Update app.py

app.py

@@ -1,30 +1,30 @@
 import gradio as gr
 import numpy as np
 import random
+import spaces
 import torch
-from diffusers import DiffusionPipeline
+from diffusers import DiffusionPipeline, FlowMatchEulerDiscreteScheduler
+from PIL import Image
+import io
 import os
 
-# Constants
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 2048
-DEFAULT_IMAGE_SIZE = 1024
-
-# Model setup
 dtype = torch.bfloat16
 device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Set your Hugging Face API token
 huggingface_token = os.getenv("HUGGINGFACE_TOKEN")
 
-pipe = DiffusionPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-dev",
-    torch_dtype=dtype,
-    token=huggingface_token
-).to(device)
+# Load the diffusion pipeline with the Hugging Face API token
+pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=dtype, token=huggingface_token).to(device)
 
-def generate_image(prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):
+MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 2048
+
+@spaces.GPU(duration=200)
+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(42)
+    generator = torch.Generator().manual_seed(seed)
     image = pipe(
         prompt=prompt,
         width=width,
@@ -35,15 +35,30 @@ def generate_image(prompt, seed, randomize_seed, width, height, guidance_scale,
     ).images[0]
     return image, seed
 
+def download_image(image, file_format):
+    img_byte_arr = io.BytesIO()
+    image.save(img_byte_arr, format=file_format)
+    img_byte_arr = img_byte_arr.getvalue()
+    return img_byte_arr
+
+examples = [
+    "a galaxy swirling with vibrant blue and purple hues",
+    "a futuristic cityscape under a dark sky",
+    "a serene forest with a magical glowing tree",
+    "a futuristic cityscape with sleek skyscrapers and flying cars",
+    "a portrait of a smiling woman with a colorful floral crown",
+    "a fantastical creature with the body of a dragon and the wings of a butterfly",
+]
+
 css = """
 body {
     background-color: #f4faff;
     color: #005662;
     font-family: 'Poppins', sans-serif;
 }
-.container {
+#col-container {
     margin: 0 auto;
-    max-width: 900px;
+    max-width: 100%;
     padding: 20px;
 }
 .gr-button {
@@ -55,62 +70,128 @@ body {
 .gr-button:hover {
     background-color: #0277bd;
 }
-.gr-box {
-    border-radius: 12px;
+.gr-examples-card {
     border: 1px solid #eeeeee;
+    border-radius: 12px;
+    padding: 16px;
+    margin-bottom: 12px;
+}
+.gr-examples-card:hover {
+    background-color: #f4faf2;
+    border-color: #0277bd;
+    color: #005662;
+}
+.gr-progress-bar, .gr-progress-bar-fill {
+    background-color: #0288d1 !important;
+}
+.gr-slider, .gr-slider-track {
+    background-color: #0288d1 !important;
+}
+.gr-slider-thumb {
+    background-color: #005662 !important;
+}
+.gr-text-input, .gr-image {
+    width: 100%;
+    box-sizing: border-box;
+    margin-bottom: 10px;
 }
 """
 
 with gr.Blocks(css=css, theme=gr.themes.Soft(primary_hue="blue", secondary_hue="gray")) as demo:
-    gr.Markdown("""
-    # FLUX.1 [dev] | A Text-To-Image Rectified Flow 12B Transformer
-    
-    Enter a text prompt below to generate an image. Click 'Generate' to create your image.
-    """)
-    
-    with gr.Row():
-        with gr.Column(scale=4):
-            prompt = gr.Text(
-                label="Prompt",
-                placeholder="Enter your prompt here",
-                lines=3
-            )
-        with gr.Column(scale=1):
-            generate_button = gr.Button("Generate", variant="primary")
     
-    result = gr.Image(label="Generated Image", type="pil")
-    
-    with gr.Accordion("Advanced Settings", open=False):
-        seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
-        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(f"""# FLUX.1 [dev] | A Text-To-Image Rectified Flow 12B Transformer
         
+<a href="https://huggingface.co/black-forest-labs/FLUX.1-dev" style="text-decoration:none;">
+<div class="gr-examples-card">
+    <h3>View Model Details</h3>
+    <p>Explore more about this model on Hugging Face.</p>
+</div>
+</a>
+        """)
+
         with gr.Row():
-            width = gr.Slider(label="Width", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=DEFAULT_IMAGE_SIZE)
-            height = gr.Slider(label="Height", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=DEFAULT_IMAGE_SIZE)
+            with gr.Column(scale=4):
+                prompt = gr.Text(
+                    label="Prompt",
+                    placeholder="Enter your prompt here",
+                    lines=2
+                )
+            with gr.Column(scale=1):
+                generate_button = gr.Button("Generate", variant="primary")
         
-        with gr.Row():
-            guidance_scale = gr.Slider(label="Guidance Scale", minimum=1, maximum=15, step=0.1, value=3.5)
-            num_inference_steps = gr.Slider(label="Number of inference steps", minimum=1, maximum=50, step=1, value=28)
+        result = gr.Image(label="Generated Image", type="pil")
     
-    gr.Examples(
-        examples=[
-            "a galaxy swirling with vibrant blue and purple hues",
-            "a futuristic cityscape under a dark sky",
-            "a serene forest with a magical glowing tree",
-            "a portrait of a smiling woman with a colorful floral crown",
-            "a fantastical creature with the body of a dragon and the wings of a butterfly",
-        ],
-        inputs=prompt,
-        outputs=[result, seed],
-        fn=generate_image,
-        cache_examples=True,
-    )
-    
-    generate_button.click(
-        fn=generate_image,
+        with gr.Accordion("Advanced Settings", open=False):
+            seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
+            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+            
+            with gr.Row():
+                width = gr.Slider(
+                    label="Width",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                )
+                height = gr.Slider(
+                    label="Height",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                )
+            
+            with gr.Row():
+                guidance_scale = gr.Slider(
+                    label="Guidance Scale",
+                    minimum=1,
+                    maximum=15,
+                    step=0.1,
+                    value=3.5,
+                )
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=50,
+                    step=1,
+                    value=28,
+                )
+        
+        download_format = gr.Radio(
+            label="Download Format",
+            choices=["PNG", "JPEG", "SVG", "WEBP"],
+            value="PNG",
+            type="value",
+        )
+
+        download_button = gr.Button("Download Image")
+
+        download_button.click(
+            fn=download_image,
+            inputs=[result, download_format],
+            outputs=gr.File(label="Download"),
+        )
+
+        gr.Examples(
+            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]
     )
 
+    demo.load(
+        fn=lambda: None,
+        inputs=None,
+        outputs=None
+    )
 
 demo.launch(share=True)