The Gemini prompts that restore and colourise old family photos best are short and scoped: one prompt per job, naming the damage, what to leave alone, and the era. Start with "Describe the damage you can see in this photo", repair creases and tears next, fix fading after that, and colourise last, adding any colours you know for certain. Gemini can mend a crease convincingly, but any colour or missing detail it adds is a guess, so the prompts below are written to keep faces and facts as they were.
Why Gemini, and what it's doing
Google's Gemini app lets you upload an image and talk to it like an editor sitting next to you. Google doesn't state on its upload help page which image model sits behind the editing, so I'll just call it Gemini's image editing. You don't need a separate app to try it, but you do need to be signed in: Google says you must be signed in to Gemini Apps to upload files.
What it's not doing is "restoring" in the archival sense. A conservator restoring a photograph is working to recover what was physically there. Gemini is predicting what probably was there, based on patterns from millions of other photographs. For a crease across a plain wall, that prediction is reliable. For half a face that's been torn away, it's inventing a face that fits the statistical pattern of faces, not necessarily your great-uncle's actual nose. That matters once you're printing the result and handing it to your mum.
Getting your scan in takes a minute. These are the steps from Google's Gemini Apps Help page on uploading files for a computer:
- Open the Gemini web app in your browser and sign in.
- In the text box at the bottom, type your prompt.
- Click Add files, then Upload files, and choose your scan.
- Click Submit.
Google allows up to 10 files in the same prompt (subject to availability) and up to 100 MB per file for anything other than video, which is plenty for a photo scan. If you get an error saying Gemini failed to analyse your file, Google's advice is simply to upload it again. For restoration I'd still upload one photo at a time, so each prompt is about one picture.
A worked example: the 1958 doorstep photo
Say you've found a black-and-white photo of your grandmother standing outside a terraced house in 1958, creased hard down the middle, with a patch of damage near her left shoulder and general fading across the whole print. Here's how I'd break that into prompts rather than firing one big request at Gemini and hoping.
- Step 1, assess before you touch anything. Upload the scan and ask: "Describe the damage you can see in this photo, including creases, tears, fading, and any areas where detail is missing." This gets Gemini to tell you what it thinks it's looking at before it starts guessing fixes, and it's a useful check, if it misreads a shadow as a tear, you'll catch it now.
- Step 2, fix structure first. Prompt: "Repair the vertical crease running down the centre of this photo and the damaged patch near the woman's left shoulder. Do not alter her face, clothing colour, or the background details. Keep the repair realistic for a 1950s photograph."
- Step 3, address fading separately. Once the structural damage is sorted, run a second prompt: "Improve the contrast and reduce the overall fading in this photo without changing the composition or adding any new objects."
- Step 4, colourise last. Only once you're happy with the repaired black-and-white version: "Add realistic, natural colour to this 1950s photograph. Use period-appropriate tones, skin tones, and clothing colours typical for the era. Keep the result looking like a colour photograph from the time, not a modern filter."
- Step 5, sense-check with family. Before anyone treats the colourised version as the "real" photo, show it to whoever remembers the original scene. Ask specifically about the clothing colour and the house. It's the step that stops you printing a fiction and calling it history.
If you only want one pass on a snapshot that doesn't carry much weight, use this instead: "Repair the creases and tears in this photo, keep every face exactly as it is, do not add or remove people or objects, and keep it black and white." It trades control for speed. For the doorstep photo, or anything going on a wall or into a memorial, stick with the four prompts above.
Four prompts and a family check, not one prompt. That's the number that matters here: trying to cram repair and colourisation and sharpening into a single instruction gives Gemini too many jobs at once, and it tends to overcorrect, smoothing out texture that should have stayed or adding colour casts that look more like Instagram filters than 1958.
Prompts for specific damage types
Different damage needs different wording. Vague prompts like "restore this" get you vague, over-smoothed results. Specific prompts get you specific fixes.
- Torn or missing corners: "Fill in the missing corner of this photograph using the surrounding pattern and lighting as a guide. Keep the rest of the image unchanged."
- Water damage or staining: "Remove the brown staining and discolouration across the top third of this photo while preserving the texture and grain of the original print."
- Faded faces: "Sharpen and clarify the facial features in this photo without changing the person's expression, age, or facial structure."
- Double exposure or scratches: "Remove the thin white scratches running across the image and the faint double-exposure ghosting in the upper left, keeping everything else exactly as it is."
- Low-resolution scans: "Increase the clarity and detail of this image without adding artificial sharpening artefacts or changing any facial features."
After each edit, run one checking prompt: "Compare the edited photo with the original and list everything you changed, including any facial features." Then put the two images side by side yourself. If the list mentions eyes, mouth, nose or jawline, or you can see a change there, go back to the previous version and repeat the repair with a firmer "do not change her face" instruction. That's how you catch an invented face before it's printed.
Notice the pattern: every prompt names the damage, states what to leave alone, and avoids open-ended instructions like "make it look better." Gemini, like every generative model, fills gaps with its best guess when you leave the door open. Close the door as much as you can.
