Star on GitHubPost your photos & videos without the AI label.
Nothing is uploaded, cleaned in-browser. How it works · Guides
Clean your images and videos
Select images or videos
Images · MP4 · MOV · WebM
Why does a platform add an AI label to my photo or video?
One possible trigger is what is written inside the file, not only what appears on screen. When media passes through an AI tool — Midjourney, DALL·E, Gemini, Firefly, Stable Diffusion, or even a single Generative Fill stroke in Photoshop — the tool may write provenance records into the file: a signed C2PA manifest, an XMP packet naming the generator, IPTC attribution fields, or container metadata. Platforms may read those records on upload.
That is why real photography gets labelled too. AI Denoise in Lightroom, an AI background removal, an AI sky replacement or a CapCut export all leave the same markers behind, and the automatic labeller cannot tell a one-click cleanup from fully synthetic media. Cleaning removes file-level metadata triggers, but platforms may also use watermarks, classifiers and their own records.
Instagram
“AI info” or “AI content”
Facebook
“AI info” or “Made with AI”
TikTok
“AI-generated”
Pinterest
GenAI badge
A free, ad-free AI label remover for photos and videos
No login, trial counter, subscription or advertising wall stands between you and the download. The focused interface handles images and videos in the same queue, shows which AI marker was detected, and inspects the cleaned result again before reporting that a marker was removed.
Processing happens in your browser tab. Your media is never posted to an application upload endpoint, stored in an account or handed to an advertising network. You get lossless cleaning where the format permits it, including video stream copying that avoids quality-reducing recompression.
What gets removed
C2PA content credentials
A signed provenance manifest that tools such as Firefly, ChatGPT Image, Gemini and Photoshop may embed for machine-readable creation and edit history.
XMP packets
Generator names, prompts, seeds, sampler settings and edit history, including the digitalSourceType tag that declares an image as trainedAlgorithmicMedia.
EXIF & GPS
Camera make and model, lens, software field, device serial numbers, capture timestamps and the GPS coordinates that can point at your home address.
IPTC attribution
The Adobe and agency attribution fields that carry credit, source and AI-disclosure strings alongside copyright data.
PNG text chunks
tEXt, iTXt and zTXt chunks in which Stable Diffusion, Automatic1111, Forge and ComfyUI store the full generation workflow.
Video container metadata
Lossless video remuxing leaves source tags, chapters, attached thumbnails, extra streams and container provenance records behind without recompressing video or audio.
How to clean AI metadata, step by step
- 1
Drop your media
The photo or video is read into browser memory with the File API. Its contents are not sent to an upload endpoint.
- 2
Inspect what is inside
Images are inspected on the spot for C2PA, XMP, EXIF, IPTC and PNG-chunk records. Videos begin a local WebAssembly remuxing job.
- 3
Clean without quality loss
JPG, PNG and WebP metadata is stripped without recompression. Video and audio streams are copied into a clean container without re-encoding.
- 4
Download and post
You get a cleaned image or video download with original visual and audio quality. File-level metadata is removed, but watermarks and classifier signals may remain.
Want the technical detail — segment by segment, chunk by chunk? Read how it works or browse our metadata guides.
Frequently asked questions
What this tool cannot do
It cannot remove an invisible watermark embedded in image pixels, video frames or audio, it cannot change how a classifier reads the content, and it cannot lift a label from a post that is already published. It also does not replace disclosure where a platform’s terms or a law such as the EU AI Act require it. Full detail on the page, and on .