DepthCrafter is not named as a product on any of the candidate sources, so no page confirms it directly. The closest matches for depth estimation are Replicate's hosted Depth Anything v2 model 717 and NVIDIA's Depth Anything v2 and FoundationStereo training actions 212, which estimate depth from images.
A question back: Did you mean a specific depth-estimation model or platform (for example Depth Anything v2 on Replicate or NVIDIA TAO), or do you need a video depth tool? DepthCrafter itself is not listed in these sou
- 1
- 2
NVIDIA TAOnvidia.comverified and signed
Provides tao-train-depth-anything-v2 for monocular depth estimation from a single RGB image and stereo depth models for disparity maps 212.
+81 community tools built for it
for agents: tao-train-depth-anything-v2 · tao-train-fast-foundation-stereo · tao-train-foundation-stereo
Sources
- 2Brev.dev Consolebrev.nvidia.com · read 2026-10-29
- 7Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 12tao-train-depth-anything-v2: declares "tao-train-depth-anything-v2" (the record we read and signed)unfragile.ai · read 2026-10-24
- 17chenxwh/depth-anything-v2: declares "chenxwh/depth-anything-v2" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
automate-this · automate-this verified and signed
Analyze a screen recording of a manual process and produce targeted, working automation scripts. Extracts frames and audio narration from video files, reconstructs the step-by-step workflow, and proposes automation at multiple complexity levels using tools already installed on the user machine.
tao-train-depth-anything-v2 · tao-train-depth-anything-v2 verified and signed
Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from single RGB images. Use when training, evaluating, exporting, or running inference for a TAO monocular depth model. Trigger phrases include "train monocular depth", "Depth
python · fastcore verified and signed
· Research website read, tools not yet checked
Discover Google Research. We publish research papers across a wide range of domains and share our latest developments in AI and science research.
stream-videos-retrieve-video-details · Cloudflare API verified and signed
Retrieve video details
ask_deepseek · DeepSeek (Activepieces) verified and signed
Ask Deepseek — Ask Deepseek anything you want!
chenxwh/depth-anything-v2 · chenxwh/depth-anything-v2 verified and signed
Depth estimation with faster inference speed, fewer parameters, and higher depth accuracy.
cjwbw/zoedepth · cjwbw/zoedepth verified and signed
ZoeDepth: Combining relative and metric depth
issue-maker · issue-maker verified and signed
Create GitHub issues following Pollinations team conventions. Use when asked to create issues, track work, or plan features.
getVideoModelInfo · Runware MCP Server found in code, not yet checked
Get detailed information about a specific video model including supported dimensions.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.