zeromodels / depth_anything_v2_base

huggingface.co
Total runs: 37
24-hour runs: 3
7-day runs: -16
30-day runs: -553
Model's Last Updated: August 27 2026
depth-estimation

Introduction of depth_anything_v2_base

Model Details of depth_anything_v2_base

See our collection for all versions of Depth Anything V2.

Run Depth Anything V2 with Keras 3: JAX, PyTorch, or TensorFlow

GitHub Docs Collection

kerasformers/depth_anything_v2_base

Paper: Depth Anything V2 (arXiv:2406.09414) · HF Papers

Depth Anything V2 keeps V1's architecture and improves data (synthetic labels plus large-scale pseudo-labeling). Relative heads return unitless inverse depth; metric indoor/outdoor heads return metres.

For more details on the model, please go to the upstream model card .

Pure- Keras 3 conversion of depth-anything/Depth-Anything-V2-Base-hf for kerasformers . One implementation runs unmodified on TensorFlow / Torch / JAX .

This is a monocular depth checkpoint ( DepthAnythingV2DepthEstimation , relative).

✨ Quick start
import os
os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

from PIL import Image
from kerasformers.models.depth_anything_v2 import DepthAnythingV2DepthEstimation, DepthAnythingV2ImageProcessor

model = DepthAnythingV2DepthEstimation.from_weights("kerasformers/depth_anything_v2_base")
processor = DepthAnythingV2ImageProcessor.from_weights("kerasformers/depth_anything_v2_base")

image = Image.open("your_image.jpg").convert("RGB")
output = model(processor(image)["pixel_values"], training=False)
depth = processor.post_process_depth_estimation(
    output, original_size=(image.height, image.width)
)
print(depth.shape)

Load any Depth Anything V2 variant the same way with from_weights("kerasformers/<variant>") :

Variant Hub Output
depth_anything_v2_small kerasformers/depth_anything_v2_small relative
depth_anything_v2_base kerasformers/depth_anything_v2_base relative
depth_anything_v2_large kerasformers/depth_anything_v2_large relative
depth_anything_v2_metric_indoor_small kerasformers/depth_anything_v2_metric_indoor_small metric indoor
depth_anything_v2_metric_indoor_base kerasformers/depth_anything_v2_metric_indoor_base metric indoor
depth_anything_v2_metric_indoor_large kerasformers/depth_anything_v2_metric_indoor_large metric indoor
depth_anything_v2_metric_outdoor_small kerasformers/depth_anything_v2_metric_outdoor_small metric outdoor
depth_anything_v2_metric_outdoor_base kerasformers/depth_anything_v2_metric_outdoor_base metric outdoor
depth_anything_v2_metric_outdoor_large kerasformers/depth_anything_v2_metric_outdoor_large metric outdoor
Tips
  • Set KERAS_BACKEND before importing Keras / kerasformers.
  • Indoor and outdoor metric heads are not interchangeable.
  • See Depth Anything V2 docs and Loading Weights .
  • Community / upstream weights: DepthAnythingV2DepthEstimation.from_weights("hf:depth-anything/Depth-Anything-V2-Base-hf") .
Special Thanks

A huge thank you to the Depth Anything authors for creating and releasing these models.

License: Apache 2.0.

Runs of zeromodels depth_anything_v2_base on huggingface.co

37
Total runs
3
24-hour runs
-15
3-day runs
-16
7-day runs
-553
30-day runs

More Information About depth_anything_v2_base huggingface.co Model

More depth_anything_v2_base license Visit here:

https://choosealicense.com/licenses/cc-by-nc-4.0

depth_anything_v2_base huggingface.co

depth_anything_v2_base huggingface.co is an AI model on huggingface.co that provides depth_anything_v2_base's model effect (), which can be used instantly with this zeromodels depth_anything_v2_base model. huggingface.co supports a free trial of the depth_anything_v2_base model, and also provides paid use of the depth_anything_v2_base. Support call depth_anything_v2_base model through api, including Node.js, Python, http.

depth_anything_v2_base huggingface.co Url

https://huggingface.co/zeromodels/depth_anything_v2_base

zeromodels depth_anything_v2_base online free

depth_anything_v2_base huggingface.co is an online trial and call api platform, which integrates depth_anything_v2_base's modeling effects, including api services, and provides a free online trial of depth_anything_v2_base, you can try depth_anything_v2_base online for free by clicking the link below.

zeromodels depth_anything_v2_base online free url in huggingface.co:

https://huggingface.co/zeromodels/depth_anything_v2_base

depth_anything_v2_base install

depth_anything_v2_base is an open source model from GitHub that offers a free installation service, and any user can find depth_anything_v2_base on GitHub to install. At the same time, huggingface.co provides the effect of depth_anything_v2_base install, users can directly use depth_anything_v2_base installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

depth_anything_v2_base install url in huggingface.co:

https://huggingface.co/zeromodels/depth_anything_v2_base

Url of depth_anything_v2_base

depth_anything_v2_base huggingface.co Url

Provider of depth_anything_v2_base huggingface.co

zeromodels
ORGANIZATIONS

Other API from zeromodels