Instructions to use MiaoshouAI/Florence-2-base-PromptGen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiaoshouAI/Florence-2-base-PromptGen with Transformers:

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

pipe = pipeline("image-text-to-text", model="MiaoshouAI/Florence-2-base-PromptGen", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("MiaoshouAI/Florence-2-base-PromptGen", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("MiaoshouAI/Florence-2-base-PromptGen", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MiaoshouAI/Florence-2-base-PromptGen with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MiaoshouAI/Florence-2-base-PromptGen

SGLang

How to use MiaoshouAI/Florence-2-base-PromptGen 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 "MiaoshouAI/Florence-2-base-PromptGen" \
    --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": "MiaoshouAI/Florence-2-base-PromptGen",
		"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 "MiaoshouAI/Florence-2-base-PromptGen" \
        --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": "MiaoshouAI/Florence-2-base-PromptGen",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MiaoshouAI/Florence-2-base-PromptGen with Docker Model Runner:
```
docker model run hf.co/MiaoshouAI/Florence-2-base-PromptGen
```

Very good model, but I've encountered an issue.

by JLGY - opened Jul 20, 2024

Discussion

JLGY

Jul 20, 2024

•

edited Jul 20, 2024

It seems to be a mix of WD tagger and natural language caption processing, and there's also a feature "named XXX who"...
Although most of the detections are incorrect,
it’s useful to use a script to replace them place.

However, I’ve found a problem: it’s easy for legs to be misinterpreted as "legs apart,"
for example, if the action is "crossed legs" but it gets detected as "legs apart."

I’m not sure why. If you use the original large model and WDtagger, it still detects "crossed legs."
It might be necessary to check how the dataset is constructed.

MiaoshouAI

Owner Jul 20, 2024

this could be a problem caused by inaccurate tags from civitai data. v1 is trained on new datasets so many of the problem mentioned should be improved in v1

pribadihcr

Aug 20, 2024

Hi, can you share the training dataset?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment