Update app.py

app.py

@@ -1,144 +1,47 @@
 import gradio as gr
-import numpy as np
-import random
 import torch
-from diffusers import DiffusionPipeline, AutoencoderTiny, AutoencoderKL
+from diffusers import DiffusionPipeline
 from PIL import Image
 
-dtype = torch.bfloat16
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).to(device)
-good_vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev", subfolder="vae", torch_dtype=dtype).to(device)
-pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=dtype, vae=taef1).to(device)
-torch.cuda.empty_cache()
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 2048
-
-# Mock function to replace flux_pipe_call_that_returns_an_iterable_of_images
-def mock_flux_pipe_call_that_returns_an_iterable_of_images(prompt, guidance_scale, num_inference_steps, width, height, generator, output_type, good_vae):
-    # Generate a placeholder image
-    image = Image.new('RGB', (width, height), color = 'red')
-    yield image
+# Load the diffusion model
+pipeline = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev")
 
-# Replace the method with the mock function
-pipe.flux_pipe_call_that_returns_an_iterable_of_images = mock_flux_pipe_call_that_returns_an_iterable_of_images.__get__(pipe)
+# Set the model to the appropriate device
+device = "cuda" if torch.cuda.is_available() else "cpu"
+pipeline.to(device)
 
-@gr.inputs.GPU(duration=75)
-def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, 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)
+def generate_image(prompt, guidance_scale=7.5, num_inference_steps=50):
+    # Generate an image based on the prompt
+    with torch.no_grad():
+        # Generate images
+        images = pipeline(prompt, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images
     
-    for img in pipe.flux_pipe_call_that_returns_an_iterable_of_images(
-            prompt=prompt,
-            guidance_scale=guidance_scale,
-            num_inference_steps=num_inference_steps,
-            width=width,
-            height=height,
-            generator=generator,
-            output_type="pil",
-            good_vae=good_vae,
-        ):
-        yield img, seed
-
-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",
-]
-
-css="""
-#col-container {
-    margin: 0 auto;
-    max-width: 520px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
+    # Assuming pipeline returns a list of images, just take the first one
+    img = images[0]
     
-    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/)  
-[[non-commercial license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)] [[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1-dev)]
-        """)
-        
-        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():
-
-                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,
-                )
-        
-        gr.Examples(
-            examples = examples,
-            fn = infer,
-            inputs = [prompt],
-            outputs = [result, seed],
-            cache_examples="lazy"
-        )
+    # Convert PIL image to format suitable for Gradio
+    return img
 
-    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]
+# Set up Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Text to Image Generation")
+    
+    with gr.Row():
+        prompt = gr.Textbox(label="Prompt", placeholder="Enter a prompt here...")
+        guidance_scale = gr.Slider(minimum=1, maximum=15, step=0.1, value=7.5, label="Guidance Scale")
+        num_inference_steps = gr.Slider(minimum=1, maximum=100, step=1, value=50, label="Number of Inference Steps")
+    
+    with gr.Row():
+        generate_button = gr.Button("Generate Image")
+    
+    result = gr.Image(label="Generated Image")
+    
+    # Connect the function to the button
+    generate_button.click(
+        fn=generate_image,
+        inputs=[prompt, guidance_scale, num_inference_steps],
+        outputs=result
     )
 
+# Launch the app
 demo.launch()