Create app.py

app.py

@@ -0,0 +1,81 @@
+import torch
+from PIL import Image
+from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline
+from diffusers import StableDiffusionImg2ImgPipeline
+from diffusers import EulerAncestralDiscreteScheduler
+
+#provide your Hugging Face Authentication token
+#you can obtain your token from https://huggingface.co/settings/tokens
+auth_token = input("Enter your Hugging Face token: ")
+
+###   image generation   ###
+
+#using stable diffusion version 2.1 for image generation
+modelid = "stabilityai/stable-diffusion-2-1"
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+pipe = StableDiffusionPipeline.from_pretrained(
+    modelid,
+    revision="fp16",
+    torch_dtype= torch.float16,
+    use_auth_token=auth_token,
+    low_cpu_mem_usage=True
+)
+#using EulerAncestralDiscreteScheduler for sharper and detailed images
+
+pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
+
+
+###    image modification    ###
+#using StableDiffusionImg2ImgPipeline for image to image generation
+pipe.to(device)
+
+pipe_img2img = StableDiffusionImg2ImgPipeline.from_pretrained("stabilityai/stable-diffusion-2-1", torch_dtype=torch.float16, low_cpu_mem_usage=True).to(device)
+pipe_img2img.to(device)
+
+import gradio as gr
+# Function to generate image from text
+def generate_image(prompt, guidance_scale):
+    global stored_image
+    image = pipe(prompt, guidance_scale=guidance_scale).images[0]
+    stored_image = image
+    return image
+
+# Function to modify image (Img2Img)
+def modify_image(prompt, strength=0.5):
+    global stored_image
+    if stored_image is None:
+        return "No generated image available. Generate an image first!"
+
+    stored_image = stored_image.convert("RGB")
+    modified_image = pipe_img2img(prompt=prompt, image=stored_image, strength=strength, guidance_scale=8.5).images[0]
+    return modified_image
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("# Stable Diffusion - Generate & Modify Images")
+    with gr.Group():
+      with gr.Row():
+        prompt_input = gr.Textbox(label="Enter Prompt", placeholder="A futuristic city at sunset")
+      with gr.Row():
+        guidance_input = gr.Slider(1.0, 15.0, value=8.5, label="Guidance Scale (More guidance meansthe model follows the prompt very strictly but is less creative)")  # User can adjust guidance
+
+    with gr.Row():
+      generate_btn = gr.Button("Generate")
+    with gr.Row():
+      output_image = gr.Image(label="Generated Image")
+
+    generate_btn.click(generate_image, inputs=[prompt_input, guidance_input], outputs=output_image)
+
+
+    # Modify Image (After Generation)
+    with gr.Tab("Modify Image"):
+        modify_prompt = gr.Textbox(label="Enter modification prompt")
+        strength_slider = gr.Slider(0.1, 1.0, value=0.5, label="Strength (Higher = More Change)")
+        modify_btn = gr.Button("Modify")
+        modified_output = gr.Image(label="Modified Image")
+
+        modify_btn.click(modify_image, inputs=[modify_prompt, strength_slider], outputs=modified_output)
+
+# Launch Gradio App
+demo.launch(share=True)