If your damage doesn't fit any of these, or you'd rather tap a button in a dedicated restoration app than write prompts, the usual route is Remini or one of the Remini alternatives.
Colourising: what you're really choosing
Colourisation is the part people enjoy most and trust least, often without realising it. When you ask Gemini to colour a black-and-white photo, it has no record of what colour your grandad's shirt was. It's choosing the most statistically plausible colour based on the era, the lighting, and typical patterns in photos from that decade. A navy shirt and a dark green shirt look nearly identical in black and white, and the model will pick one. It might pick wrong.
That's not a reason to avoid colourising old photos. It's a reason to treat the result as an interpretation, not a document. If a colour matters to the family story, like a specific dress or a car, say so in the prompt: "Colourise this photo. The car in the background was red, a Ford from around 1955." Gemini will use that detail rather than guessing. For everything else, it's filling in plausible colour, and that's fine as long as everyone looking at the final print knows that's what happened.
For the doorstep photo, a family member might remember the details, which gives you a stronger prompt: "Colourise this photo. My grandmother's dress was pale blue, the door was dark green, and the photo is from 1958 in the UK." Gemini now has three facts to work from. The brickwork, the sky, her shoes and her skin tone are still its guess, because any colour you don't name is a guess.
If you want a side-by-side sense of how different free tools handle this exact trade-off, there's a fuller comparison on where to colourise old black and white photos with AI free, which is worth reading before you commit a whole shoebox of prints to one approach.
If you're using Gemini on modern portraits too, there's a separate explainer on Gemini AI photo prompts for men.
Want AI doing the heavy lifting in your marketing?
I build the systems that handle the boring 80 percent, so you get your week back. Done properly, with the human kept in.
Working the free tier without wasting your photos
Google doesn't publish a daily number for image edits on its upload help page. What it does say is that higher limits, such as uploading more files, come with a Google AI plan. So if Gemini stops accepting uploads partway through a session, either come back later or look at a plan. Work in smaller rounds: pick five or six photos, run your repair and colourise prompts on those, export them, then come back later rather than trying to clear an entire family archive in one go. It also means you're checking results as you go rather than discovering twenty photos later that Gemini decided your great-grandfather's cottage had a different roof.
A few practical habits that save you re-work:
- Scan at a high resolution before uploading anything, since Gemini can only work with the detail that's in the file. Google doesn't publish a recommended scan setting, so the practical ceiling is its 100 MB per-file limit.
- Keep the original scan untouched and always work on a copy, so you can go back if a prompt overcorrects.
- Ask for one change at a time on anything that matters, a wedding photo, a photo of someone who's passed away, a photo that's going into a memorial slideshow. Save the one-prompt-does-everything approach for snaps that don't carry weight.
- Export at the resolution Gemini gives you, then check it against the original before printing. Upscaling a result that's already slightly soft will only make the softness more obvious.
And for modern photos of two people rather than family archives, see my post on Gemini couple photo prompts.
When Gemini isn't the right tool
For heavily damaged photos, physically torn into pieces, mould damage, or prints where most of the surface detail is gone, Gemini's guesswork gets less reliable the less original information it has to work from. In those cases a specialist restoration service, or a human retoucher working frame by frame, will do a more faithful job than any prompt, however carefully worded. There's a rundown of options, free and otherwise, including where the AI tools hold their own, at where to restore damaged old photos with AI for free, which is worth a look if you're dealing with anything beyond creases and fading.
Some photos should stay damaged. A tear across a photo of a grandparent who died young isn't always a flaw to erase, it's part of the object's history, and a perfectly smoothed AI version can feel less honest than the creased original, even if it looks sharper. Worth deciding that on purpose rather than by default.
I have written more around this on the site: Where to Restore Damaged Old Photos With AI for Free, Where to Colourise Old Black and White Photos With AI Free.
If you also edit photos in ChatGPT, the wider series is the ChatGPT Prompts and Limits: 30 Guides to Fun Prompts, Photo Edits and Daily Caps, and if your damage needs wording that isn't in the lists above, try the free tool that writes the prompt for you.
Portuguese speakers can find more ideas in prompts para foto em português.
And if you write about AI tools yourself, there's a list of LLM blogs open to guest writers in one place on this site.
Frequently asked questions
Do I need to sign in to use Gemini to edit a photo?
Yes. Google says you must be signed in to Gemini Apps to upload files, so you'll need a Google Account before you can add your scan.
How many photos can I upload to Gemini at once?
Google says up to 10 files in the same prompt, subject to availability, and up to 100 MB per file for anything other than video. For restoration, one photo per prompt keeps the instructions clear.
Why does Gemini sometimes change a face when restoring a photo?
When part of a face is damaged or missing, Gemini fills the gap with a statistically likely face rather than the actual person's features, so always prompt it to leave facial structure unchanged and check the result against other photos of the same person.
What do I do if Gemini fails to read my scan?
Upload it again. Google's help suggests re-uploading when you get an error that Gemini failed to analyse your file. If it keeps failing, check the file is under the 100 MB limit.
Run a business, a brand or a blog? I feature tools, products and expert guest posts for an audience of 15,000. See how it works