All tutorials

Images & design

Create an AI profile photo for social media

Prepare the source, run the supplied image workflow, compare the result, and keep only the version that preserves the important details.

Guide
TUT-005
Time
77 min
Level
Intermediate
Reviewed

Adapted from TUT-005, dated 2026-02-25.

What you'll make

A checked set of generated visuals matched to the source assets and intended format.

Create an AI profile photo for social media

Who this is for

Creators, marketers, founders, and small teams producing visual work from their own source assets.

Step by step

Run the workflow

  1. 01

    Review the workflow

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Turn one photo into multiple AI profile photo styles.
    2. Output: Multiple profile photo variations for selection
    Expected result for create an ai profile photo for social media.
    Use this source result as the visual comparison point for the step.
    Expected result for create an ai profile photo for social media.
    Use this source result as the visual comparison point for the step.
    Expected result for create an ai profile photo for social media.
    Use this source result as the visual comparison point for the step.
    Expected result for create an ai profile photo for social media.
    Use this source result as the visual comparison point for the step.
    Expected result for create an ai profile photo for social media.
    Use this source result as the visual comparison point for the step.
    Expected result for create an ai profile photo for social media.
    Use this source result as the visual comparison point for the step.
    Expected result for create an ai profile photo for social media.
    Use this source result as the visual comparison point for the step.
    Expected result for create an ai profile photo for social media.
    Use this source result as the visual comparison point for the step.
    Expected result for create an ai profile photo for social media.
    Use this source result as the visual comparison point for the step.
    Common failure modes
    • The model changes the subject, framing, text, product, or background instead of editing only the requested element.
    • The result looks polished at first glance but contains broken hands, unreadable text, warped objects, or inconsistent lighting.
  2. 02

    Prepare your source photo

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Take a few photos and choose the clearest one. Good lighting matters more than camera gear.
    Source example for review the workflow.
    Use this visual to confirm the expected setup or result.
    Common failure modes
    • The model changes the subject, framing, text, product, or background instead of editing only the requested element.
    • The result looks polished at first glance but contains broken hands, unreadable text, warped objects, or inconsistent lighting.
  3. 03

    Your Prompt Director

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. We remove the guesswork from prompt writing. This CustomGPT turns your source photo and design reference into a structured profile photo prompt for Gemini.
    Prompt setup used for prepare your source photo.
    Check the prompt field, reference order, and visible settings.
    Common failure modes
    • The model changes the subject, framing, text, product, or background instead of editing only the requested element.
    • The result looks polished at first glance but contains broken hands, unreadable text, warped objects, or inconsistent lighting.
  4. 04

    Let's get started

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Link Open the CustomGPT
    2. Open the Custom ChatGPT using the link above.
    3. Press "let's beginʼ.
    4. ChatGPT will guide you with the setup instructions.
    Source example for your prompt director.
    Use this visual to confirm the expected setup or result.
    Source example for your prompt director.
    Use this visual to confirm the expected setup or result.
    Common failure modes
    • The model changes the subject, framing, text, product, or background instead of editing only the requested element.
    • The result looks polished at first glance but contains broken hands, unreadable text, warped objects, or inconsistent lighting.
  5. 05

    Upload your source photo and ring asset, then reply to the setup questions

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Download Circle Asset: Link
    2. ChatGPT will generate a ready-to-paste prompt for Gemini.
    Upload interface used for let's get started.
    Check the selected files and their order before continuing.
    Upload interface used for let's get started.
    Check the selected files and their order before continuing.
    Common failure modes
    • The model changes the subject, framing, text, product, or background instead of editing only the requested element.
    • The result looks polished at first glance but contains broken hands, unreadable text, warped objects, or inconsistent lighting.
  6. 06

    Image Generation

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. With your prompt and assets ready, it's time to generate your profile photo in Gemini.
    2. Go to Google Gemini
    Prompt setup used for upload your source photo and ring asset, then reply to the setup questions.
    Check the prompt field, reference order, and visible settings.
    Prompt setup used for upload your source photo and ring asset, then reply to the setup questions.
    Check the prompt field, reference order, and visible settings.
    Prompt setup used for upload your source photo and ring asset, then reply to the setup questions.
    Check the prompt field, reference order, and visible settings.
    Common failure modes
    • The model changes the subject, framing, text, product, or background instead of editing only the requested element.
    • The result looks polished at first glance but contains broken hands, unreadable text, warped objects, or inconsistent lighting.
  7. 07

    Copy the prompt generated by ChatGPT in Phase 2

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Paste the ChatGPT prompt, then upload your source photo, ring asset, and optional logo.
    Upload interface used for image generation.
    Check the selected files and their order before continuing.
    Upload interface used for image generation.
    Check the selected files and their order before continuing.
    Common failure modes
    • The model changes the subject, framing, text, product, or background instead of editing only the requested element.
    • The result looks polished at first glance but contains broken hands, unreadable text, warped objects, or inconsistent lighting.
  8. 08

    Click Create image, then submit the prompt

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Review the generated result. If needed, refine the prompt in ChatGPT and try again.
    Expected result for copy the prompt generated by chatgpt in phase 2.
    Use this source result as the visual comparison point for the step.
    Common failure modes
    • The model changes the subject, framing, text, product, or background instead of editing only the requested element.
    • The result looks polished at first glance but contains broken hands, unreadable text, warped objects, or inconsistent lighting.
  9. 09

    Generated profile photo variations

    Use the source inputs to complete this stage and produce a result that can be checked before continuing.

    1. Follow the shown setup, keep the source order unchanged, and run one controlled test.
    Source example for click create image, then submit the prompt.
    Use this visual to confirm the expected setup or result.
    Source example for click create image, then submit the prompt.
    Use this visual to confirm the expected setup or result.
    Source example for click create image, then submit the prompt.
    Use this visual to confirm the expected setup or result.
    Source example for click create image, then submit the prompt.
    Use this visual to confirm the expected setup or result.
    Source example for click create image, then submit the prompt.
    Use this visual to confirm the expected setup or result.
    Source example for click create image, then submit the prompt.
    Use this visual to confirm the expected setup or result.
    Source example for click create image, then submit the prompt.
    Use this visual to confirm the expected setup or result.
    Source example for click create image, then submit the prompt.
    Use this visual to confirm the expected setup or result.
    Source example for click create image, then submit the prompt.
    Use this visual to confirm the expected setup or result.
    Source example for click create image, then submit the prompt.
    Use this visual to confirm the expected setup or result.
    Source example for click create image, then submit the prompt.
    Use this visual to confirm the expected setup or result.
    Common failure modes
    • The model changes the subject, framing, text, product, or background instead of editing only the requested element.
    • The result looks polished at first glance but contains broken hands, unreadable text, warped objects, or inconsistent lighting.

Before you use it

Final checks

  • Check the full result for changed people, products, text, timing, or layout.
  • Confirm the tool, model, controls, and cost before generating.
  • Keep private or unreleased material out of third-party tools.

Share your work

Made it? Show me.

Post your finished result on Instagram and tag @terencesia. I'll share a few standout results with the community.

Tag @terencesia on Instagram (opens in a new tab)

Next step

Run one low-cost test, record the first visible failure, and revise only the instruction or source asset tied to that problem.

Back to the tutorial library

Sources

What this guide relies on