depth-estimation AI Models

🤖 Model

cjwbw/zoedepth

Estimate monocular depth from a single input image and output a dense depth map. Combine relative and metric depth; sele...

depth-estimation • 4.6M runs

🤖 Model 🎥

vufinder/vggt-1b

Reconstruct 3D scene geometry from images or video. Accepts one or more images or a video and returns per-frame depth ma...

🎥 • image-to-3d • video-to-3d • depth-estimation • 3.1K runs

🤖 Model 🖼️

vufinder/vggt-1b-point

Reconstruct 3D point clouds and scene geometry from single images, image sets, or video. Takes images or a video as inpu...

🖼️ • image-to-3d • depth-estimation • camera-pose-estimation • 714 runs

🤖 Model 🎥

vufinder/vggt-1b-depth

Estimate depth and reconstruct 3D point clouds from single images or videos. Accepts one or more images or a video and r...

🎥 • depth-estimation • image-to-3d • video-to-3d • 63 runs

🤖 Model

kjjk10/lotus-diffusion-dense-prediction

Estimates depth from a single image and returns a depth map visualization. Uses the Lotus diffusion model trained in dis...

depth-estimation • 980 runs

🤖 Model

chenxwh/depth-anything-v2

Estimate monocular depth from a single image, returning colorized and grayscale depth maps. Choose Small, Base, or Large...

depth-estimation • 314.1K runs

🤖 Model

cjwbw/midas

Estimate per-pixel depth from a single image and return a dense grayscale relative depth map. Leverage MiDaS with DPT ba...

depth-estimation • 730.6K runs

🤖 Model

ibrahimpenekli/depth-pro

Estimate per-pixel metric depth from a single image. Takes an RGB image (optionally a known focal length) and returns a...

depth-estimation • focal-length-estimation • 311 runs

🤖 Model 🎥

chenxwh/depth-any-video

Estimate temporally consistent per-pixel depth from an input video. Accepts an image or a video and outputs a depth-map...

🎥 • depth-estimation • video-to-video • 227 runs

🤖 Model

cjwbw/depth-anything

Estimate per-pixel depth from a single image. Accepts an image and returns a dense grayscale depth map (relative monocul...

depth-estimation • 12.8K runs

🤖 Model

aiunivers/openpose

Estimate human pose from an input image and output an OpenPose-style pose map image. Optionally include facial landmarks...

pose-estimation • depth-estimation • openpose • 433 runs

🤖 Model 🖼️ → 🖼️

arielreplicate/crestereo

Estimate dense depth from a stereo pair of rectified images. Takes left and right images and outputs a per-pixel dispari...

🖼️ → 🖼️ • depth-estimation • image-to-image • 790 runs

🤖 Model

zedge/zoedepth

Estimate per-pixel depth from a single image and output a grayscale depth map. Perform monocular depth estimation for AR...

depth-estimation • 3.7M runs

🤖 Model 🖼️

jasonod888/moge2

Estimate 3D geometry from a single RGB image. Takes an image input and outputs a depth map (EXR + preview), surface norm...

🖼️ • depth-estimation • image-to-3d • camera-calibration • 1 runs

🤖 Model

fofr/controlnet-preprocessors

Generate ControlNet conditioning maps from an input image. Run multiple preprocessors simultaneously and return images f...

controlnet-preprocessor • pose-estimation • depth-estimation • 42.5K runs

🤖 Model 📝 → 🖼️

qwen/qwen-image

Generates images from text prompts with exceptional text rendering capabilities, particularly excelling at complex multi...

📝 → 🖼️ • text-to-image • image-to-image • image-editing • 2.0M runs

🤖 Model 🖼️ → 🖼️

adirik/t2i-adapter-sdxl-depth-midas

Generates images using input images as depth map guides combined with text prompts. Uses a T2I-Adapter with Stable Diffu...

🖼️ → 🖼️ • image-to-image • depth-estimation • 667.1K runs

🤖 Model 📝 → 🖼️

stspanho/illusion

Creates optical illusion images from text prompts by incorporating depth information. Can generate QR codes with artisti...

📝 → 🖼️ • text-to-image • image-to-image • depth-estimation • 340 runs