Models tagged "image-segmentation"

🤖 Model 🖼️ → 📝

bytedance/sa2va-26b-image

Segment objects and regions in images from natural-language instructions and answer visual questions. Takes an image and...

🖼️ → 📝 • image-segmentation • image-to-text • 6.3K runs

🤖 Model 🖼️ → 📝

bytedance/sa2va-8b-image

Segment objects and answer questions from an input image using natural-language instructions. Provide an image and an in...

🖼️ → 📝 • image-segmentation • image-to-text • 17.4K runs

🤖 Model 🖼️ → 📝

bytedance/sa2va-4b-image

Segment objects in images from a text instruction, returning a segmentation overlay image and a textual response. Suppor...

🖼️ → 📝 • image-segmentation • image-to-text • 53 runs

🤖 Model 🖼️

jimothyjohn/nanosam

Segment objects in images from a bounding box prompt. Provide an image plus bounding box coordinates (x0, y0, x1, y1) an...

🖼️ • image-segmentation • 49 runs

🤖 Model 🖼️

peter65374/sam-vit

Encode images using the SAM (Segment Anything) ViT-H model, which is designed for image segmentation tasks.

🖼️ • image-segmentation • vit • image-encoding • 358.0K runs

🤖 Model 🖼️

tmappdev/lang-segment-anything

Segment objects and regions in images using natural-language prompts. Input an image and a text prompt; output a segment...

🖼️ • image-segmentation • 1.7M runs

🤖 Model 🖼️

hadilq/hair-segment

Segment hair in photos. Takes an input image and returns a hair segmentation result as a mask or overlaid image, enablin...

🖼️ • image-segmentation • hair-segmentation • 503 runs

🤖 Model 🖼️

ahmdyassr/mask-clothing

Segment clothing and faces in images and return binary mask images. Accepts a single image input and outputs masks for a...

🖼️ • image-segmentation • clothing-segmentation • face-segmentation • 35.9K runs

🤖 Model 🖼️

naklecha/clothing-segmentation

Segment clothing in images, isolating topwear or bottomwear. Accepts an image and a clothing category (topwear or bottom...

🖼️ • image-segmentation • clothing-segmentation • 3.7K runs

🤖 Model 🖼️

pengdaqian2020/unet-clothing-segment

Segment clothing in images. Accepts an image and outputs a mask image isolating garment regions, with a selector to targ...

🖼️ • image-segmentation • clothing-segmentation • 873 runs

🤖 Model 🖼️

asyasyarif/ootd_masking

Segment clothing in outfit photos and generate clean masks for the selected garment piece (top or bottom). Accepts an im...

🖼️ • image-segmentation • background-removal • 150 runs

🤖 Model 🖼️

medicapture/seg-model

Segment the pelvis in hip X-ray images and return a per-pixel probability map and mask. Performs binary semantic segment...

🖼️ • image-segmentation • medical-imaging • x-ray • 312 runs

🤖 Model 🖼️

hassamdevsy/mask2former

Segment images into per-pixel ADE20K categories using Mask2Former, returning a color-coded segmentation map and a list o...

🖼️ • image-segmentation • scene-parsing • panoptic-segmentation • 57.9K runs

🤖 Model 🖼️

wzesk/littoral_segment

Segment islands and coastlines in images. Takes a single image as input and outputs a segmentation mask highlighting lit...

🖼️ • image-segmentation • remote-sensing • geospatial • 19 runs

🤖 Model 🖼️ → 🖼️

wzesk/littoral_refine

Refine satellite-derived shoreline masks from an image and a corresponding mask, then output a cleaned shoreline visuali...

🖼️ → 🖼️ • image-to-image • image-segmentation • remote-sensing • 5 runs

🤖 Model 🖼️

hcl14/omnipart

Reconstruct part-aware 3D assets from a single image. Generate whole and exploded meshes, per-part bounding-box visualiz...

🖼️ • image-to-3d • image-segmentation • 64 runs

🤖 Model 🖼️

suket-shubhankar/road_marker_model

Segment roads in images. Accepts a single image and outputs an image with road regions highlighted as a segmentation mas...

🖼️ • image-segmentation • road-segmentation • 14 runs

🤖 Model 🖼️

lhungting-ship-it/card-glare-detection

Detect glare regions on card photos and return a pixel-level segmentation mask. Input: an image containing a card; Outpu...

🖼️ • image-segmentation • glare-detection • 7 runs

🤖 Model 🖼️

lucataco/dis-background-removal

Remove backgrounds from images. Accepts an image and uses ECCV 2022 Dichotomous Image Segmentation (DIS) to segment the...

🖼️ • background-removal • image-segmentation • 285 runs

🤖 Model

catacolabs/dis-background-removal

Remove backgrounds from images. Accepts a single image input and returns a foreground cutout with a transparent backgrou...

background-removal • 70 runs