Update app.py

app.py

@@ -1,29 +1,18 @@
 import gradio as gr
 import numpy as np
 import random
-
-
-# import spaces #[uncomment to use ZeroGPU]
 from diffusers import DiffusionPipeline
 import torch
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
+# Load the pipeline
 pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev")
 pipe.load_lora_weights("EvanZhouDev/open-genmoji")
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 pipe = pipe.to(device)
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
 def infer(
     prompt,
     negative_prompt,
@@ -33,25 +22,24 @@ def infer(
     height,
     guidance_scale,
     num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
 ):
+    # Handle seed randomization
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
+    generator = torch.manual_seed(seed)
 
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
+    # Generate the image using the pipeline
+    result = pipe(
         prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
+        negative_prompt=negative_prompt if negative_prompt else None,
         width=width,
         height=height,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
         generator=generator,
     ).images[0]
 
-    return image, seed
-
+    return result, seed
 
 examples = [
     "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
@@ -88,7 +76,7 @@ with gr.Blocks(css=css) as demo:
                 label="Negative prompt",
                 max_lines=1,
                 placeholder="Enter a negative prompt",
-                visible=False,
+                visible=True,
             )
 
             seed = gr.Slider(
@@ -107,7 +95,7 @@ with gr.Blocks(css=css) as demo:
                     minimum=256,
                     maximum=MAX_IMAGE_SIZE,
                     step=32,
-                    value=1024,  # Replace with defaults that work for your model
+                    value=512,  # Default width for your model
                 )
 
                 height = gr.Slider(
@@ -115,7 +103,7 @@ with gr.Blocks(css=css) as demo:
                     minimum=256,
                     maximum=MAX_IMAGE_SIZE,
                     step=32,
-                    value=1024,  # Replace with defaults that work for your model
+                    value=512,  # Default height for your model
                 )
 
             with gr.Row():
@@ -124,7 +112,7 @@ with gr.Blocks(css=css) as demo:
                     minimum=0.0,
                     maximum=10.0,
                     step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
+                    value=7.5,  # Default guidance scale for your model
                 )
 
                 num_inference_steps = gr.Slider(
@@ -132,25 +120,25 @@ with gr.Blocks(css=css) as demo:
                     minimum=1,
                     maximum=50,
                     step=1,
-                    value=2,  # Replace with defaults that work for your model
+                    value=25,  # Default number of inference steps for your model
                 )
 
         gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
+
+        run_button.click(
+            infer,
+            inputs=[
+                prompt,
+                negative_prompt,
+                seed,
+                randomize_seed,
+                width,
+                height,
+                guidance_scale,
+                num_inference_steps,
+            ],
+            outputs=[result, seed],
+        )
 
 if __name__ == "__main__":
     demo.launch()