Anything2Real is a dedicated LoRA model built on Qwen Edit 2509, capable of transforming any art style (illustrations, anime, cartoons, paintings, etc.) into realistic images while preserving the original composition and content.

Computer VisionDiffusers

SAM-HQ is an enhanced version of the Segment Anything Model (SAM), capable of generating higher-quality object masks, especially suitable for handling objects with complex structures.

Computer VisionTransformers

SAM-HQ is an enhanced version of the Segment Anything Model (SAM), capable of generating higher-quality object masks from input prompts such as points or boxes.

Computer VisionTransformers

SAM-HQ is an enhanced version of Segment Anything Model, generating higher-quality object masks through input prompts like points or boxes

Computer VisionTransformers

Prompt Depth Anything is a high-resolution and accurate metric depth estimation method that unleashes the potential of depth foundation models through prompting, capable of generating precise metric depth at up to 4K resolution.

Computer VisionTransformers

Prompt Depth Anything is a high-resolution and precise metric depth estimation method that employs a prompt mechanism to unleash the potential of depth foundation models.

Computer VisionSafetensors

This is a powerful text-image interleaved input-output model, deeply aligned through the Align Anything algorithm, improving image generation capabilities and human preference alignment.

MultimodalTransformersEnglish

A fine-tuned version of Depth Anything V2 for indoor metric depth estimation using the synthetic Hypersim dataset, compatible with the transformers library.

Computer VisionTransformers

A version fine-tuned for indoor metric depth estimation tasks using the Hypersim synthetic dataset, based on the Depth Anything V2 model

Computer VisionTransformers

A model fine-tuned from Depth Anything V2 for indoor metric depth estimation tasks, trained on the synthetic dataset Hypersim, compatible with the transformers library.

Computer VisionTransformers

A fine-tuned version of Depth Anything V2, specifically designed for metric depth estimation in outdoor scenes, trained on the synthetic dataset Virtual KITTI.

Computer VisionTransformers

A fine-tuned version of Depth Anything V2 for outdoor metric depth estimation tasks, trained on the synthetic dataset Virtual KITTI

Computer VisionTransformers

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, offering finer details and stronger robustness.

Computer VisionTransformers

Depth Anything V2 is currently the most powerful Monocular Depth Estimation (MDE) model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, offering finer details and stronger robustness.

Computer VisionTransformers

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, offering finer details and stronger robustness.

Computer VisionTransformers

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, featuring fine details and robustness.

Computer VisionTransformers

Depth Anything V2 is a depth estimation model based on the DPT architecture, utilizing a DINOv2 backbone network. It achieves fine and robust depth prediction through training on large-scale synthetic and real-world data.

Computer VisionCoreml

ONNX version of Depth Anything V2 Small, designed for Transformers.js, intended for monocular depth estimation tasks.

Computer VisionTransformers

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on a large amount of synthetic and real images, providing fine depth details and high robustness.

Depth Anything V2 is currently the most powerful monocular depth estimation (MDE) model, trained on 595,000 synthetically annotated images and over 62 million real unannotated images.