More free image tools
Same quality bar. Still free. Still no upload.
Your files never leave your device
This is not a promise about how carefully we handle your upload. There is no upload. The file you choose is read into memory by your own browser, processed there, and handed back as a download — the tool has no server component and makes no network request with your data.
- Nothing is stored. We never receive the file, so there is no copy to retain, no retention period to disclose, and nothing to delete on request.
- Nothing is transmitted. No upload endpoint, no analytics payload carrying file contents, no third-party processor.
- You can verify it. Load this page, disconnect from the internet, and use the tool. It still works, because everything it needs is already on your machine.
- Nothing persists after you close the tab. Files are held in page memory only — not in local storage, not in a cache, not in a database.
A note on wording, because it matters: we do not describe these tools as “encrypted.” Encryption protects data that travels to somebody else's computer. Your file does not travel, so there is nothing to encrypt and nothing to intercept — which is a stronger guarantee than encryption, not a weaker one. The page itself is served over HTTPS like the rest of the site.
This makes the tools safe for material you are contractually barred from uploading to third-party services — client footage under NDA, unreleased campaign assets, anything covered by a confidentiality clause.
How it works
1. Drop a still photo
PNG, JPEG or WebP. Video is out of scope. The file is read in this tab only.
2. Estimate relative depth
Distill-Any-Depth Base ONNX runs on WebGPU fp16 (~188 MB first download) or WASM q8 (~97.5 MB). Optional q4f16 (~71 MB) if WebGPU runs out of memory. Weights cache in the browser; your photo is never sent.
3. Download depth or fake DoF
Export a normalized grayscale depth PNG (near=white or near=black). Adjust focus plane and blur for a fake depth-of-field preview. Stack blur is not a real camera lens.
Questions
Does this upload my photo?
No. Inference runs in your browser. The only network fetch is the model weights from Hugging Face on first use (WebGPU fp16 is 196,847,178 bytes / about 188 MB; WASM q8 is 102,212,799 bytes / about 97.5 MB; low-memory WebGPU q4f16 is 74,764,381 bytes / about 71 MB). Your image is never attached to that request. Later runs reuse the browser cache.
Is the depth map metric (metres)?
No. This is relative monocular depth from a single still. Values are normalized for display (near vs far), not LiDAR, stereo, or MagicPlan measurements. Do not use it for surveying, room plans, or safety-critical distance.
What model and license do you use?
We ship the MIT-licensed ONNX conversion Ko033/distill-any-depth-base-onnx (Distill-Any-Depth Base, ViT-B, architecture compatible with Depth Anything V2 DPT 518). It converts Distill Any Depth / He et al. 2025; the original GitHub is MIT. The Hugging Face card on xingyang1 also lists apache-2.0 for related weights. We disclose both: this tool uses the MIT ONNX conversion and credits the paper.
What is the fake depth-of-field?
A canvas stack-blur that blurs pixels more as their relative depth diverges from the focus plane. It is a fake circle of confusion for previews, not optical bokeh from a real lens. Quality is honest and limited; hair, thin structures and specular edges will look soft or smeared.
Will it work in Safari?
Depth can fall back to WASM q8 when WebGPU is missing or fails. Safari WebGPU support varies by version and may OOM on large stills; try a smaller image or another Chromium-based browser if fp16 fails. The tool will attempt q4f16 (~71 MB) on WebGPU out-of-memory when possible.
Do my files get uploaded anywhere?
No. This free tool runs entirely in your browser using the Canvas and File APIs. The file you choose is read into memory on your own machine, processed there, and offered back as a download. Nothing is sent to a server, which is also why it keeps working with your network off.
Is it actually free, or is there a catch?
Actually free, with no account and no limit, because it costs nothing to run. The work happens on your device rather than on our hardware. That is different from generating with an AI model on Versely, which does cost credits. There is no free tier for generation.
Related tools
Stay in the same job cluster. Free tools stay on-device; paid tools are labelled as such.
These rearrange files. Versely makes new ones.
Everything on this page works on a file you already have, which is why it costs nothing. Generating something that did not exist (video from a prompt, a voice, a score) runs a model, and that costs credits.