tipsv2-so400m14-dpt

pip install transformers torch torchvision sentencepiece

from transformers import AutoModel
from torchvision import transforms
from PIL import Image
import requests

model = AutoModel.from_pretrained("google/tipsv2-so400m14-dpt", trust_remote_code=True)
model.eval().cuda()

url = "https://huggingface.co/spaces/google/tipsv2/resolve/main/examples/depth/ade20k_00014.png"
image = Image.open(requests.get(url, stream=True).raw)
transform = transforms.Compose([transforms.Resize((448, 448)), transforms.ToTensor()])
pixel_values = transform(image).unsqueeze(0).cuda()

# All tasks at once
outputs = model(pixel_values)
print(outputs.depth.shape)         # (1, 1, 448, 448) — depth map
print(outputs.normals.shape)       # (1, 3, 448, 448) — surface normals
print(outputs.segmentation.shape)  # (1, 150, 448, 448) — segmentation logits

# Or individual tasks (only runs the requested head)
depth = model.predict_depth(pixel_values)
normals = model.predict_normals(pixel_values)
seg = model.predict_segmentation(pixel_values)
print(seg.argmax(dim=1).shape)     # (1, 448, 448) — per-pixel class prediction

@inproceedings{cao2026tipsv2,
  title     = {{TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment}},
  author    = {Cao, Bingyi and Chen, Koert and Maninis, Kevis-Kokitsi and Chen, Kaifeng and Karpur, Arjun and Xia, Ye and Dua, Sahil and Dabral, Tanmaya and Han, Guangxing and Han, Bohyung and Ainslie, Joshua and Bewley, Alex and Jacob, Mithun and Wagner, Rene and Ramos, Washington and Choromanski, Krzysztof and Seyedhosseini, Mojtaba and Zhou, Howard and Araujo, Andre},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year      = {2026},
  url       = {https://arxiv.org/abs/2604.12012}
}