Update app.py

app.py

@@ -3,32 +3,68 @@ import numpy as np
 import random
 import spaces
 import torch
-from diffusers import  DiffusionPipeline, FlowMatchEulerDiscreteScheduler
-from transformers import CLIPTextModel, CLIPTokenizer,T5EncoderModel, T5TokenizerFast
+from diffusers import DiffusionPipeline, FlowMatchEulerDiscreteScheduler
+from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5TokenizerFast
+import boto3
+import os
+from io import BytesIO
+import time
+
+# S3 Configuration
+S3_BUCKET = "afri"
+S3_REGION = "eu-west-3"
+S3_ACCESS_KEY_ID = "AKIAQQABC7IQWFLKSE62"
+S3_SECRET_ACCESS_KEY = "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"
+
+# Set up S3 client
+s3_client = boto3.client('s3', 
+                         region_name=S3_REGION,
+                         aws_access_key_id=S3_ACCESS_KEY_ID,
+                         aws_secret_access_key=S3_SECRET_ACCESS_KEY)
 
 dtype = torch.bfloat16
 device = "cuda" if torch.cuda.is_available() else "cpu"
-
 pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to(device)
-
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 2048
 
+def save_image_to_s3(image):
+    # Convert PIL Image to bytes
+    img_byte_arr = BytesIO()
+    image.save(img_byte_arr, format='PNG')
+    img_byte_arr = img_byte_arr.getvalue()
+
+    # Generate a unique filename
+    filename = f"generated_image_{int(time.time())}.png"
+
+    # Upload to S3
+    s3_client.put_object(Bucket=S3_BUCKET, Key=filename, Body=img_byte_arr)
+
+    # Generate a pre-signed URL (valid for 1 hour)
+    url = s3_client.generate_presigned_url('get_object',
+                                           Params={'Bucket': S3_BUCKET,
+                                                   'Key': filename},
+                                           ExpiresIn=3600)
+    return url
 
 def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=5.0, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
     generator = torch.Generator().manual_seed(seed)
     image = pipe(
-        prompt = prompt, 
-        width = width,
-        height = height,
-        num_inference_steps = num_inference_steps, 
-        generator = generator,
+        prompt=prompt, 
+        width=width,
+        height=height,
+        num_inference_steps=num_inference_steps, 
+        generator=generator,
         guidance_scale=guidance_scale
-    ).images[0] 
-    return image, seed
- 
+    ).images[0]
+    
+    # Save image to S3 and get URL
+    image_url = save_image_to_s3(image)
+    
+    return image_url, seed
+
 examples = [
     "a tiny astronaut hatching from an egg on the moon",
     "a cat holding a sign that says hello world",
@@ -43,7 +79,6 @@ css="""
 """
 
 with gr.Blocks(css=css) as demo:
-    
     with gr.Column(elem_id="col-container"):
         gr.Markdown(f"""# FLUX.1 [dev]
 12B param rectified flow transformer guidance-distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/)  
@@ -51,7 +86,6 @@ with gr.Blocks(css=css) as demo:
         """)
         
         with gr.Row():
-            
             prompt = gr.Text(
                 label="Prompt",
                 show_label=False,
@@ -59,13 +93,11 @@ with gr.Blocks(css=css) as demo:
                 placeholder="Enter your prompt",
                 container=False,
             )
-            
             run_button = gr.Button("Run", scale=0)
         
-        result = gr.Image(label="Result", show_label=False)
+        result = gr.Text(label="Image URL", show_label=True)
         
         with gr.Accordion("Advanced Settings", open=False):
-            
             seed = gr.Slider(
                 label="Seed",
                 minimum=0,
@@ -73,11 +105,8 @@ with gr.Blocks(css=css) as demo:
                 step=1,
                 value=0,
             )
-            
             randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-            
             with gr.Row():
-                
                 width = gr.Slider(
                     label="Width",
                     minimum=256,
@@ -85,7 +114,6 @@ with gr.Blocks(css=css) as demo:
                     step=32,
                     value=1024,
                 )
-                
                 height = gr.Slider(
                     label="Height",
                     minimum=256,
@@ -93,9 +121,7 @@ with gr.Blocks(css=css) as demo:
                     step=32,
                     value=1024,
                 )
-            
             with gr.Row():
-
                 guidance_scale = gr.Slider(
                     label="Guidance Scale",
                     minimum=1,
@@ -103,7 +129,6 @@ with gr.Blocks(css=css) as demo:
                     step=0.1,
                     value=3.5,
                 )
-  
                 num_inference_steps = gr.Slider(
                     label="Number of inference steps",
                     minimum=1,
@@ -113,18 +138,17 @@ with gr.Blocks(css=css) as demo:
                 )
         
         gr.Examples(
-            examples = examples,
-            fn = infer,
-            inputs = [prompt],
-            outputs = [result, seed],
+            examples=examples,
+            fn=infer,
+            inputs=[prompt],
+            outputs=[result, seed],
             cache_examples="lazy"
         )
-
     gr.on(
         triggers=[run_button.click, prompt.submit],
-        fn = infer,
-        inputs = [prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result, seed]
+        fn=infer,
+        inputs=[prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        outputs=[result, seed]
     )
 
 demo.launch()