Christi Loucks @christiloucksofficial

Workflows / Claude

How I Edit My Photos with Claude

A photoshoot wasn't in the cards. So I used the pictures I already had.

August 2026

Written August 2026. Nothing here needs a design background. It does need a Claude account and a folder of your own photos.

I'm rebuilding my brand and my website right now. I needed photos that matched the direction I'm going, and a real photoshoot isn't happening this month. Two kids, one of them brand new.

So I opened the folder where all my old pictures live. About 30 of them, going back 5 years. Different outfits, different rooms, different cameras, different years. Nothing that looked like a set.

By the end of the afternoon I had 35 finished images that all look like they came from the same place. Same treatment, same color, same grain, same feel.

Here's exactly how, in 5 steps. The last one matters most.

1. Go find examples of what you want

Open Google, search for the kind of photo you like, and save everything that stops you.

I searched things like "grainy film photo aesthetic" and "blurry flash photo" and "black and white editorial photo." I saved about 8 images. Grainy ones that look like security footage. Blurry gold ones where the flash caught someone mid-turn. Hard black and white with giant pink type across it. Washed-out cream covers with the subject off to one side.

Here's the part that felt wrong: I couldn't describe a single one of them. I knew I liked them. That was it.

Save them anyway. You're not going to copy them. You just need something to point at.

Where else to look: Pinterest works. So does an Instagram account whose photos you keep saving. Mine came from one account I'd been collecting from for months, and it turned out every look I wanted was in one place.

2. Ask Claude to describe them back to you

This step is easy to skip, and it's the one that makes the rest work.

Claude can't copy a picture. It needs the look written out as instructions before it can apply that look to your photos.

So upload your examples and ask it to describe them. The word that matters there is describe.

Here's the prompt I use:

Here are the images I've been saving. For each one, describe what was done to the photograph, written as instructions someone could actually follow.

Cover all of these:
- Color and contrast. How dark are the blacks, how blown out are the whites, what color cast is on it.
- Framing. Where is the subject in the frame, what got cropped off, what is out of focus.
- Texture. Grain, blur, scan lines, anything sitting on top of the image.
- Type, if there's text on it. Size, color, placement, whether it's cut off.

Do not tell me it looks moody or cinematic or editorial. Those words don't help me. Tell me what was physically done to the picture.

The last line is doing the most work. Without it you get adjectives, and you can't build anything out of an adjective.

What came back for the security-footage look:

Black and white, contrast pushed until skin blows out and shadows go solid. Four separate camera feeds in a grid with thin black gaps. Every crop is deliberately wrong. Chins cut off, heads half out of frame, nothing centered. Scan lines and grain over everything. Small monospace text in the corners: REC, a timecode, a battery icon.

There's something in that description I would never have found on my own.

The crops are what make it work. If I'd only copied the grainy filter part and put it over a nice centered portrait, I'd have gotten a photo with a filter on it. Cutting the chin off is what makes it look like a camera that didn't know it was recording you.

That's what a description gets you that copying never does. It finds the rule underneath.

Push back if it's vague. If it says "warm tones," ask warm how. Toward orange or toward yellow. If it says "high contrast," ask whether the blacks still have detail in them. You want it specific enough that you'd know if it was wrong.

3. Hand over your own photos

Now give it your pictures and ask it to apply one of the descriptions.

This is where I got told no, and I'm glad I was.

I asked it to use an AI image editor on my photos. I'd tried that a few months back on my headshots. What came back was a woman with my haircut, flat dead eyes, and a melted hand wrapped around a coffee mug. I put it on my homepage and looked at it and said, this is so bad.

Here's the thing I didn't know. Claude can look at a picture and tell you everything about it. It can't make one. There's no image generator inside it yet. So when I asked for one, it didn't pretend.

It wrote code instead.

Python that opens my actual photo file, works out where my face and the light really are, crops it, then adjusts the color. My real photograph goes in and my real photograph comes out, treated. Nothing is generated. Which is why I still look like me.

Before

Original photo of Christi in a denim jacket, sharp and in full color

After

The same photo cropped at the chin, motion blurred and graded warm gold
Same picture, taken years ago. The crop cuts my head off at the chin, so it's about the hands instead of my face. Then the color goes warm and a directional blur runs across the frame, like the camera moved. It's still my hands and my jacket. Nothing here was drawn by an AI.

