Instructions to use remyxai/PoseFlorence-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use remyxai/PoseFlorence-2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="remyxai/PoseFlorence-2", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("remyxai/PoseFlorence-2", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("remyxai/PoseFlorence-2", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use remyxai/PoseFlorence-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "remyxai/PoseFlorence-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "remyxai/PoseFlorence-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/remyxai/PoseFlorence-2

SGLang

How to use remyxai/PoseFlorence-2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "remyxai/PoseFlorence-2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "remyxai/PoseFlorence-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "remyxai/PoseFlorence-2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "remyxai/PoseFlorence-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use remyxai/PoseFlorence-2 with Docker Model Runner:
```
docker model run hf.co/remyxai/PoseFlorence-2
```

Model Card for PoseFlorence-2

This model fine-tunes Florence-2-base-ft in the POSE task for body keypoint estimation using the PoseText Dataset.

Running PoseFlorence-2

import requests

import torch
from PIL import Image
from transformers import AutoProcessor, AutoModelForCausalLM 


device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model = AutoModelForCausalLM.from_pretrained("remyxai/PoseeFlorence-2", trust_remote_code=True).to(device)
processor = AutoProcessor.from_pretrained("remyxai/PoseFlorence-2", trust_remote_code=True)

prompt = "<POSE>"

url = "https://remyx.ai/assets/spatialvlm/warehouse_rgb.jpg?download=true"
image = Image.open(requests.get(url, stream=True).raw)

inputs = processor(text=prompt, images=image, return_tensors="pt").to(device, torch_dtype)

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

parsed_answer = processor.post_process_generation(generated_text, task=prompt, image_size=(image.width, image.height))

print(parsed_answer)