See our collection for all versions of TIPSv2.
Run TIPSv2 with Keras 3: JAX, PyTorch, or TensorFlow
zeromodels/tipsv2-l14
Paper: TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment (arXiv:2604.12012)
TIPSv2 (Google DeepMind) is a CLIP/SigLIP-style dual encoder: a DINOv2-style ViT vision tower with register tokens plus a bidirectional text tower, aligned with a temperature-scaled contrastive objective.
For more details on the model, please go to the upstream model card.
Pure-Keras 3 conversion of google/tipsv2-l14 for zeromodels. One implementation runs unmodified on TensorFlow / Torch / JAX. The full model and both towers load from this single repo.
✨ Quick start (zero-shot)
import os
os.environ["KERAS_BACKEND"] = "torch" # or "jax" / "tensorflow"
from PIL import Image
import numpy as np
import keras
from zeromodels.models.tipsv2 import Tipsv2Model, Tipsv2Processor
model = Tipsv2Model.from_weights("zeromodels/tipsv2-l14")
processor = Tipsv2Processor.from_weights("zeromodels/tipsv2-l14")
image = Image.open("your_image.jpg").convert("RGB")
texts = ["a photo of a cat", "a photo of a dog", "a photo of a car"]
inputs = processor(text=texts, images=np.array(image))
out = model(inputs)
probs = keras.ops.softmax(out["logits_per_image"], axis=-1)
print(keras.ops.convert_to_numpy(probs)[0])
Towers only:
from zeromodels.models.tipsv2 import Tipsv2VisionModel, Tipsv2TextModel
vision = Tipsv2VisionModel.from_weights("zeromodels/tipsv2-l14")
text = Tipsv2TextModel.from_weights("zeromodels/tipsv2-l14")
All TIPSv2 variants load the same way with from_weights("zeromodels/<variant>"):
| Variant | Hub |
|---|---|
tipsv2-b14 | zeromodels/tipsv2-b14 |
tipsv2-l14 | zeromodels/tipsv2-l14 |
tipsv2-so400m14 | zeromodels/tipsv2-so400m14 |
tipsv2-g14 | zeromodels/tipsv2-g14 |
Tips
- Set
KERAS_BACKENDbefore importing Keras / zeromodels. - The image processor rescales to
[0, 1](no mean/std normalization); input resolution is 448. - Upstream checkpoints:
Tipsv2Model.from_weights("hf:google/tipsv2-l14").
Special Thanks
A huge thank you to the TIPSv2 authors (Google DeepMind) and the HF community.
License: Apache-2.0 (matches the upstream google/tipsv2-l14 checkpoint).