위치는 데이터가 영구 저장되는 위치를 제어하기 위해 요청에서 지정할 수 있는 리전입니다. 사용 가능한 리전 목록은 Vertex AI의 생성형 AI 위치를 참조하세요.
안전 필터링
Imagen에 이미지 수정 요청을 전송하면 입력 데이터와 출력 콘텐츠 모두 불쾌감을 주는 자료가 있는지 확인됩니다. 즉, 사용자가 제공하는 텍스트 프롬프트 또는 기본 이미지에서 불쾌감을 주는 입력 데이터를 차단할 수 있습니다. 마찬가지로 불쾌감을 주는 출력 이미지도 차단될 수 있으며, 이는 응답에서 얻는 생성된 이미지 수에 영향을 미칩니다.
[[["이해하기 쉬움","easyToUnderstand","thumb-up"],["문제가 해결됨","solvedMyProblem","thumb-up"],["기타","otherUp","thumb-up"]],[["이해하기 어려움","hardToUnderstand","thumb-down"],["잘못된 정보 또는 샘플 코드","incorrectInformationOrSampleCode","thumb-down"],["필요한 정보/샘플이 없음","missingTheInformationSamplesINeed","thumb-down"],["번역 문제","translationIssue","thumb-down"],["기타","otherDown","thumb-down"]],["최종 업데이트: 2025-09-04(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)."]]
