Create: Generate Images

The Create tab generates new images from a written description. You describe the image, pick a model, and the result is placed into your document as a new layer.

How to generate an image

1. 1
   Choose a model in the dropdown at the top of the tab.
2. 2
   Type a description into the text field. This description is called a prompt. Plain language works, you do not need special wording.
3. 3
   Optional: add reference images (see below).
4. 4
   Optional: set the number of variations to receive several results to compare.
5. 5
   Click Generate. Each result arrives as its own layer.

Reference images

Most models accept reference images. They guide the result, for example toward a certain style, product, or person.

• Add images with the image button (PNG, JPG, or WebP files) or take the content of the current layer with the layer button.
• Drag the thumbnails to change their order. Without an active selection in Photoshop, the first image is treated as the main image and the others as references.
• Each model has its own limit for the number of images (see the list below).

Models in the Create tab

• Nano Banana 2 (default): General purpose model by Google. Resolutions up to 4K, a wide range of aspect ratios, up to 14 reference images. Supports Preview and Commit, a thinking level setting, and an optional web search that lets the model look up current information.
• Nano Banana 2 Pro: The larger model of the same family. Up to 14 reference images. Supports Preview and Commit.
• GPT Image 2: Image model by OpenAI. Quality setting from auto to high, up to 10 reference images, up to 4 variations per run. Supports Preview and Commit.
• Reve: Up to 6 reference images and a quality setting. Offers optional post processing: background removal and additional upscaling of the result. These steps can add costs.
• Reve 2.1: Newer version of Reve with more aspect ratio options. Up to 6 reference images. No quality setting.
• FLUX Pro Kontext: One reference image. Includes a guidance setting.
• FLUX Pro Kontext Max Multi: Same family, accepts up to 9 reference images.
• FLUX 2 Max Edit: Up to 9 reference images.
• FLUX 2 LoRA Edit: Supports LoRA files. A LoRA is a small add-on file that gives a model a specific style. Up to 3 reference images, guidance and steps settings.
• Seedream 4.5: Up to 10 reference images and up to 6 variations per run.
• Imagen 4 Ultra: Text only model by Google. Does not accept reference images.

Model settings

The settings panel shows only the options the selected model supports. The most common ones:

• Aspect ratio: The shape of the image, for example square, landscape, or portrait. On "auto" Seam derives it from your selection or canvas.
• Resolution: The output size. On "auto" Seam picks the smallest size that covers the target area.
• Seed: A number that fixes the random part of a generation. The same seed with the same settings repeats a result. The shuffle button picks a new random number.
• Variations: How many images are generated in one run. Each variation counts as one generation.
• Guidance: How strictly the model follows your description. Lower values give the model more freedom.
• Steps: How many refinement passes the model runs. More steps take longer.