docs: Unsloth-style KerasFormers model card for owlvit-base-patch32

README.md

@@ -1,21 +1,102 @@
 ---
 pipeline_tag: zero-shot-object-detection
 license: apache-2.0
+base_model: google/owlvit-base-patch32
 library_name: kerasformers
 tags:
 - keras
 - kerasformers
 - owlvit
-- tf
-- jax
+- open-vocabulary
+- zero-shot-object-detection
+- object-detection
+- arxiv:2205.06230
 - pytorch
+- jax
+- tf
 ---
 
-# owlvit-base-patch32 (Keras 3)
+## ***See [our collection](https://huggingface.co/collections/kerasformers/owl-vit-6a6a7af2bb61206cd50397ff) for all versions of OWL-ViT.***
+
+# Run OWL-ViT with Keras 3: JAX, PyTorch, or TensorFlow
+
+[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-black?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-OWL--ViT-blue)](https://imvision12.github.io/KerasFormers/owlvit/) [![Collection](https://img.shields.io/badge/HF-OWL--ViT%20collection-yellow)](https://huggingface.co/collections/kerasformers/owl-vit-6a6a7af2bb61206cd50397ff)
+
+# kerasformers/owlvit-base-patch32
+
+Paper: [Simple Open-Vocabulary Object Detection with Vision Transformers (arXiv:2205.06230)](https://arxiv.org/abs/2205.06230) · [HF Papers](https://huggingface.co/papers/2205.06230)
+
+OWL-ViT detects objects described by free text, with no fixed class list. It starts from a CLIP-style vision and text encoder, then drops CLIP's pooling and attaches a lightweight box head to every patch token. Each patch becomes a detection candidate, scored by cosine similarity against your text queries.
+
+For more details on the model, please go to Google's original [model card](https://huggingface.co/google/owlvit-base-patch32).
+
+Pure-**Keras 3** conversion of [`google/owlvit-base-patch32`](https://huggingface.co/google/owlvit-base-patch32) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
 
-Pure-Keras 3 weights for [kerasformers](https://github.com/IMvision12/KerasFormers), mirrored from the GitHub release. Apache 2.0.
+This is an **open-vocabulary object detection** checkpoint (`OwlViTDetect`): pass free-text prompts at inference time.
+
+## ✨ Quick start
 
 ```python
-from kerasformers.models.owlvit import OwlViTDetect
-model = OwlViTDetect.from_weights("owlvit-base-patch32")
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+from PIL import Image
+from kerasformers.models.owlvit import (
+    OwlViTDetect,
+    OwlViTProcessor,
+    OwlViTImageProcessor,
+)
+
+model = OwlViTDetect.from_weights("kerasformers/owlvit-base-patch32")
+processor = OwlViTProcessor.from_weights("kerasformers/owlvit-base-patch32")
+image_processor = OwlViTImageProcessor()
+
+image = Image.open("your_image.jpg").convert("RGB")
+prompts = ["a photo of a mug", "a photo of a knife"]
+inputs = processor(text=[prompts], images=image)
+output = model(
+    {
+        "input_ids": inputs["input_ids"],
+        "pixel_values": inputs["pixel_values"],
+    }
+)
+results = image_processor.post_process_object_detection(
+    output,
+    threshold=0.1,
+    target_sizes=[(image.height, image.width)],
+    text_labels=[prompts],
+)[0]
+for score, name, box in zip(
+    results["scores"], results["text_labels"], results["boxes"]
+):
+    print(f"{name}: {float(score):.3f} {box}")
 ```
+
+Load any OWL-ViT / OWLv2 variant the same way with `from_weights("kerasformers/<variant>")` (use `OwlViTDetect` for this repo):
+
+| Variant | Hub | Family |
+|---|---|---|
+| `owlvit-base-patch32` | [`kerasformers/owlvit-base-patch32`](https://huggingface.co/kerasformers/owlvit-base-patch32) | OWL-ViT |
+| `owlvit-base-patch16` | [`kerasformers/owlvit-base-patch16`](https://huggingface.co/kerasformers/owlvit-base-patch16) | OWL-ViT |
+| `owlvit-large-patch14` | [`kerasformers/owlvit-large-patch14`](https://huggingface.co/kerasformers/owlvit-large-patch14) | OWL-ViT |
+| `owlv2-base-patch16` | [`kerasformers/owlv2-base-patch16`](https://huggingface.co/kerasformers/owlv2-base-patch16) | OWLv2 |
+| `owlv2-base-patch16-ensemble` | [`kerasformers/owlv2-base-patch16-ensemble`](https://huggingface.co/kerasformers/owlv2-base-patch16-ensemble) | OWLv2 |
+| `owlv2-base-patch16-finetuned` | [`kerasformers/owlv2-base-patch16-finetuned`](https://huggingface.co/kerasformers/owlv2-base-patch16-finetuned) | OWLv2 |
+| `owlv2-large-patch14` | [`kerasformers/owlv2-large-patch14`](https://huggingface.co/kerasformers/owlv2-large-patch14) | OWLv2 |
+| `owlv2-large-patch14-ensemble` | [`kerasformers/owlv2-large-patch14-ensemble`](https://huggingface.co/kerasformers/owlv2-large-patch14-ensemble) | OWLv2 |
+| `owlv2-large-patch14-finetuned` | [`kerasformers/owlv2-large-patch14-finetuned`](https://huggingface.co/kerasformers/owlv2-large-patch14-finetuned) | OWLv2 |
+
+## Tips
+
+- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
+- Prefer `Processor.from_weights(...)` so image size matches the variant.
+- Open-vocab thresholds are often much lower than closed-set detectors (try `0.1`).
+- OWLv2 pads to square before resize; pass the original `(height, width)` as `target_sizes` carefully (see the OWLv2 docs for the padding trap).
+- See [OWL-ViT docs](https://imvision12.github.io/KerasFormers/owlvit/) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
+- Community / upstream safetensors still work via the `hf:` prefix, e.g. `OwlViTDetect.from_weights("hf:google/owlvit-base-patch32")`.
+
+## Special Thanks
+
+A huge thank you to the Google OWL-ViT authors for creating and releasing these models.
+
+License: Apache 2.0.