On the Firefly homepage, select Generate in the left panel and then Generate image.
Last updated on
Jun. 9, 2026
Learn how to use Gemini image generation models to generate image variations.
Use Gemini models like Gemini 2.5 (Nano Banana), Gemini 3 (Nano Banana Pro), and Gemini 3.1 (Nano Banana 2) with the Generate image feature to create images from simple text prompts in Firefly. These models can help generate visually rich outputs from descriptive prompts. Refine your prompt and use Firefly controls to explore different image variations and creative directions.
When you select a partner model to generate images, you'll be prompted to confirm that you're using a model that isn't developed by Adobe, along with other relevant information. Please review the details and select OK to continue.
In the General settings section, select the Model dropdown menu.
Under the Partner models section, select the Gemini 2.5 (w/ Nano Banana), Gemini 3 (w/ Nano Banana Pro), or Gemini 3.1 (w/ Nano Banana 2) model.
Select the aspect ratio from the following options:
- Ultra Wide (21:9)
- Widescreen (16:9)
- Classic (5:4)
- Landscape (4:3)
- Wide (3:2)
- Square (1:1)
- Standard (4:5)
- Portrait (3:4)
- Tall (2:3)
- Vertical (9:16)
With Gemini 3 (w/ Nano Banana Pro) and Gemini 3.1 (w/ Nano Banana 2), you can select the Resolution drop-down menu to define the resolution settings for the generated video as 1K and 2K.
If you want to edit an image, such as adding elements, use the Reference images section to upload one or multiple files.
Enter a text prompt in the Prompt field.
Uploaded image
Edited image using text prompt
Edited image using text prompt
Edited image using text prompt
Select Generate .
Turn text into art with Adobe Firefly
Create beautiful images and video clips from text prompts using generative AI.
