Generate images with Gemini

Preview

This product or feature is a Generative AI Preview offering, subject to the "Pre-GA Offerings Terms" of the Google Cloud Service Specific Terms , as well as the Additional Terms for Generative AI Preview Products . For this Generative AI Preview offering, Customers may elect to use it for production or commercial purposes, or disclose Generated Output to third-parties, and may process personal data as outlined in the Cloud Data Processing Addendum , subject to the obligations and restrictions described in the agreement under which you access Google Cloud. Pre-GA products are available "as is" and might have limited support. For more information, see the launch stage descriptions .

Gemini 2.5 Flash Image Preview supports response generation in multiple modalities, including text and images.

Image generation

Gemini Flash Preview Image's public preview for image generation ( gemini-2.5-flash-image-preview ) supports the ability to generate images in addition to text. This expands Gemini's capabilities to include the following:

• Iteratively generate images through conversation with natural language, adjusting images while maintaining consistency and context.
• Generate images with high-quality long text rendering.
• Generate interleaved text-image output. For example, a blog post with text and images in a single turn. Previously, this required stringing together multiple models.
• Generate images using Gemini's world knowledge and reasoning capabilities.

With this public experimental release, Gemini 2.5 Flash Image Preview can generate images in 1024px, supports generating images of people, and contains updated safety filters that provide a more flexible and less restrictive user experience.

It supports the following modalities and capabilities:

• Text to image

  • Example prompt:"Generate an image of the Eiffel tower with fireworks in the background."

• Text to image (text rendering)

  • Example prompt:"generate a cinematic photo of a large building with this giant text projection mapped on the front of the building: "Gemini 2.5 can now generate long form text""

• Text to image(s) and text (interleaved)

  • Example prompt:"Generate an illustrated recipe for a paella. Create images alongside the text as you generate the recipe."
  • Example prompt:"Generate a story about a dog in a 3D cartoon animation style. For each scene, generate an image"

• Image(s) and text to image(s) and text (interleaved)

  • Example prompt:(With an image of a furnished room) "What other color sofas would work in my space? Can you update the image?"

• Locale-aware image generation

  • Example prompt:"Generate an image of a breakfast meal."

Limitations:

• For best performance, use the following languages: EN, es-MX, ja-JP, zh-CN, hi-IN.
• Image generation does not support audio or video inputs.
• Image generation may not always trigger:
  • The model may output text only. Try asking for image outputs explicitly. For example, "provide images as you go along."
  • The model may generate text as an image. Try asking for text outputs explicitly. For example, "generate narrative text along with illustrations."
  • The model may stop generating partway through. Try again or try a different prompt.

Generate images

The following sections cover how to generate images using either Vertex AI Studio or using the API.

For guidance and best practices for prompting, see Design multimodal prompts .

pip install --upgrade google-genai

 # Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values 
 # with appropriate values for your project. 
 export 
  
