You with a fitness transformation split
YouTube Thumbnails AI image prompt Β· 5 styles Β· works with Nano Banana, ChatGPT, Gemini, Midjourney & Grok
Scene: The person with a fitness transformation split, 'DAY 1 vs DAY 90'.
Style 1: MrBeast-style hyper-saturated thumbnail
MrBeast-style hyper-saturated thumbnail, thick white outline around the person, bold text
Nano Banana prompt
Using the uploaded photo as reference, keep every face, facial feature and identity 100% identical. Create the person with a fitness transformation split, 'DAY 1 vs DAY 90'. MrBeast-style hyper-saturated thumbnail, thick white outline around the person, bold text. Highly detailed, 4K, aspect ratio 16:9.
ChatGPT prompt
Create an image using my uploaded photo. Show the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Style: MrBeast-style hyper-saturated thumbnail, thick white outline around the person, bold text. Keep the face exactly recognisable β do not change facial features, skin tone or hairline. Landscape (3:2) orientation.
Gemini prompt
Edit my photo into a new image: the person with a fitness transformation split, 'DAY 1 vs DAY 90'. MrBeast-style hyper-saturated thumbnail, thick white outline around the person, bold text. Keep my face the same as in the original photo and make the result look natural, sharp and high quality.
Midjourney prompt
the person with a fitness transformation split, 'DAY 1 vs DAY 90', mrbeast-style hyper-saturated thumbnail, thick white outline around the person, bold text, highly detailed --ar 16:9 --oref <your-photo-URL> --ow 100
Grok prompt
Edit this photo: the person with a fitness transformation split, 'DAY 1 vs DAY 90'. MrBeast-style hyper-saturated thumbnail, thick white outline around the person, bold text. Keep my face exactly the same as in the photo. Aspect ratio 16:9, high detail.
Style 2: Clean minimal tech-reviewer thumbnail
Clean minimal tech-reviewer thumbnail, soft gradient background
Nano Banana prompt
Using the uploaded photo as reference, keep every face, facial feature and identity 100% identical. Create the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Clean minimal tech-reviewer thumbnail, soft gradient background. Highly detailed, 4K, aspect ratio 16:9.
ChatGPT prompt
Create an image using my uploaded photo. Show the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Style: Clean minimal tech-reviewer thumbnail, soft gradient background. Keep the face exactly recognisable β do not change facial features, skin tone or hairline. Landscape (3:2) orientation.
Gemini prompt
Edit my photo into a new image: the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Clean minimal tech-reviewer thumbnail, soft gradient background. Keep my face the same as in the original photo and make the result look natural, sharp and high quality.
Midjourney prompt
the person with a fitness transformation split, 'DAY 1 vs DAY 90', clean minimal tech-reviewer thumbnail, soft gradient background, highly detailed --ar 16:9 --oref <your-photo-URL> --ow 100
Grok prompt
Edit this photo: the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Clean minimal tech-reviewer thumbnail, soft gradient background. Keep my face exactly the same as in the photo. Aspect ratio 16:9, high detail.
Style 3: Dramatic cinematic thumbnail with dark vignette and glow
Dramatic cinematic thumbnail with dark vignette and glow
Nano Banana prompt
Using the uploaded photo as reference, keep every face, facial feature and identity 100% identical. Create the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Dramatic cinematic thumbnail with dark vignette and glow. Highly detailed, 4K, aspect ratio 16:9.
ChatGPT prompt
Create an image using my uploaded photo. Show the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Style: Dramatic cinematic thumbnail with dark vignette and glow. Keep the face exactly recognisable β do not change facial features, skin tone or hairline. Landscape (3:2) orientation.
Gemini prompt
Edit my photo into a new image: the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Dramatic cinematic thumbnail with dark vignette and glow. Keep my face the same as in the original photo and make the result look natural, sharp and high quality.
Midjourney prompt
the person with a fitness transformation split, 'DAY 1 vs DAY 90', dramatic cinematic thumbnail with dark vignette and glow, highly detailed --ar 16:9 --oref <your-photo-URL> --ow 100
Grok prompt
Edit this photo: the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Dramatic cinematic thumbnail with dark vignette and glow. Keep my face exactly the same as in the photo. Aspect ratio 16:9, high detail.
