PaliGemma 2 | Roboflow Docs

PaliGemma 2 is Google's vision-language model. It accepts an image and a text prompt and returns a text response. We support PaliGemma 2 through our Serverless Cloud API, Dedicated Deployments, and self-hosted Inference.

PaliGemma 2 API

Get your API Key

Create a Roboflow account, find your key on the Roboflow API settings page and make it available to your shell:

export ROBOFLOW_API_KEY="your-key-here"

Install the dependencies

Install the Inference SDK:

pip install -U inference-sdk supervision

Run the model

The sample calls the pretrained paligemma2-3b-pt-224 checkpoint with a caption prompt.

import os
import supervision as sv
from inference_sdk import InferenceHTTPClient

image = sv.load_image_from_url("https://media.roboflow.com/quickstart/dog.jpeg")

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.environ["ROBOFLOW_API_KEY"],
)
result = client.infer_lmm(
    image,
    model_id="paligemma2-3b-pt-224",
    prompt="caption en",
    max_new_tokens=64,
)
print(result["response"])

The code above prints the model response to the terminal:

a dog is seen here on the shoulder of a man

PaliGemma 2 inference speed

Latency measured with Roboflow Inference on 1x NVIDIA L4, batch size 1, generating exactly 128 tokens with greedy decoding from a fixed prompt. Latency scales with output length, so use tokens/sec to estimate other lengths.

Alias	Latency, 128 tokens (ms)	Tokens/sec
`paligemma2-3b-pt-224`	3986	32

Set api_url to match your deployment target:

https://serverless.roboflow.com for the Serverless Cloud API.
http://localhost:9001 for a local Inference server.
Your Dedicated Deployment URL for a private endpoint.

You can train your own PaliGemma 2 checkpoint on Roboflow and call it by its per-model {workspace}/{model-slug} ID (see Versions, Trainings, and Models). See the Inference documentation for additional prompt formats and supported checkpoints.

PaliGemma 1 (legacy)

The original PaliGemma release is still loadable through the inference package on your own hardware. New projects should use PaliGemma 2 above; this section is kept for existing integrations.

Install the package:

pip install "inference[transformers]"

Use inference-gpu[transformers] on a GPU machine.

Visual question answering

from PIL import Image

from inference.models.paligemma.paligemma import PaliGemma

model = PaliGemma("paligemma-3b-mix-224", api_key="YOUR_API_KEY")

image = Image.open("image.jpeg")
result = model.predict(image, "How many dogs are in this image?")

print(result)

Object detection

PaliGemma emits detections as <loc####> tokens rather than JSON, so the response has to be parsed before it can be visualized. Prompt with detect <class>; <class> and decode the tokens into boxes:

import re
from typing import List, Optional, Tuple

import numpy as np
import supervision as sv

_DETECT_RE = re.compile(r"(.*?)" + r"<loc(\d{4})>" * 4 + r"\s*([^;<>]+)? ?(?:; )?")


def from_pali_gemma(
    response: str,
    resolution_wh: Tuple[int, int],
    class_list: Optional[List[str]] = None,
) -> sv.Detections:
    width, height = resolution_wh
    xyxy_list, class_name_list = [], []

    while response:
        match = _DETECT_RE.match(response)
        if not match:
            break

        groups = list(match.groups())
        before = groups.pop(0)
        name = groups.pop()
        y1, x1, y2, x2 = [int(value) / 1024 for value in groups[:4]]
        y1, x1, y2, x2 = map(round, (y1 * height, x1 * width, y2 * height, x2 * width))

        content = match.group()
        if before:
            response = response[len(before):]
            content = content[len(before):]

        xyxy_list.append([x1, y1, x2, y2])
        class_name_list.append(name.strip())
        response = response[len(content):]

    class_name = np.array(class_name_list)
    class_id = (
        np.array([class_list.index(name) for name in class_name])
        if class_list is not None
        else None
    )
    return sv.Detections(
        xyxy=np.array(xyxy_list),
        class_id=class_id,
        data={"class_name": class_name},
    )


classes = ["person", "car", "backpack"]
response = model.predict(image, "detect person; car; backpack")[0]
detections = from_pali_gemma(response, resolution_wh=image.size, class_list=classes)

Pass the resulting sv.Detections to supervision annotators to draw the boxes.