|
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
library_name: transformers
|
|
pipeline_tag: image-text-to-text
|
|
tags:
|
|
- art
|
|
base_model: microsoft/Florence-2-large
|
|
datasets:
|
|
- kadirnar/fluxdev_controlnet_16k
|
|
---
|
|
|
|
```
|
|
pip install -q datasets flash_attn timm einops
|
|
```
|
|
|
|
```python
|
|
|
|
from transformers import AutoModelForCausalLM, AutoProcessor, AutoConfig
|
|
import torch
|
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("gokaygokay/Florence-2-Flux-Large", trust_remote_code=True).to(device).eval()
|
|
processor = AutoProcessor.from_pretrained("gokaygokay/Florence-2-Flux-Large", trust_remote_code=True)
|
|
|
|
# Function to run the model on an example
|
|
def run_example(task_prompt, text_input, image):
|
|
prompt = task_prompt + text_input
|
|
|
|
# Ensure the image is in RGB mode
|
|
if image.mode != "RGB":
|
|
image = image.convert("RGB")
|
|
|
|
inputs = processor(text=prompt, images=image, return_tensors="pt").to(device)
|
|
generated_ids = model.generate(
|
|
input_ids=inputs["input_ids"],
|
|
pixel_values=inputs["pixel_values"],
|
|
max_new_tokens=1024,
|
|
num_beams=3,
|
|
repetition_penalty=1.10,
|
|
)
|
|
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
|
|
parsed_answer = processor.post_process_generation(generated_text, task=task_prompt, image_size=(image.width, image.height))
|
|
return parsed_answer
|
|
|
|
from PIL import Image
|
|
import requests
|
|
import copy
|
|
|
|
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)
|
|
answer = run_example("<DESCRIPTION>", "Describe this image in great detail.", image)
|
|
|
|
final_answer = answer["<DESCRIPTION>"]
|
|
print(final_answer)
|
|
|
|
``` |
