Skip to content
ComfyDeploy
Get started

Insta Pic (Nano Banana)

Upload a photo of yourself and type a place or scene, and the workflow generates a new picture of you there. Made for social media posts and travel-style content.

Run on ComfyDeployDownload JSON
Insta Pic (Nano Banana) example output

How it works

Insta Pic is a Nano Banana workflow. The generation is handled by Google’s Gemini 2.5 Flash Image model (google/gemini-2.5-flash-image-preview, with a free variant listed) via OpenRouter, so no model files are loaded on the GPU.

Your subject photo is loaded and passed through a ResizeAndPad node so it matches the aspect ratio you choose. The text you type, such as a city name and camera angle, goes into the LLMPromptManager together with a BananaTaskGenerator node that supplies the task instructions. A PreviewAny node shows the final prompt text. The GenerateImage node then sends image and prompt to the model with the OpenRouter configuration and saves the result with SaveImage.

The inputs you see in the playground are the subject image, location prompt, extra prompt, aspect ratio, seed, model choice and your API key.

Tips

  • Use a clear photo where your face and body are visible and not cut off, since the image is padded rather than cropped.
  • Add camera language to the location, for example a low angle or close-up, as in the default Hong Kong prompt.
  • Pick the aspect ratio for the destination: 9:16 for stories, 3:4 or 1:1 for feed posts.
  • Re-run with a new seed if the first result changes your face too much.

Run it as an API

Deploy it on ComfyDeploy to call it from a script or app that sends a photo and a location.

What you can use it for

  • Travel-style photos without traveling
  • Social media content from one selfie
  • Changing the camera angle or setting of a portrait
  • Quick location mockups for creators

Run it in three steps

  1. Open the template

    Click Run on ComfyDeploy. The workflow, its custom nodes and models are set up for you on a cloud machine.

  2. Add your inputs

    Provide subject photo and location or scene prompt in the playground or the ComfyUI editor.

  3. Run, share or deploy

    Run it on a T4, share it with your team as a playground, or deploy it as an API endpoint.

Frequently asked questions

What GPU does the Insta Pic workflow need?

The recommended GPU is a T4. The image itself is generated by Gemini 2.5 Flash Image through OpenRouter, so the GPU only handles light resizing and padding.

Do I need my own API key?

Yes. The workflow has an external_api_key text input for your OpenRouter key, which the GenerateImage node uses to call the Gemini model. Without a key, the call cannot be made.

What should I type as the prompt?

Describe a place and, optionally, a camera angle. The default example is a Hong Kong trip with a close-up shot from a low camera angle.

Related workflows

All Nano Banana workflows