Florence-2

This model was released on 2024-06-16 and added to Hugging Face Transformers on 2025-08-20.

Florence-2

Overview

Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks. Florence-2 can interpret simple text prompts to perform tasks like captioning, object detection, and segmentation. It leverages the FLD-5B dataset, containing 5.4 billion annotations across 126 million images, to master multi-task learning. The model’s sequence-to-sequence architecture enables it to excel in both zero-shot and fine-tuned settings, proving to be a competitive vision foundation model.

You can find all the original Florence-2 checkpoints under the Florence-2 collection.

Tip

This model was contributed by ducviet00. Click on the Florence-2 models in the right sidebar for more examples of how to apply Florence-2 to different vision and language tasks.

The example below demonstrates how to perform object detection with Pipeline or the AutoModel class.

import torch
import requests
from PIL import Image
from transformers import pipeline

pipeline = pipeline(
    "image-text-to-text",
    model="florence-community/Florence-2-base",
    device=0,
    dtype=torch.bfloat16
)

pipeline(
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true",
    text="<OD>"
)

import torch
import requests
from PIL import Image
from transformers import AutoProcessor, Florence2ForConditionalGeneration

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")

model = Florence2ForConditionalGeneration.from_pretrained("florence-community/Florence-2-base", dtype=torch.bfloat16, device_map="auto")
processor = AutoProcessor.from_pretrained("florence-community/Florence-2-base")

task_prompt = "<OD>"
inputs = processor(text=task_prompt, images=image, return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **inputs,
    max_new_tokens=1024,
    num_beams=3,
)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]

image_size = image.size
parsed_answer = processor.post_process_generation(generated_text, task=task_prompt, image_size=image_size)
print(parsed_answer)

Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the Quantization overview for more available quantization backends.

The example below uses bitsandbytes to quantize the model to 4-bit.

# pip install bitsandbytes
import torch
import requests
from PIL import Image
from transformers import AutoProcessor, Florence2ForConditionalGeneration, BitsAndBytesConfig

quantization_config = BitsAndBytesConfig(load_in_4bit=True)

model = Florence2ForConditionalGeneration.from_pretrained(
    "florence-community/Florence-2-base",
    dtype=torch.bfloat16,
    device_map="auto",
    quantization_config=quantization_config
)
processor = AutoProcessor.from_pretrained("florence-community/Florence-2-base")

url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")

task_prompt = "<OD>"
inputs = processor(text=task_prompt, images=image, return_tensors="pt").to(model.device, torch.bfloat16)

generated_ids = model.generate(
    **inputs,
    max_new_tokens=1024,
    num_beams=3,
)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]

image_size = image.size
parsed_answer = processor.post_process_generation(generated_text, task=task_prompt, image_size=image_size)

print(parsed_answer)

Notes

• Florence-2 is a prompt-based model. You need to provide a task prompt to tell the model what to do. Supported tasks are:
  • <OCR>
  • <OCR_WITH_REGION>
  • <CAPTION>
  • <DETAILED_CAPTION>
  • <MORE_DETAILED_CAPTION>
  • <OD>
  • <DENSE_REGION_CAPTION>
  • <CAPTION_TO_PHRASE_GROUNDING>
  • <REFERRING_EXPRESSION_SEGMENTATION>
  • <REGION_TO_SEGMENTATION>
  • <OPEN_VOCABULARY_DETECTION>
  • <REGION_TO_CATEGORY>
  • <REGION_TO_DESCRIPTION>
  • <REGION_TO_OCR>
  • <REGION_PROPOSAL>
• The raw output of the model is a string that needs to be parsed. The Florence2Processor has a post_process_generation method that can parse the string into a more usable format, like bounding boxes and labels for object detection.

Resources

• Florence-2 technical report
• Jupyter Notebook for inference and visualization of Florence-2-large model

Florence2VisionConfig

[[autodoc]] Florence2VisionConfig

Florence2Config

[[autodoc]] Florence2Config

Florence2Processor

[[autodoc]] Florence2Processor

Florence2Model

[[autodoc]] Florence2Model - forward

Florence2ForConditionalGeneration

[[autodoc]] Florence2ForConditionalGeneration - forward

Florence2VisionBackbone

[[autodoc]] Florence2VisionBackbone - forward