Spaces:
Build error
Build error
File size: 1,673 Bytes
339d456 9404648 339d456 9404648 339d456 0473518 97fa256 9404648 0473518 09ccbce 9404648 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 |
import gradio as gr
import subprocess
import torch
from PIL import Image
from transformers import AutoProcessor, AutoModelForCausalLM
# Install flash-attn library
subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
# Initialize Florence model
device = "cuda" if torch.cuda.is_available() else "cpu"
florence_model = AutoModelForCausalLM.from_pretrained('microsoft/Florence-2-base', trust_remote_code=True).to(device).eval()
florence_processor = AutoProcessor.from_pretrained('microsoft/Florence-2-base', trust_remote_code=True)
def generate_caption(image):
if not isinstance(image, Image.Image):
image = Image.fromarray(image)
inputs = florence_processor(text="<MORE_DETAILED_CAPTION>", images=image, return_tensors="pt").to(device)
generated_ids = florence_model.generate(
input_ids=inputs["input_ids"],
pixel_values=inputs["pixel_values"],
max_new_tokens=1024,
early_stopping=False,
do_sample=False,
num_beams=3,
)
generated_text = florence_processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
parsed_answer = florence_processor.post_process_generation(
generated_text,
task="<MORE_DETAILED_CAPTION>",
image_size=(image.width, image.height)
)
prompt = parsed_answer["<MORE_DETAILED_CAPTION>"]
print("\n\nGeneration completed!:" + prompt)
return prompt
# Gradio interface
io = gr.Interface(
generate_caption,
inputs=[gr.Image(label="Input Image")],
outputs=[gr.Textbox(label="Output Prompt", lines=2, show_copy_button=True)]
)
io.launch(debug=True)
|