Spaces:
Running
Running
File size: 6,165 Bytes
d8a9fb0 c59606b |
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 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 |
import streamlit as st
from PIL import Image, ImageDraw, ImageFont
import io
import cv2
import numpy as np
import easyocr
import os
from dotenv import load_dotenv
import requests
import logging
# Load environment variables
load_dotenv()
# Set up logging
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger(__name__)
# Hugging Face API setup
API_URL = "https://api-inference.huggingface.co/models/black-forest-labs/FLUX.1-schnell"
HF_TOKEN = os.getenv("HF_TOKEN")
headers = {"Authorization": f"Bearer {HF_TOKEN}"}
def load_image(image_file):
img = Image.open(image_file)
return img
def detect_text(image):
reader = easyocr.Reader(['en'])
img_array = np.array(image)
results = reader.readtext(img_array)
return [(text, box) for (box, text, _) in results]
def replace_text_in_image(image, text_to_replace, new_text):
img_array = np.array(image)
for (text, box) in detect_text(image):
if text == text_to_replace:
x, y, w, h = int(box[0][0]), int(box[0][1]), int(box[2][0] - box[0][0]), int(box[2][1] - box[0][1])
mask = np.zeros(img_array.shape[:2], dtype=np.uint8)
cv2.rectangle(mask, (x, y), (x+w, y+h), 255, -1)
img_array = cv2.inpaint(img_array, mask, 3, cv2.INPAINT_TELEA)
image = Image.fromarray(img_array)
draw = ImageDraw.Draw(image)
font = ImageFont.truetype("arial.ttf", 40)
draw.text((x, y), new_text, font=font, fill="#000000")
return image
return Image.fromarray(img_array)
def query(payload):
try:
response = requests.post(API_URL, headers=headers, json=payload)
response.raise_for_status()
logger.debug(f"API response status code: {response.status_code}")
logger.debug(f"API response headers: {response.headers}")
content_type = response.headers.get('Content-Type', '')
if 'application/json' in content_type:
return response.json()
elif 'image' in content_type:
return response.content
else:
logger.error(f"Unexpected content type: {content_type}")
st.error(f"Unexpected content type: {content_type}")
return None
except requests.exceptions.RequestException as e:
logger.error(f"Request failed: {str(e)}")
st.error(f"Request failed: {str(e)}")
return None
def increase_image_quality(image, scale_factor):
width, height = image.size
new_size = (width * scale_factor, height * scale_factor)
return image.resize(new_size, Image.LANCZOS)
def image_text_replacer():
st.header("Image Text Replacer")
uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
if uploaded_file is not None:
image = load_image(uploaded_file)
st.image(image, caption='Uploaded Image', use_column_width=True)
text_results = detect_text(image)
st.subheader("Detected Text:")
edited_image = image.copy()
for i, (text, box) in enumerate(text_results):
if text.strip(): # Only process non-empty text
st.text(f"{i+1}. {text}")
new_text = st.text_input(f"Enter new text for '{text}':", value=text, key=f"new_text_{i}")
if st.button(f"Replace '{text}'", key=f"replace_{i}"):
edited_image = replace_text_in_image(edited_image, text, new_text)
st.image(edited_image, caption='Edited Image', use_column_width=True)
# Provide download option for the edited image
buf = io.BytesIO()
edited_image.save(buf, format="PNG")
byte_im = buf.getvalue()
st.download_button(
label="Download edited image",
data=byte_im,
file_name="edited_image.png",
mime="image/png"
)
def poster_generator():
st.header("Generate Poster")
poster_type = st.selectbox("Poster Type", ["Fashion", "Movie", "Event", "Advertisement", "Other"])
prompt = st.text_area("Prompt")
num_images = st.number_input("Number of Images", min_value=1, max_value=5, value=1)
quality_factor = st.number_input("Quality Factor", min_value=1, max_value=4, value=1)
if st.button("Generate Images"):
if poster_type == "Other":
full_prompt = f"A colorful poster with the following elements: {prompt}"
else:
full_prompt = f"A colorful {poster_type.lower()} poster with the following elements: {prompt}"
generated_images = []
for i in range(num_images):
with st.spinner(f"Generating image {i+1}..."):
logger.info(f"Generating image {i+1} with prompt: {full_prompt}")
response = query({"inputs": full_prompt})
if isinstance(response, bytes):
image = Image.open(io.BytesIO(response))
if quality_factor > 1:
image = increase_image_quality(image, quality_factor)
generated_images.append(image)
else:
st.error("Failed to generate image")
# Display generated images
for i, img in enumerate(generated_images):
st.image(img, caption=f"Generated Poster {i+1}", use_column_width=True)
# Provide download option for the generated image
buf = io.BytesIO()
img.save(buf, format="PNG")
byte_im = buf.getvalue()
st.download_button(
label=f"Download generated poster {i+1}",
data=byte_im,
file_name=f"generated_poster_{i+1}.png",
mime="image/png"
)
def main():
st.title("Image Processing App")
app_mode = st.sidebar.selectbox("Choose the app mode",
["Image Text Replacer", "Poster Generator"])
if app_mode == "Image Text Replacer":
image_text_replacer()
elif app_mode == "Poster Generator":
poster_generator()
if __name__ == "__main__":
main() |