Image and video decision
Mirage — Detect Image Editing
A capable technical user can reproduce the core detection+undo workflow using open-source forensic and inpainting projects; building a minimal hosted replacement is realistic though it won't match the vendor's native iOS polish or app-store distribution.
View on the App Store↗Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off80 h to build
$250/mo6 h/mo upkeep
No published price to break even against.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Mirage — Detect Image Editing alternatives, with the arithmetic →
What a replacement has to do
- User uploads a face photo → forensic detector highlights edited regions → inpainting/undo runs to reconstruct pre-edit pixels → UI shows overlay and before/after compare
What it still won’t have
- Polished native iOS app and App Store distribution
- In-app purchase/subscription handling and existing paid-user base
- Certain creative features listed in the store (change hair style, emote images) unless separately implemented
- Any proprietary model or tuned dataset used by the vendor
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Mirage — Detect Image Editing does not publish a price we could read, so there is nothing to compare against. What building costs is below.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal web service (Python 3.10, Flask or FastAPI, Docker) that accepts an image upload and returns a forensic-edit mask and an inpainted "undo" image. Use GuidoBartoli/sherloq for forensic detection and HuggingFace diffusers for masked inpainting running on a GPU-enabled instance. Core features in scope: image upload + face-present validation, run sherloq to produce per-pixel edit mask and confidence, run diffusers masked inpainting to reconstruct masked regions, web UI with overlay and before/after toggle and download, containerized deployment (Dockerfile) to an AWS/GCP GPU VM. Out of scope: native iOS App Store bundling, paid subscription UI, advanced hairstyle/emote generation. Require robust error handling for invalid files, model failures and timeouts, basic unit/integration tests for upload→process→render flow, and documentation for deploying to a GPU instance.
How we checked
How the score was reached
- Build verdict base78
- An open-source build was found+5
- 3 cited sources+3
- Evidence score86
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 3
Every page the run actually retrieved.
- official productMirage - Detect Image Editing (App Store)
- open sourceGuidoBartoli/sherloq
- open sourcehuggingface/diffusers
Integrity checks
What held up, and what did not.
