Update app.py

app.py

@@ -1,25 +1,90 @@
-from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
-import torch
-import gradio as gr 
-model_id = "stabilityai/stable-diffusion-2"
+import gradio as gr
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+from io import BytesIO
+from tensorflow.keras.applications.inception_v3 import InceptionV3, preprocess_input
+from tensorflow.keras.preprocessing.image import load_img, img_to_array
+from transformers import TFAutoModelWithLMHead, AutoTokenizer
+from stylegan2.tf_api import G_synthesis as StyleGAN2
 
-# Use the Euler scheduler here instead
-scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
-pipe = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, revision="fp16", torch_dtype=torch.float16)
-pipe = pipe.to("cuda")
 
-#prompt = "realistic photo of 3d cartoon style of a cat in a space suit with milky way background"
+# Load pre-trained image captioning model
+tokenizer = AutoTokenizer.from_pretrained("t5-large")
+model = TFAutoModelWithLMHead.from_pretrained("t5-large")
 
-def txt2img(prompt):
+# Load pre-trained StyleGAN2 model
+g = StyleGAN2()
+g.load_weights('models/stylegan2-ffhq-config-f.pkl')
 
-  image = pipe(prompt, height=768, width=768, guidance_scale = 10).images[0]
-    
-  image.save("sd_image.png")
+# Load pre-trained InceptionV3 model for image preprocessing
+inception_v3 = InceptionV3(weights='imagenet')
 
-  return image
+# Define function to preprocess image for GAN
+def preprocess_image(image):
+    image = image.resize((256, 256))
+    image_array = img_to_array(image)
+    image_array = preprocess_input(image_array)
+    image_array = np.expand_dims(image_array, axis=0)
+    return image_array
 
-txt2img(prompt)
+# Define function to generate image from text using StyleGAN2
+def generate_image(description):
+    z = tf.random.normal([1, g.input_shape[1]])
+    text = "generate image of a " + description
+    input_ids = tokenizer.encode(text, return_tensors='tf')
+    output = model.generate(input_ids=input_ids)
+    caption = tokenizer.decode(output[0], skip_special_tokens=True)
+    image = g(z, caption)
+    image = (image.numpy()[0] * 255).astype(np.uint8)
+    image = Image.fromarray(image, mode='RGB')
+    return image
 
+# Define function to generate text description of uploaded image using InceptionV3 and T5
+def generate_description(image_file):
+    image = Image.open(BytesIO(image_file.read()))
+    image = preprocess_image(image)
+    features = inception_v3.predict(image)
+    features = tf.keras.backend.flatten(features)
+    input_text = tokenizer.encode("generate a description of an image", return_tensors="tf")
+    output = model.generate(input_ids=input_text, attention_mask=tf.ones(input_text.shape), max_length=50)
+    caption = tokenizer.decode(output[0], skip_special_tokens=True)
+    return caption
 
+# Define functionto create the web application using Gradio
+def image_generation(text_input, image_file):
+    if image_file is not None:
+        # Generate text description of uploaded image
+        description = generate_description(image_file)
+        # Generate image from text description
+        generated_image = generate_image(description)
+    else:
+        # Generate image from user input text
+        generated_image = generate_image(text_input)
+    return generated_image
 
-gr.Interface(txt2img, gr.Text(), gr.Image(), title = 'AI TEXT TO IMAGE GENERATION 🖼️').launch(share = True, debug = True)
+#Define Gradio interface
+inputs = [gr.inputs.Textbox(label="Input text"),
+          gr.inputs.Image(label="Upload an image (optional)")
+         ]
+outputs = gr.outputs.Image(label="Generated Image")
+
+gr.Interface(
+    fn=image_generation,
+    inputs=inputs,
+    outputs=outputs,
+    title="Image Generation from Text",
+    description="Generate high-quality images from text descriptions.",
+    theme="default",
+    layout="vertical",
+    examples=[
+["a red sports car on a mountain road"],
+["a cute puppy"],
+["an elegant woman with a hat and a scarf"],
+["a scenic beach with palm trees and blue water"],
+["a golden retriever sitting on a couch"],
+["a delicious pizza with pepperoni and cheese"],
+["a futuristic city with tall buildings and flying cars"],
+["an adorable kitten playing with a ball of yarn"],
+],
+).launch(debug=True)