The rule I'd give anyone: never point an AI image generator at a real person you care about, or at anything that's supposed to be a true record. A real photo that's a bit off for your layout beats a generated one that's perfect, every single time.

One thing worth asking for. Before it crops anything, have it measure the photo. Mine builds a version of the picture with a grid over it, reads off where the face sits, and crops from those numbers. When I let it guess instead, it put a crop in the wrong place four times in a row. Measuring took one try.

4. Tell it what's wrong

This is most of the work, and it's the part I'd have skipped a year ago. It feels like the project going badly. It's actually the project working.

Three things went wrong for me.

My kids' faces. I'd asked for them to be blurred out. What came back was a small child with a smeared-over face, and it looked like a horror movie. I said so. Now it crops them out of the frame instead. Their hands, their feet, a toy truck, the back of a head. Those turned out to be better pictures anyway.

The color was too yellow. I said that too. It went and looked at the account I'd been saving from, worked out that the palette is rust and cognac rather than olive green, and fixed the setting properly instead of nudging it.

It only made one of my favorite ones. I asked why. Turned out it had applied a rule from a different style where it didn't belong. It built three more.

Say what you don't like in normal words. "That's creepy" is a complete piece of feedback. Naming what's wrong is enough. Working out the fix is its job.

5. Save the setup as a skill

Everything above gets you good photos once. This step is what makes it yours.

A skill is a folder on your computer with a set of written instructions inside, plus any code that goes with it. Claude reads it before it starts working. You make one by asking:

Save all of this as a skill so I don't have to set it up again. Put the descriptions of each style in it, the code you wrote, and every correction I made today with the reason behind it.

That's it. It writes the folder.

Here's why it's the step that matters. A chat is gone tomorrow. Everything I explained, every correction, every "no, not like that," disappears when the conversation ends. Next month I'd start over and re-explain it to a version of Claude that had never met me.

A skill keeps it. Mine now holds these rules on its own:

I didn't have to write any of that down. I just had to notice it while it was happening and say it once when it happened.

What I actually ended up with

31 photos in. 35 finished images back, in 5 looks that all belong together:

Enough to rebuild the site, out of pictures that were already sitting on my hard drive.

And I still can't edit a photo.

The setup, if you want to run this yourself

All of this happened in Claude Code, which is Claude running in your terminal instead of a chat window. That's the part that matters. A chat window can't reach the photos on your hard drive. The terminal can, so Claude can open your actual files, write the code, run it, look at what came out, and fix it.

If the word terminal makes you want to close this tab, stay with me. You type a sentence in plain English and it does the work. You are not writing code. You're just working in the room where your files already live.

Where nano banana comes in

Nano banana is the nickname everyone uses for Google's image model. It's the thing that actually makes and edits pictures, and it's very good at props and texture: paper stock, tape, torn edges, backgrounds, objects on a desk.

You can try it in the Gemini app at gemini.google.com. To use it inside Claude Code you need a free API key from Google AI Studio. Google's own notes on it are here.

So the split in my setup is this. Claude reads my photos, writes the code, and runs it. Nano banana makes the paper and the tape. Nano banana never touches my face, or my kids' faces. Props and texture only. That rule came out of the melted hand.

Plugging one into the other

MCP stands for Model Context Protocol, and it's how Claude Code talks to outside tools. Think of it as a plug. Somebody writes the adapter once, you plug it in, and Claude can use that tool the same way it uses everything else it has.

The one I use is nanobanana-mcp. Download it and install its dependencies:

git clone https://github.com/charlesdove977/nanobanana-mcp
cd nanobanana-mcp
npm install

Then tell Claude Code it exists. One line, run from anywhere:

claude mcp add nano-banana \
  -e GEMINI_API_KEY=your-key-here \
  -- node /full/path/to/nanobanana-mcp/dist/index.js

Swap in your own key and your own path. Then open Claude Code and type /mcp to check it connected. Once it's in, you don't think about it again. You ask for a paper texture and you get one.

All free resources