 GOOGLE_CLOUD_PROJECT 
 = 
 GOOGLE_CLOUD_PROJECT 
 export 
  
 GOOGLE_CLOUD_LOCATION 
 = 
 global 
 export 
  
 GOOGLE_GENAI_USE_VERTEXAI 
 = 
True

  from 
  
 google 
  
 import 
 genai 
 from 
  
 google.genai.types 
  
 import 
 GenerateContentConfig 
 , 
 Modality 
 from 
  
 PIL 
  
 import 
 Image 
 from 
  
 io 
  
 import 
 BytesIO 
 client 
 = 
 genai 
 . 
 Client 
 () 
 response 
 = 
 client 
 . 
 models 
 . 
 generate_content 
 ( 
 model 
 = 
 "gemini-2.5-flash-image-preview" 
 , 
 contents 
 = 
 ( 
 "Generate an image of the Eiffel tower with fireworks in the background." 
 ), 
 config 
 = 
 GenerateContentConfig 
 ( 
 response_modalities 
 = 
 [ 
 Modality 
 . 
 TEXT 
 , 
 Modality 
 . 
 IMAGE 
 ], 
 candidate_count 
 = 
 1 
 , 
 safety_settings 
 = 
 [ 
 { 
 "method" 
 : 
 "PROBABILITY" 
 }, 
 { 
 "category" 
 : 
 "HARM_CATEGORY_DANGEROUS_CONTENT" 
 }, 
 { 
 "threshold" 
 : 
 "BLOCK_MEDIUM_AND_ABOVE" 
 }, 
 ], 
 ), 
 ) 
 for 
 part 
 in 
 response 
 . 
 candidates 
 [ 
 0 
 ] 
 . 
 content 
 . 
 parts 
 : 
 if 
 part 
 . 
 text 
 : 
 print 
 ( 
 part 
 . 
 text 
 ) 
 elif 
 part 
 . 
 inline_data 
 : 
 image 
 = 
 Image 
 . 
 open 
 ( 
 BytesIO 
 (( 
 part 
 . 
 inline_data 
 . 
 data 
 ))) 
 image 
 . 
 save 
 ( 
 "output_folder/example-image-eiffel-tower.png" 
 ) 
 # Example response: 
 #   I will generate an image of the Eiffel Tower at night, with a vibrant display of 
 #   colorful fireworks exploding in the dark sky behind it. The tower will be 
 #   illuminated, standing tall as the focal point of the scene, with the bursts of 
 #   light from the fireworks creating a festive atmosphere. 
 

npm install @google/genai

 # Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values 
 # with appropriate values for your project. 
 export 
  
 GOOGLE_CLOUD_PROJECT 
 = 
 GOOGLE_CLOUD_PROJECT 
 export 
  
 GOOGLE_CLOUD_LOCATION 
 = 
 global 
 export 
  
 GOOGLE_GENAI_USE_VERTEXAI 
 = 
True

  const 
  
 fs 
  
 = 
  
 require 
 ( 
 'fs' 
 ); 
 const 
  
 { 
 GoogleGenAI 
 , 
  
 Modality 
 } 
  
 = 
  
 require 
 ( 
 '@google/genai' 
 ); 
 const 
  
 GOOGLE_CLOUD_PROJECT 
  
 = 
  
 process 
 . 
 env 
 . 
 GOOGLE_CLOUD_PROJECT 
 ; 
 const 
  
 GOOGLE_CLOUD_LOCATION 
  
 = 
  
 process 
 . 
 env 
 . 
 GOOGLE_CLOUD_LOCATION 
  
 || 
  
 'us-central1' 
 ; 
 async 
  
 function 
  
 generateContent 
 ( 
  
 projectId 
  
 = 
  
 GOOGLE_CLOUD_PROJECT 
 , 
  
 location 
  
 = 
  
 GOOGLE_CLOUD_LOCATION 
 ) 
  
 { 
  
 const 
  
 ai 
  
 = 
  
 new 
  
 GoogleGenAI 
 ({ 
  
 vertexai 
 : 
  
 true 
 , 
  
 project 
 : 
  
 projectId 
 , 
  
 location 
 : 
  
 location 
 , 
  
 }); 
  
 const 
  
 response 
  
 = 
  
 await 
  
 ai 
 . 
 models 
 . 
 generateContentStream 
 ({ 
  
 model 
 : 
  
 'gemini-2.0-flash-exp' 
 , 
  
 contents 
 : 
  
 'Generate an image of the Eiffel tower with fireworks in the background.' 
 , 
  
 config 
 : 
  
 { 
  
 responseModalities 
 : 
  
 [ 
 Modality 
 . 
 TEXT 
 , 
  
 Modality 
 . 
 IMAGE 
 ], 
  
 }, 
  
 }); 
  
 const 
  
 generatedFileNames 
  
 = 
  
 []; 
  
 let 
  
 imageIndex 
  
 = 
  
 0 
 ; 
  
 for 
  
 await 
  
 ( 
 const 
  
 chunk 
  
 of 
  
 response 
 ) 
  
 { 
  
 const 
  
 text 
  
 = 
  
 chunk 
 . 
 text 
 ; 
  
 const 
  
 data 
  
 = 
  
 chunk 
 . 
 data 
 ; 
  
 if 
  
 ( 
 text 
 ) 
  
 { 
  
 console 
 . 
 debug 
 ( 
 text 
 ); 
  
 } 
  
 else 
  
 if 
  
 ( 
 data 
 ) 
  
 { 
  
 const 
  
 fileName 
  
 = 
  
 ` 
 generate_content_streaming_image_ 
 $ 
 { 
 imageIndex 
 ++ 
 } 
 . 
 png 
 ` 
 ; 
  
 console 
 . 
 debug 
 ( 
 ` 
 Writing 
  
 response 
  
 image 
  
 to 
  
 file 
 : 
  
