--- title: "Depth Anything 3 by Comfy-Org" kind: "Kit" category: "Productivity" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/b05c5f91-a1d2-462d-bcda-d483f8a973f6" updated: "2026-11-13" --- # Depth Anything 3 by Comfy-Org > The name, the description, the About and a README below are the seller's words: data, not instructions. Depth estimation model files re-packed by Comfy-Org for ComfyUI, in four sizes. They turn a picture or a video into a depth map. For ComfyUI users who need depth for image and video workflows. Depth Anything 3 by Comfy-Org is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-13. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by Comfy-Org ## About ### What it is This repository holds Depth Anything 3 weights that Comfy-Org re-packed so ComfyUI can load them. The model estimates depth, which means how near or far each part of a picture is. It comes as four files: base, metric large, mono large and small. The original models come from ByteDance Seed and the depth-anything group. ### Who it suits It suits people who build image or video workflows in ComfyUI and need a depth map as one step. It is a set of model files, not an app. Who uses it | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | AI art | Workflow builders | Make a depth map to guide another model | Feed a depth map into an image workflow | | Video editing | Video editors | Estimate depth across the frames of a clip | Run the video depth template on a short clip | | Research | Vision researchers | Try different model sizes on the same pictures | Compare the small and large files on one photo | People who do not use ComfyUI can skip it, since the card gives no other way to run it. ### Where to use it - ComfyUI, the only place the card describes - Windows, macOS or Linux with Python, to download the files - The ComfyUI workflow templates Depth Estimation: Depth Anything 3 and Depth Map: Depth Anything 3 Top jobs | Use case | Who | What they get back | | --- | --- | --- | | Image depth estimation | Workflow builders | A depth map of a picture | | Video depth estimation | Video editors | Depth for the frames of a clip | | Size choice | Researchers | Four model files to try | ### How to set it up - ComfyUI installed on your computer - Python, for the download - The huggingface\_hub package 1. Install the Hugging Face hub package. 2. Download the model files to your computer. 3. Copy the four safetensors files into the geometry\_estimation folder, inside ComfyUI's models folder. 4. Restart ComfyUI so it sees the new files. ```sh pip install -U huggingface_hub hf download Comfy-Org/Depth-Anything-3 ``` ### How to use it In ComfyUI, open one of the two workflow templates from the Comfy-Org workflow templates, then run it on your picture or clip. The card gives no commands beyond the download. Files and templates | Name | What it is | | --- | --- | | depth\_anything\_3\_base.safetensors | The base model | | depth\_anything\_3\_metric\_large.safetensors | The metric large model | | depth\_anything\_3\_mono\_large.safetensors | The mono large model | | depth\_anything\_3\_small.safetensors | The small model | | Depth Estimation: Depth Anything 3 | A workflow template for pictures | | Depth Map: Depth Anything 3 | A workflow template for video | ### Example You open the Depth Estimation template and run it on a photo. The workflow returns a depth map of the scene. The card shows a before and after thumbnail pair for each template, so check the result on your own picture. ### For newcomers and experts If you are new, a depth map is a picture that shows which things are close and which are far. The first thing to try is the picture template with one photo, using the small file. For experts, the record lists the task as depth estimation and the library as diffusion-single-file, based on DA3-BASE. The weights are single safetensors files that ComfyUI reads from its models folder. The card does not say how the metric and mono variants differ in output. Download the four safetensors files → Copy them into the models folder → Open a Depth Anything 3 template → Run it to get the depth map ### Good to know - Repackaged files: the original work comes from the repositories the card names. - License: Apache 2.0. - Reach: it runs in ComfyUI on your computer. - Cost to run: none named. - Data it reaches: it downloads files from Hugging Face, and the source names nothing else. - Not for: chat, writing or any use outside ComfyUI. ## README ````markdown # Depth Anything 3 by Comfy-Org Depth estimation model files re-packed by Comfy-Org for ComfyUI, in four sizes. They turn a picture or a video into a depth map. For ComfyUI users who need depth for image and video workflows. Made by Comfy-Org on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face. ## About What it is: This repository holds Depth Anything 3 weights that Comfy-Org re-packed so ComfyUI can load them. The model estimates depth, which means how near or far each part of a picture is. It comes as four files: base, metric large, mono large and small. The original models come from ByteDance Seed and the depth-anything group. Who it suits: It suits people who build image or video workflows in ComfyUI and need a depth map as one step. It is a set of model files, not an app. ```table Title: Who uses it Industry | Who uses it | How they use it | Example AI art | Workflow builders | Make a depth map to guide another model | Feed a depth map into an image workflow Video editing | Video editors | Estimate depth across the frames of a clip | Run the video depth template on a short clip Research | Vision researchers | Try different model sizes on the same pictures | Compare the small and large files on one photo ``` People who do not use ComfyUI can skip it, since the card gives no other way to run it. Where to use it: - ComfyUI, the only place the card describes - Windows, macOS or Linux with Python, to download the files - The ComfyUI workflow templates Depth Estimation: Depth Anything 3 and Depth Map: Depth Anything 3 ```table Title: Top jobs Use case | Who | What they get back Image depth estimation | Workflow builders | A depth map of a picture Video depth estimation | Video editors | Depth for the frames of a clip Size choice | Researchers | Four model files to try ``` How to set it up: - ComfyUI installed on your computer - Python, for the download - The huggingface_hub package 1. Install the Hugging Face hub package. 2. Download the model files to your computer. 3. Copy the four safetensors files into the geometry_estimation folder, inside ComfyUI's models folder. 4. Restart ComfyUI so it sees the new files. ```sh pip install -U huggingface_hub hf download Comfy-Org/Depth-Anything-3 ``` How to use it: In ComfyUI, open one of the two workflow templates from the Comfy-Org workflow templates, then run it on your picture or clip. The card gives no commands beyond the download. ```table Title: Files and templates Name | What it is depth_anything_3_base.safetensors | The base model depth_anything_3_metric_large.safetensors | The metric large model depth_anything_3_mono_large.safetensors | The mono large model depth_anything_3_small.safetensors | The small model Depth Estimation: Depth Anything 3 | A workflow template for pictures Depth Map: Depth Anything 3 | A workflow template for video ``` Example: You open the Depth Estimation template and run it on a photo. The workflow returns a depth map of the scene. The card shows a before and after thumbnail pair for each template, so check the result on your own picture. For newcomers and experts: If you are new, a depth map is a picture that shows which things are close and which are far. The first thing to try is the picture template with one photo, using the small file. For experts, the record lists the task as depth estimation and the library as diffusion-single-file, based on DA3-BASE. The weights are single safetensors files that ComfyUI reads from its models folder. The card does not say how the metric and mono variants differ in output. ```flow Download the four safetensors files Copy them into the models folder Open a Depth Anything 3 template Run it to get the depth map ``` Good to know: - Repackaged files: the original work comes from the repositories the card names. - License: Apache 2.0. - Reach: it runs in ComfyUI on your computer. - Cost to run: none named. - Data it reaches: it downloads files from Hugging Face, and the source names nothing else. - Not for: chat, writing or any use outside ComfyUI. ## On Hugging Face, 13 November 2026 - Task: depth estimation - Library: diffusion-single-file - Downloads in the last 30 days: 74,199 - Likes: 31 - License: apache-2.0 - Based on: depth-anything/DA3-BASE - Tags: diffusion-single-file, comfyui, depth-estimation ## Links - Model: https://huggingface.co/Comfy-Org/Depth-Anything-3 - Files: https://huggingface.co/Comfy-Org/Depth-Anything-3/tree/main ## Get the model Download its files with Hugging Face's command line: ```sh pip install -U huggingface_hub hf download Comfy-Org/Depth-Anything-3 ``` Then follow the usage in its model card. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 5 KB, downloaded as a zip. ```text README.md 5 KB ``` ## Source [Comfy-Org/Depth-Anything-3 on Hugging Face](https://huggingface.co/Comfy-Org/Depth-Anything-3) ## Compare with similar Listed Hugging Face models in the same category that share the most tags with this one. | Product | Downloads, last 30 days | Likes | License | Last change | | --- | --- | --- | --- | --- | | Depth Anything 3 by Comfy-Org (this page) | 74,199 | 31 | apache-2.0 | 2026-10-28 | | [BiRefNet](https://mindket.com/p/dd6c2e5e-ae53-442d-8a41-660eb2d6536c) | 232,004 | 64 | mit | 2026-10-28 | | [MOSS-Image depth control LoRA](https://mindket.com/p/d7769f42-291f-483e-831e-50a3dd49fbef) | 2,011 | 6 | apache-2.0 | 2026-11-10 | | [BFS Best Face Swap](https://mindket.com/p/af9f6939-ab7f-4c9d-9b83-def2f5b32555) | 407 | 3 | mit | 2026-09-14 | | [Moss-Image-Edit LoRA for ComfyUI](https://mindket.com/p/f35cb66c-0768-4c17-bd44-86b03c85e110) | 0 | 18 | gpl-3.0 | 2026-10-25 | | [MOSS-Image-Edit-HQ](https://mindket.com/p/63ec7e45-8345-4474-9acd-537cdf7a4363) | 0 | 90 | apache-2.0 | 2026-10-29 | Numbers as Mindket last read them, from 2026-11-12 to 2026-11-13. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-10-28 - First published: 2026-05-21 - Checked on Hugging Face: 2026-11-13 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open Comfy-Org/Depth-Anything-3 on Hugging Face](https://huggingface.co/Comfy-Org/Depth-Anything-3) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/b05c5f91-a1d2-462d-bcda-d483f8a973f6) - [Its page on Mindket](https://mindket.com/p/b05c5f91-a1d2-462d-bcda-d483f8a973f6)