Create app.py

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+import torch
+from diffusers import AuraFlowPipeline
+
+# Initialize the AuraFlow pipeline
+pipe = AuraFlowPipeline.from_pretrained("purplesmartai/pony-v7-base", torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+
+def generate_image(prompt, negative_prompt, height, width, num_inference_steps, guidance_scale, seed):
+    """
+    Function to generate an image using the AuraFlow pipeline.
+    """
+    generator = torch.Generator("cuda").manual_seed(seed)
+    image = pipe(
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        height=int(height),
+        width=int(width),
+        num_inference_steps=int(num_inference_steps),
+        guidance_scale=guidance_scale,
+        generator=generator
+    ).images[0]
+    return image
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=generate_image,
+    inputs=[
+        gr.Textbox(label="Prompt", value="A cat holding a sign that says hello world"),
+        gr.Textbox(label="Negative Prompt", placeholder="Enter prompts to exclude"),
+        gr.Slider(label="Height", minimum=256, maximum=2048, step=64, value=1024),
+        gr.Slider(label="Width", minimum=256, maximum=2048, step=64, value=1024),
+        gr.Slider(label="Number of Inference Steps", minimum=1, maximum=100, step=1, value=50),
+        gr.Slider(label="Guidance Scale", minimum=1.0, maximum=20.0, step=0.1, value=5.0),
+        gr.Number(label="Seed", value=42)
+    ],
+    outputs=gr.Image(label="Generated Image"),
+    title="AuraFlow Text-to-Image Generation",
+    description="Generate images from text prompts using the AuraFlow model."
+)
+
+# Launch the Gradio app
+iface.launch()