Update app.py

app.py

@@ -8,6 +8,8 @@ import gradio as gr
 import os
 from spaces import GPU
 from dotenv import load_dotenv
+import torch
+from diffusers import DiffusionPipeline
 
 load_dotenv()
 
@@ -88,7 +90,14 @@ def remove_duplicates(text):
             seen_lines.add(line)
     return '\n'.join(unique_lines)
 
-@GPU(duration=1)
+dtype = torch.bfloat16 if torch.cuda.is_available() else torch.float32
+device = "cuda" if torch.cuda.is_available() else "cpu"
+pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=dtype).to(device)
+MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 2048
+
+@spaces.GPU()
+@GPU(duration=1) 
 def generate_model_response(model, inputs):
     try:
         response = model(inputs)
@@ -97,6 +106,22 @@ def generate_model_response(model, inputs):
         print(f"Error generating model response: {e}")
         return ""
 
+@spaces.GPU()
+@GPU(duration=1)
+def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, num_inference_steps=4):
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    generator = torch.Generator(device=device).manual_seed(seed)
+    image = pipe(
+            prompt=prompt,
+            width=width,
+            height=height,
+            num_inference_steps=num_inference_steps,
+            generator=generator,
+            guidance_scale=0.0
+    ).images[0]
+    return image, seed
+
 def remove_repetitive_responses(responses):
     unique_responses = {}
     for response in responses:
@@ -124,15 +149,88 @@ async def process_message(message):
     """
     return formatted_response, curl_command
 
+examples = [
+    "a tiny astronaut hatching from an egg on the moon",
+    "a cat holding a sign that says hello world",
+    "an anime illustration of a wiener schnitzel",
+]
 
-iface = gr.Interface(
-    fn=process_message,
-    inputs=gr.Textbox(lines=2, placeholder="Enter your message here..."),
-    outputs=[gr.Markdown(), gr.Textbox(label="cURL command")],
-    title="Multi-Model LLM API",
-    description="Enter a message and get responses from multiple LLMs.",
-)
+css="""
+#col-container {
+    margin: 0 auto;
+    max-width: 520px;
+}
+"""
+
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(f"""# FLUX.1 [schnell]
+12B param rectified flow transformer distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/) for 4 step generation
+[[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1-schnell)]
+        """)
+
+        with gr.Row():
+            prompt = gr.Text(
+                label="Prompt",
+                show_label=False,
+                max_lines=1,
+                placeholder="Enter your prompt",
+                container=False,
+            )
+            run_button = gr.Button("Run", scale=0)
+        
+        result = gr.Image(label="Result", show_label=False)
+        
+        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():
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=50,
+                    step=1,
+                    value=4,
+                )
+
+        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, num_inference_steps],
+        outputs=[result, seed]
+    )
 
 if __name__ == "__main__":
     port = int(os.environ.get("PORT", 7860))
-    iface.launch(server_port=port)
+    demo.launch(server_port=port)