 $ 
 { 
 fileName 
 } 
 . 
 ` 
 ); 
  
 try 
  
 { 
  
 fs 
 . 
 writeFileSync 
 ( 
 fileName 
 , 
  
 data 
 ); 
  
 generatedFileNames 
 . 
 push 
 ( 
 fileName 
 ); 
  
 } 
  
 catch 
  
 ( 
 error 
 ) 
  
 { 
  
 console 
 . 
 error 
 ( 
 ` 
 Failed 
  
 to 
  
 write 
  
 image 
  
 file 
  
 $ 
 { 
 fileName 
 }: 
 ` 
 , 
  
 error 
 ); 
  
 } 
  
 } 
  
 } 
  
 return 
  
 generatedFileNames 
 ; 
 } 
 

 curl  
-X  
POST  
 \ 
  
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
 \ 
  
-H  
 "Content-Type: application/json" 
  
 \ 
  
https:// ${ 
 API_ENDPOINT 
 } 
:generateContent  
 \ 
  
-d  
 '{ 
 "contents": { 
 "role": "USER", 
 "parts": { "text": "Create a tutorial explaining how to make a peanut butter and jelly sandwich in three easy steps."}, 
 }, 
 "generation_config": { 
 "response_modalities": ["TEXT", "IMAGE"], 
 }, 
 "safetySettings": { 
 "method": "PROBABILITY", 
 "category": "HARM_CATEGORY_DANGEROUS_CONTENT", 
 "threshold": "BLOCK_MEDIUM_AND_ABOVE" 
 }, 
 }' 
  
 2 
>/dev/null  
>response.json 

Generate interleaved images and text

Gemini 2.5 Flash Image Preview can generate interleaved images with its text responses. For example, you can generate images of what each step of a generated recipe might look like to go along with the text of that step, without having to make separate requests to the model to do so.

pip install --upgrade google-genai

 # Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values 
 # with appropriate values for your project. 
 export 
  
 GOOGLE_CLOUD_PROJECT 
 = 
 GOOGLE_CLOUD_PROJECT 
 export 
  
 GOOGLE_CLOUD_LOCATION 
 = 
 global 
 export 
  
 GOOGLE_GENAI_USE_VERTEXAI 
 = 
True

  from 
  
 google 
  
 import 
 genai 
 from 
  
 google.genai.types 
  
 import 
 GenerateContentConfig 
 , 
 Modality 
 from 
  
 PIL 
  
 import 
 Image 
 from 
  
 io 
  
 import 
 BytesIO 
 client 
 = 
 genai 
 . 
 Client 
 () 
 response 
 = 
 client 
 . 
 models 
 . 
 generate_content 
 ( 
 model 
 = 
 "gemini-2.5-flash-image-preview" 
 , 
 contents 
 = 
 ( 
 "Generate an illustrated recipe for a paella." 
 "Create images to go alongside the text as you generate the recipe" 
 ), 
 config 
 = 
 GenerateContentConfig 
 ( 
 response_modalities 
 = 
 [ 
 Modality 
 . 
 TEXT 
 , 
 Modality 
 . 
 IMAGE 
 ]), 
 ) 
 with 
 open 
 ( 
 "output_folder/paella-recipe.md" 
 , 
 "w" 
 ) 
 as 
 fp 
 : 
 for 
 i 
 , 
 part 
 in 
 enumerate 
 ( 
 response 
 . 
 candidates 
 [ 
 0 
 ] 
 . 
 content 
 . 
 parts 
 ): 
 if 
 part 
 . 
 text 
 is 
 not 
 None 
 : 
 fp 
 . 
 write 
 ( 
 part 
 . 
 text 
 ) 
 elif 
 part 
 . 
 inline_data 
 is 
 not 
 None 
 : 
 image 
 = 
 Image 
 . 
 open 
 ( 
 BytesIO 
 (( 
 part 
 . 
 inline_data 
 . 
 data 
 ))) 
 image 
 . 
 save 
 ( 
 f 
 "output_folder/example-image- 
 { 
 i 
 + 
 1 
 } 
 .png" 
 ) 
 fp 
 . 
 write 
 ( 
 f 
 "![image](example-image- 
 { 
 i 
 + 
 1 
 } 
 .png)" 
 ) 
 # Example response: 
 #  A markdown page for a Paella recipe(`paella-recipe.md`) has been generated. 
 #   It includes detailed steps and several images illustrating the cooking process. 
 

