Talk2DINOv3-ViTB

lorebianchi98/Talk2DINOv3-ViTB

Image Segmentation236M parametersPytorchLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
680
Total downloads
5,600
Gained 7D
+49(increase)
0.9%(up) vs baseline
Gained 30D
—
Likes
0
+0 in 7D
Rank · tracked models
#35,077
339(down 339 places)this week
Parameters
236M
Last source update
Oct 19, 2025
Momentum
29.4
  • Talk2DINOv3-ViTB gained 49 downloads during the last seven tracked days.
  • It moved from #155 to #157 among tracked Image Segmentation models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Talk2DINOv3-ViTB is a image segmentation model published by lorebianchi98. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Sep 22, 2026.

Published
Oct 15, 2025
Last updated
Oct 19, 2025
Library
Pytorch
License
apache-2.0
Task
Image Segmentation
Parameters
236,246,753
Spaces
1
Derivative models
—
Velocity 7D/day
7
Pytorchsafetensorstalk2dinomodel_hub_mixinpytorch_model_hub_mixinDINOv2CLIPopen-vocabulary segmentationimage-segmentationcustom_codearxiv:2411.19331license:apache-2.0

Similar models

Models similar to Talk2DINOv3-ViTB
ModelDL 30D
upernet-swin-largeopenmmlab26.1K
VRMBG-3.0briaai89
BiRefNetZhengPeng7971.1K
RMBG-2.0briaai613.8K
BiRefNet_HRZhengPeng749.5K
BiRefNet_HR-mattingZhengPeng736.3K
lorebianchi98/Talk2DINOv3-ViTB — Downloads, Growth & Stats | OpenModelStats