Upload folder using huggingface_hub

README.md

@@ -1,12 +1,57 @@
 ---
-title: Stable Diffusion 3
-emoji: 🏃
-colorFrom: gray
-colorTo: red
+title: stable-diffusion-3
+app_file: SD3.py
 sdk: gradio
 sdk_version: 4.26.0
-app_file: app.py
-pinned: false
 ---
+# Stable Diffusion 3 Text-to-Image Generator
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+This is a Python application that utilizes the Stable Diffusion 3 model to generate images from textual prompts. It provides a user-friendly interface built with Gradio, allowing users to enter a prompt, select a model, and choose an aspect ratio to generate an image.
+
+## Requirements
+
+To run this application, you need to have the following dependencies installed:
+
+- requests
+- requests-toolbelt
+- gradio
+
+You can install these dependencies by running the following command:
+
+```bash
+pip install -r requirements.txt
+```
+
+## Usage
+
+1. Clone this repository to your local machine.
+2. Install the required dependencies using the command mentioned above.
+3. Replace the `api_key` variable in the `SD3.py` file with your actual Stability AI API key.
+4. Run the `SD3.py` script using the following command:
+
+```bash
+python SD3.py
+```
+
+5. The application will launch in your default web browser.
+6. Enter a text prompt describing the image you want to generate.
+7. Select the desired model (either "sd3" or "sd3-turbo").
+8. Choose the aspect ratio for the generated image.
+9. Click the "Submit" button to generate the image.
+10. The generated image will be displayed on the screen.
+
+## About Stable Diffusion 3
+
+Stable Diffusion 3 is a state-of-the-art text-to-image generation model developed by Stability AI. It is capable of generating high-quality images from textual descriptions, allowing users to create visual content based on their imagination.
+
+The model has been trained on a vast dataset of image-text pairs, enabling it to understand and generate images across a wide range of domains and styles. It uses a diffusion-based approach to iteratively refine the generated image, resulting in highly detailed and coherent visual outputs.
+
+Stable Diffusion 3 offers two variants: "sd3" and "sd3-turbo". The "sd3" model is the standard version, while "sd3-turbo" is a more powerful and computationally intensive variant that can generate even higher-quality images.
+
+## Acknowledgements
+
+This application is built using the Stability AI API and the Gradio library. We would like to thank the developers and contributors of these projects for their excellent work.
+
+## License
+
+This project is licensed under the [MIT License](LICENSE).

SD3.py

@@ -0,0 +1,53 @@
+import requests
+from requests_toolbelt.multipart.encoder import MultipartEncoder
+import gradio as gr
+
+def generate_image(prompt, aspect_ratio='1:1', model='sd3', seed=0, output_format='png'):
+    api_url = "https://api.stability.ai/v2beta/stable-image/generate/sd3"
+    api_key = "sk-lr4V2rv0uFv2dmgD34TPrURw9ppaFgcZs67rNW7zKqJqiHEb"  # Replace this with your actual API key
+
+    m = MultipartEncoder(
+        fields={
+            'prompt': prompt,
+            'aspect_ratio': aspect_ratio,
+            'model': model,
+            'seed': str(seed),
+            'output_format': output_format,
+            'mode': 'text-to-image'  # Default mode
+        }
+    )
+
+    headers = {
+        'Authorization': f'Bearer {api_key}',
+        'Content-Type': m.content_type,
+        'Accept': 'image/*'  # To receive the image directly
+    }
+
+    response = requests.post(api_url, data=m, headers=headers)
+    print(response.status_code, response.content)
+    
+    if response.status_code == 200:
+        # Assuming the response content is the image in binary format
+        output_path = 'generated_image.png'
+        with open(output_path, 'wb') as f:
+            f.write(response.content)
+        return output_path  # Return the path for Gradio to display the image
+    else:
+        return f"Error: {response.text}"
+
+def wrap_generate_image(prompt, model, aspect_ratio):
+    return generate_image(prompt, aspect_ratio, model)
+
+iface = gr.Interface(
+    fn=wrap_generate_image,
+    inputs=[
+        gr.Textbox(lines=2, label="Prompt", placeholder="Enter a description for the image..."),
+        gr.Radio(choices=['sd3', 'sd3-turbo'], label="Model", value='sd3'),
+        gr.Dropdown(choices=['1:1', '16:9', '21:9', '2:3', '3:2', '4:5', '5:4', '9:16', '9:21'], label="Aspect Ratio", value='1:1')
+    ],
+    outputs=gr.Image(),
+    title="Stable Diffusion 3 Text-to-Image Generator",
+    description="Select a model, aspect ratio, and enter a prompt to generate an image using Stable Diffusion 3."
+)
+
+iface.launch(share=True)

requirements.txt

@@ -0,0 +1,3 @@
+requests
+requests-toolbelt
+gradio