Free · No sign up for your first image

Add a Ghost to a Photo, Online and Free
Change what you want. Keep what matters.

Choose a ghost and where it should stand — doorway, window, mirror, stairs — and the AI paints it into your photo with matching light and grain. The people in it stay untouched. First photo free, no account.

No sign up No added visible watermark Auto-delete in 24h Never used for training

Choose a ghost, then say where it stands

1Upload image
2Choose change
3Generate
Step 1 · Add your image
Drop your image here
Drag & drop, paste, or choose from your device
Upload image
JPGPNGWebP≤ 10 MB
Private · auto-deleted in 24h

No photo handy? Try a sample

What do you want to change?

Pick one direction. Hold Frame will protect the important parts automatically.

We’ll detect what matters after you upload, then protect it automatically.
2 Choose one you can refine it below
Advanced settings Optional
Detected mode after upload
Keep protected recommended for this image
Change strength
Balanced — clear change, identity and layout stay stable.
Aspect ratio

✦ 1 free result as a guest · failed generations never count

Real before & after

A ghost is added where you ask; the people stay pixel-for-pixel the same

Examples use AI-generated people, not real ones. The people in each result are the original upload's pixels.

The control other tools hide

You don't pick a model. You pick what survives.

Most img2img tools give you one abstract “strength” slider. We turn it into decisions a human actually makes.

Keep — hard constraints

Locked items become explicit model instructions — and a region mask when you paint one. The AI regenerates the whole image using your photo as the reference, so compare locked details with the original before you publish.

  • Face — it's still the same person. Identity reference plus face-region protection.
  • Subject — the product, pet or object keeps its shape, logo and key details.
  • Composition — pose and layout stay put via structure and depth control.
  • Text & Logo — the model is told to keep lettering and logos as they are; fine print can still change, so check it.

Change — creative freedom

One tap per intent. Each chip compiles into a structured instruction with the right negative constraints.

  • Style — anime, watercolor, film, 3D, oil paint and 40+ more.
  • Background — a new scene behind an untouched subject.
  • Outfit — swap clothing while the person stays the person.
  • Lighting — golden hour, studio, neon night, overcast.

Subtle

Light touch: tone, light, small edits. Routed to precise editing models.

Balanced

The default. Obvious change with stable identity and layout.

Creative

Big reimagining. Structure loosens — fine details may drift, on purpose.

Three steps

From photo to finished image in under a minute

Upload & auto-detect

Drop any JPG, PNG or WebP. We recognize portraits, products, sketches and interiors, and pre-lock what usually matters for that kind of image.

Lock, describe, set strength

Toggle what to keep, tap what to change, pick Subtle, Balanced or Creative. No denoising values, no seed numbers, no model menus.

Compare, download, iterate

Slide before/after, download free with no added visible watermark, then keep editing the result with plain language — no re-upload needed.

One-tap starts

Prompt templates that fill the tool for you

Tap any template — it configures keep, change and strength, then scrolls you back to the studio.

Complete guide

How to add a ghost to a photo

Pick a ghost, then tell it where to stand. The AI only paints the scene behind the people — the ghost, its shadow and the light around it — and Keep subject pixels exactly pastes the original people back, so nobody's face, hair or clothes change.

In short

To add a ghost to a photo online, upload the photo to Hold Frame, tap one of six ghosts — long-hair ghost, shadow figure, Victorian lady, face in the window, cute sheet ghost or orbs & mist — and say where it should stand, for example 'in the doorway on the left' or 'in the mirror'. The AI paints the ghost into the scene with the photo's own lighting, colour, grain and perspective, instead of pasting a flat sticker on top. Keep subject pixels exactly (on by default) cuts the people out in your browser and puts their original pixels back, so they don't change at all. It's an AI ghost photo editor for a fake ghost photo prank or a Halloween post, with no app. Your first photo is free with no sign-up and no added watermark; after that it's $2.90 per photo, 3 for $6.90 or 5 for $9.90, one-time with no subscription. People also search for it as add ghost to photo, add ghost to photo online free, add ghost to photo AI, add fake ghost to photo, add ghost to picture.

Facts checked October 10, 2026.

