PricingSave big
DEPTH ANYTHING · VIDEO

Video Depth Anything: turn footage into depth maps

Video Depth Anything is the video model of the Depth Anything family, built on Depth Anything V2 by the same research team. Upload a clip and it estimates a depth map for every frame - grayscale or a color map - that stays steady from the first second to the last. Available now in Picsart's AI Playground.

Generate depth map
Video
Upload a video to turn into a depth map...

Depth maps made with Video Depth Anything

Video Depth Anything sample output (placeholder creative)
Video Depth Anything sample output (placeholder creative)
Video Depth Anything sample output (placeholder creative)
WHAT IS DEPTH ANYTHING

What is Video Depth Anything?

Video Depth Anything is a depth estimation model from the research team behind Depth Anything V2, presented as a CVPR 2025 highlight. It reads your footage and estimates how far every pixel sits from the camera, producing a depth map for each frame - the same data that drives depth-of-field, fog, relighting, and 3D-style effects in professional pipelines.

Generate depth map
  • Bring your own video
  • A depth map for every frame
  • Keep editing in Picsart
A video frame next to its depth map (placeholder creative)
NO FLICKER

Consistent from first frame to last

Per-frame depth models tend to shimmer: values jump between frames, and any effect built on them crawls. Video Depth Anything was built around temporal consistency - depth stays stable across the whole clip, and the model handles footage several minutes long without drifting. Its faster variants run in real time at 30 frames per second.

Generate depth map
Stable depth across consecutive frames (placeholder creative)
TWO WAYS TO READ DEPTH

Grayscale or a color map - your pick

Choose the output that fits your pipeline: a grayscale map where bright pixels sit close to the camera and dark ones fall away, or a color-coded map that makes depth bands easy to read at a glance. Either way you get one map per frame, ready to drive masks, grades, and composites.

Generate depth map
Grayscale and color depth map outputs side by side (placeholder creative)
INSIDE AI PLAYGROUND

Video Depth Anything in Picsart AI Playground

Video Depth Anything lives in Picsart's AI Playground alongside 150+ other AI models, so you can turn footage into depth maps and keep building on the result right next to your other creative tools - no third-party API keys or separate subscriptions. Reach it whichever way you work: on the web, in the desktop app, and via CLI, MCP, REST API, and SDK, so a depth pass you prototype here drops straight into an automated pipeline.

Generate depth map
Video Depth Anything inside Picsart AI Playground (placeholder creative)

What you can do with Video Depth Anything

Three ways to put frame-by-frame depth to work.
Depth-of-field effect driven by a depth map (placeholder creative)

  • Use the depth pass to blur by distance, pull focus to your subject, or add fog and haze that sits naturally behind it.

    Generate depth map

How to make a depth map from video

Upload a clip, pick your output, generate the depth pass, and use it in your edit.

How to

Upload your video

Open Video Depth Anything in Picsart AI Playground and add the clip you want to map.

Step 1: Uploading a video (placeholder creative)

Video Depth Anything FAQ

Answers about turning video into depth maps in Picsart.

  • Video Depth Anything is a depth estimation model from the research team behind Depth Anything V2, presented as a CVPR 2025 highlight. It turns a video into a frame-by-frame depth map while keeping depth consistent across the whole clip.

Pricing

Try a few depth passes or build a repeatable workflow for effects, grading, and composites.

Pro

Most popular

AI tools for everyday creative work.

$15 $10.5/mo
Billed yearly
You save $54 with yearly
  • Access to all photo & video editing features
  • Advanced background & object removal
  • Parallel video generations with the world's most powerful AI video models
  • Unlimited image generations with Flex.2 Klein
  • 1-tap image enhancer
  • Millions of stock photos & Getty video clips
  • Selection of trendy fonts, text styles & stickers
  • Thousands of premium templates
  • Support for 3+ brand kits
  • Bulk edit up to 50 images at once
  • 100 GB of cloud storage
New features:
  • Auto-generate content from your terminal or agent with the Picsart CLI
  • Use Picsart inside Claude Code, Cursor, and ChatGPT via MCP — coming soon
  • AI agents for multi-step workflows and batch generation — coming soon

Ultra

Most powerful

Heavy AI usage for creators & teams.

$45 $24.5/mo
Billed yearly, per seat
You save $246 with yearly
  • Everything in Pro
  • Early access to advanced AI features
  • Leading AI models to design & automate workflows (Nano Banana, Veo 3, Seedance 2.0 & more)
  • Parallel video generations with the world's most powerful AI video models
  • Unlimited image generations with Flex.2 Klein
  • Support for 10+ brand kits
  • Add team seats
  • Create ad variations and localize
  • Track ads performance
  • 2000 credits for API services
  • Bulk edit up to 100 images at once
  • 300 GB of cloud storage per seat
New features:
  • Auto-generate content from your terminal or agent with the Picsart CLI
  • Use Picsart inside Claude Code, Cursor, and ChatGPT via MCP — coming soon
  • AI agents for multi-step workflows and batch generation — coming soon