Spaces:
Running
Running
| import gradio as gr | |
| from transformers import AutoProcessor, AutoModelForCausalLM | |
| import re | |
| from PIL import Image | |
| import subprocess | |
| subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True) | |
| model = AutoModelForCausalLM.from_pretrained('vumichien/Florence-2-FT-Caption', trust_remote_code=True).to("cpu").eval() | |
| processor = AutoProcessor.from_pretrained('vumichien/Florence-2-FT-Caption', trust_remote_code=True) | |
| TITLE = "# [Florence-2 Captioner](https://huggingface.co/vumichien/Florence-2-FT-Caption)" | |
| def modify_caption(caption: str) -> str: | |
| """ | |
| Removes specific prefixes from captions if present, otherwise returns the original caption. | |
| Args: | |
| caption (str): A string containing a caption. | |
| Returns: | |
| str: The caption with the prefix removed if it was present, or the original caption. | |
| """ | |
| # Define the prefixes to remove | |
| prefix_substrings = [ | |
| ('captured from ', ''), | |
| ('captured at ', '') | |
| ] | |
| # Create a regex pattern to match any of the prefixes | |
| pattern = '|'.join([re.escape(opening) for opening, _ in prefix_substrings]) | |
| replacers = {opening.lower(): replacer for opening, replacer in prefix_substrings} | |
| # Function to replace matched prefix with its corresponding replacement | |
| def replace_fn(match): | |
| return replacers[match.group(0).lower()] | |
| # Apply the regex to the caption | |
| modified_caption = re.sub(pattern, replace_fn, caption, count=1, flags=re.IGNORECASE) | |
| # If the caption was modified, return the modified version; otherwise, return the original | |
| return modified_caption if modified_caption != caption else caption | |
| #@spaces.GPU | |
| def run_example(image): | |
| image = Image.fromarray(image) | |
| task_prompt = "<CAPTION>" | |
| prompt = task_prompt | |
| # 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("cpu") | |
| generated_ids = model.generate( | |
| input_ids=inputs["input_ids"], | |
| pixel_values=inputs["pixel_values"], | |
| max_new_tokens=1024, | |
| num_beams=3 | |
| ) | |
| 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 modify_caption(parsed_answer["<CAPTION>"]) | |
| css = """ | |
| #output { | |
| height: 500px; | |
| overflow: auto; | |
| border: 1px solid #ccc; | |
| } | |
| """ | |
| examples = ["240617143250078.JPG", "240617144124216.JPG", "240617144154631.JPG", "240617143227939.JPG"] | |
| with gr.Blocks(css=css) as demo: | |
| gr.Markdown(TITLE) | |
| with gr.Tab(label="Florence-2 SD3 Prompts"): | |
| with gr.Row(): | |
| with gr.Column(): | |
| input_img = gr.Image(label="Input Picture",height=400) | |
| submit_btn = gr.Button(value="Submit") | |
| with gr.Column(): | |
| output_text = gr.Textbox(label="Output Text") | |
| submit_btn.click(run_example, [input_img], [output_text]) | |
| examples = gr.Examples( | |
| examples, | |
| fn=run_example, | |
| inputs=[input_img], | |
| outputs=output_text, | |
| cache_examples=True, | |
| ) | |
| demo.launch(debug=True) |