Add Ghost to Photo: what you get

Free to tryFirst ghost photo free as a guest — no sign-up, no credit card, no app download. Failed generations don't count.
After the free photo$2.90 for one photo, $6.90 for three (most popular) or $9.90 for five — one-time, no subscription, no account needed to pay. Existing Hold Frame credits work too (5 per photo).
WatermarkNo visible watermark is added. The model provider's invisible provenance mark (SynthID) is not removed.
Original pixels kept?For background changes, yes: with "Keep subject pixels exactly" (on by default for product photos, one tick for people) the original product or person is cut out in your browser and pasted back pixel-for-pixel; only the background is AI — same price. Other edits are regenerated by the image model (Google Gemini 3.1 Flash Image) with your photo as the reference, so compare locked details.
Best forQuick, controlled edits from one photo when you want to try several directions before committing.
Not the right tool forPixel-exact compositing (use layer masks in Photoshop) or editing dozens of images in one batch.

What you can make

A fake ghost photo prank

Send a 'look what I caught on camera' photo to friends or family.

Haunted house photos

Add a figure at a window or on the stairs of a house, a hallway or a party photo.

Halloween posts and invites

A ghost in the background of an ordinary photo makes an instant Halloween post or invite.

How to get a controlled result

A three-step workflow for Add Ghost to Photo

Pick a photo with a place for the ghost

A doorway, window, mirror, staircase or dark corner works best.

Choose the ghost and the spot

Tap a ghost card, then add where it stands, e.g. 'in the mirror' or 'on the stairs'.

Review the edge

Keep subject pixels exactly pastes the people back; check fine hair at the edges.

Prompt examples

Copy one as a starting point, then change only the details that matter to your image.

  1. add a faint, semi-transparent Victorian ghost lady in a high-collared white dress, standing at the far end of the room and looking at the camera; place it in the background behind the person, partly hidden by them, at a believable size and distance; match the room's lighting, colour, grain and perspective so it looks like it was really in the photo; no blood or gore; do not change the person

Common problems and fixes

Use these checks before increasing change strength or adding more instructions.

The ghost is in the wrong place. Name the spot in plain words — 'in the doorway on the left', 'behind the man on the right'.
It looks too obvious. Add 'make it subtler, easy to miss' or 'more see-through' — the best fake ghost photos are noticed late.
The ghost covers a person. Keep subject pixels exactly on: the original people are always pasted back on top of the ghost.
The engine declined the photo. Some photos are declined by the safety checks. Declined or failed generations don't use your free try or a paid photo.

Private by default

Your images and results are never public. No gallery, no indexable links.

Auto-delete in 24h

Anonymous uploads and results are wiped within 24 hours, automatically.

Never trained on

We don't use your uploads to train models. Not opt-out — it just doesn't happen.

Delete instantly

One click removes the source and every result. Download links die with it.

Simple pricing

A free first photo. Then one-time packs, no subscription.

Your first photo is free. After that: $2.90 for one photo, $6.90 for three (most popular) or $9.90 for five — one-time, no subscription, no account needed to pay. Failed or declined generations are refunded. Existing Hold Frame credits work too (5 per photo).

Compare all credit plans and usage costs

Loading prices…

Subscriptions renew monthly and add credits after each successful payment. Packs are one-time purchases, available with or without a subscription. Unused credits carry over and remain after cancellation. No automatic pack purchases.

Honest limits

What AI still gets wrong — and what we do about it

No “100% accurate” promises. Here's the truth, and the workaround.

Faces can drift at Creative strength. If it stops looking like you, drop to Balanced or Subtle — Face lock works hardest there.
Hands and fingers remain the hardest thing in AI imaging. Keep them out of the change region when you can.
Tiny text and fine logos may blur or change. Turn on Text & Logo lock and compare them against the original before publishing.
Complex textures like lace, fur or micro-patterns can simplify. Subtle strength preserves them best.
Big scene swaps can nudge edges of the composition. Lock Composition and expect minor boundary shifts, not layout changes.
Failed generations happen. Timeouts and moderation blocks are labeled clearly and never consume your free quota.
FAQ

Questions, answered straight

Upload your photo, tap a ghost card, optionally say where it should stand, and generate. Your first photo is free with no sign-up and no added visible watermark.

The ghost is generated into the scene with the photo's own lighting, grain and perspective, and the people are pasted back over it, so it sits behind them like it was really there.

Yes. Add a place to the description — 'in the doorway on the left', 'in the mirror', 'on the stairs', 'outside the window' — or tap one of the suggestions.

No. Keep subject pixels exactly is on by default: the people are cut out in your browser and their original pixels are pasted back.

$2.90 per photo, 3 for $6.90 or 5 for $9.90 — one-time, no subscription. Failed or declined generations are refunded.

No app needed. It runs in the browser on iPhone, Android and desktop.

Only with their permission. Sexual or violent content is declined.

No. Uploads are processed to make the result and are not used to train models.