Style 4: Bright cartoon-pop thumbnail with comic stickers
Bright cartoon-pop thumbnail with comic stickers
Nano Banana prompt
Using the uploaded photo as reference, keep every face, facial feature and identity 100% identical. Create the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Bright cartoon-pop thumbnail with comic stickers. Highly detailed, 4K, aspect ratio 16:9.
ChatGPT prompt
Create an image using my uploaded photo. Show the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Style: Bright cartoon-pop thumbnail with comic stickers. Keep the face exactly recognisable β do not change facial features, skin tone or hairline. Landscape (3:2) orientation.
Gemini prompt
Edit my photo into a new image: the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Bright cartoon-pop thumbnail with comic stickers. Keep my face the same as in the original photo and make the result look natural, sharp and high quality.
Midjourney prompt
the person with a fitness transformation split, 'DAY 1 vs DAY 90', bright cartoon-pop thumbnail with comic stickers, highly detailed --ar 16:9 --oref <your-photo-URL> --ow 100
Grok prompt
Edit this photo: the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Bright cartoon-pop thumbnail with comic stickers. Keep my face exactly the same as in the photo. Aspect ratio 16:9, high detail.
Style 5: Documentary-style thumbnail
Documentary-style thumbnail, muted tones, serious mood
Nano Banana prompt
Using the uploaded photo as reference, keep every face, facial feature and identity 100% identical. Create the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Documentary-style thumbnail, muted tones, serious mood. Highly detailed, 4K, aspect ratio 16:9.
ChatGPT prompt
Create an image using my uploaded photo. Show the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Style: Documentary-style thumbnail, muted tones, serious mood. Keep the face exactly recognisable β do not change facial features, skin tone or hairline. Landscape (3:2) orientation.
Gemini prompt
Edit my photo into a new image: the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Documentary-style thumbnail, muted tones, serious mood. Keep my face the same as in the original photo and make the result look natural, sharp and high quality.
Midjourney prompt
the person with a fitness transformation split, 'DAY 1 vs DAY 90', documentary-style thumbnail, muted tones, serious mood, highly detailed --ar 16:9 --oref <your-photo-URL> --ow 100
Grok prompt
Edit this photo: the person with a fitness transformation split, 'DAY 1 vs DAY 90'. Documentary-style thumbnail, muted tones, serious mood. Keep my face exactly the same as in the photo. Aspect ratio 16:9, high detail.
How to use this prompt
π Nano Banana
- Open the Gemini app or Google AI Studio and pick the π image tool (Nano Banana).
- Upload your photo (skip this for prompts that don't need one).
- Paste the prompt and generate. Ask for small tweaks in follow-up messages.
π¬ ChatGPT
- Open ChatGPT and start a new chat (it uses OpenAI's GPT Image model).
- Attach your photo with the + button if the prompt needs one.
- Paste the prompt and send. If details drift, reply with a short correction.
β¨ Gemini
- Open gemini.google.com or the Gemini app.
- Upload your photo if the prompt needs one.
- Paste the prompt and send, then refine with short follow-ups.
β΅ Midjourney
- Open midjourney.com (or Discord) and go to Create.
- For photo prompts, drag your photo into the prompt bar as an Omni Reference β or replace <your-photo-URL> with its link.
- Paste the prompt and generate; raise --ow (up to 1000) to keep the face or product closer.
π Grok
- Open Grok (grok.com, the app or on X) and choose Imagine / image editing.
- Upload your photo if the prompt needs one.
- Paste the prompt and generate.
Tips for better results
- Use a sharp, well-lit, front-facing photo β avoid sunglasses, heavy filters and group shots for solo prompts.
- If the face changes, reply: βKeep my face exactly the same as in the uploaded photo.β
- Change details freely β swap colours, outfits or locations to make the image yours.
- For couple or family prompts, upload one photo per person and say who is who.
- Generate 2β3 times and keep the best; small wording changes can give very different results.