Tasks and inputs
LiheYoung/depth-anything-large-hf is listed for Depth estimation. It accepts image and produces depth map. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Oct 7, 2026
LiheYoung/depth-anything-large-hf is a source-linked Hugging Face repository assigned to Depth estimation. Its recorded task interface accepts image and produces depth map.
The specification score summarizes recorded features and limits. It is not a benchmark result.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
LiheYoung/depth-anything-large-hf is a Hugging Face repository returned by the public Depth estimation task feed. Its recorded download count is 389,826 and it has 65 likes when the repository snapshot was collected. Popularity is useful for discovery, but it is not a performance ranking or a guarantee of suitability.
This record is categorized for Depth estimation. A task category describes the intended machine-learning problem; it does not prove that every version, checkpoint, quantization, or deployment method produces the same quality. Teams should read the model card and test representative inputs before choosing it.
The public repository lists transformers as its library metadata. Its recorded tags include transformers, safetensors, depth_anything, depth-estimation, vision, arxiv:2401.10891, license:apache-2.0, endpoints_compatible. These source details are retained so readers can trace this directory entry back to the repository instead of relying on copied descriptions.
Check whether the output is relative or metric depth and whether scale is stable across scenes. Test indoor and outdoor examples, reflective surfaces and the downstream geometry pipeline.
The Hugging Face task assignment records image as input and depth map as output for LiheYoung/depth-anything-large-hf. This interface summary comes from the repository’s recorded Depth estimation task classification. It helps readers distinguish a text, image, audio, video, document, embedding, or prediction workflow without inferring undocumented API behavior. Model wrappers can expose different preprocessing and response formats, so verify the upstream model card and the exact runtime before deployment.
Explore LiheYoung models and the depth estimation collection. Use the comparison tool to inspect a second candidate.
Compare the model on the work you need to complete.
LiheYoung/depth-anything-large-hf is listed for Depth estimation. It accepts image and produces depth map. Use the publisher’s input format and preprocessing for your chosen deployment.
Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Apple
Hugging Face repository for Depth estimation.
Apple
apple/DepthPro-hf is a source-linked Hugging Face repository assigned to Depth estimation. Its recorded task interface accepts image and produces depth map.
depth-anything
depth-anything/DA3-GIANT is a source-linked Hugging Face repository assigned to Depth estimation. Its recorded task interface accepts image and produces depth map.
depth-anything
depth-anything/DA3-GIANT-1.1 is a source-linked Hugging Face repository assigned to Depth estimation. Its recorded task interface accepts image and produces depth map.
depth-anything
depth-anything/DA3-LARGE is a source-linked Hugging Face repository assigned to Depth estimation. Its recorded task interface accepts image and produces depth map.
depth-anything
depth-anything/DA3-LARGE-1.1 is a source-linked Hugging Face repository assigned to Depth estimation. Its recorded task interface accepts image and produces depth map.