/image/edit-outpainting)\n- [Edit product images](/vertex-ai/generative-ai/docs/image/edit-product-image)\n\n- [Edit images using text prompts](/vertex-ai/generative-ai/docs/image/edit-images)."]]