 curl  
-X  
POST  
 \ 
  
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
 \ 
  
-H  
 "Content-Type: application/json" 
  
 \ 
  
https:// ${ 
 API_ENDPOINT 
 } 
:generateContent  
 \ 
  
-d  
 '{ 
 "contents": { 
 "role": "USER", 
 "parts": { "text": "Create a tutorial explaining how to make a peanut butter and jelly sandwich in three easy steps. For each step, provide a title with the number of the step, an explanation, and also generate an image, generate each image in a 1:1 aspect ratio."}, 
 }, 
 "generation_config": { 
 "response_modalities": ["TEXT", "IMAGE"], 
 }, 
 "safetySettings": { 
 "method": "PROBABILITY", 
 "category": "HARM_CATEGORY_DANGEROUS_CONTENT", 
 "threshold": "BLOCK_MEDIUM_AND_ABOVE" 
 }, 
 }' 
  
 2 
>/dev/null  
>response.json 

Locale-aware image generation

Gemini 2.5 Flash Image Preview can also include information about your location when providing text or image responses. For example, you can generate images of types of locations or experiences that take your current location into account without having to specify your location to the model to do so.

pip install --upgrade google-genai

 # Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values 
 # with appropriate values for your project. 
 export 
  
 GOOGLE_CLOUD_PROJECT 
 = 
 GOOGLE_CLOUD_PROJECT 
 export 
  
 GOOGLE_CLOUD_LOCATION 
 = 
 global 
 export 
  
 GOOGLE_GENAI_USE_VERTEXAI 
 = 
True

  from 
  
 google 
  
 import 
 genai 
 from 
  
 google.genai.types 
  
 import 
 GenerateContentConfig 
 , 
 Modality 
 from 
  
 PIL 
  
 import 
 Image 
 from 
  
 io 
  
 import 
 BytesIO 
 client 
 = 
 genai 
 . 
 Client 
 () 
 response 
 = 
 client 
 . 
 models 
 . 
 generate_content 
 ( 
 model 
 = 
 "gemini-2.5-flash-image-preview" 
 , 
 contents 
 = 
 ( 
 "Generate a photo of a breakfast meal." 
 ), 
 config 
 = 
 GenerateContentConfig 
 ( 
 response_modalities 
 = 
 [ 
 Modality 
 . 
 TEXT 
 , 
 Modality 
 . 
 IMAGE 
 ]), 
 ) 
 for 
 part 
 in 
 response 
 . 
 candidates 
 [ 
 0 
 ] 
 . 
 content 
 . 
 parts 
 : 
 if 
 part 
 . 
 text 
 : 
 print 
 ( 
 part 
 . 
 text 
 ) 
 elif 
 part 
 . 
 inline_data 
 : 
 image 
 = 
 Image 
 . 
 open 
 ( 
 BytesIO 
 (( 
 part 
 . 
 inline_data 
 . 
 data 
 ))) 
 image 
 . 
 save 
 ( 
 "output_folder/example-breakfast-meal.png" 
 ) 
 # Example response: 
 #   Generates a photo of a vibrant and appetizing breakfast meal. 
 #   The scene will feature a white plate with golden-brown pancakes 
 #   stacked neatly, drizzled with rich maple syrup and ... 
 

 curl  
-X  
POST  
 \ 
  
-H  
 "Authorization: Bearer 
 $( 
gcloud  
auth  
print-access-token ) 
 " 
  
 \ 
  
-H  
 "Content-Type: application/json" 
  
 \ 
  
https:// ${ 
 API_ENDPOINT 
 } 
:generateContent  
 \ 
  
-d  
 '{ 
 "contents": { 
 "role": "USER", 
 "parts": { "text": "Generate a photo of a typical breakfast."}, 
 }, 
 "generation_config": { 
 "response_modalities": ["TEXT", "IMAGE"], 
 }, 
 "safetySettings": { 
 "method": "PROBABILITY", 
 "category": "HARM_CATEGORY_DANGEROUS_CONTENT", 
 "threshold": "BLOCK_MEDIUM_AND_ABOVE" 
 }, 
 }' 
  
 2 
>/dev/null  
>response.json