Update app.py

app.py

@@ -8,10 +8,10 @@ from PIL import Image
 import spaces
 import torch
 from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
-from diffusers import AuraFlowPipeline
-
 
 DESCRIPTIONx = """
+
+
 """
 
 css = '''
@@ -22,10 +22,17 @@ footer {
 }
 '''
 
+#examples = [
+ #   "3d image, cute girl, in the style of Pixar --ar 1:2 --stylize 750, 4K resolution highlights, Sharp focus, octane render, ray tracing, Ultra-High-Definition, 8k, UHD, HDR, (Masterpiece:1.5), (best quality:1.5)",
+  #  "Chocolate dripping from a donut against a yellow background, in the style of brocore, hyper-realistic oil --ar 2:3 --q 2 --s 750 --v 5  --ar 2:3 --q 2 --s 750 --v 5",
+  #  "Illustration of A starry night camp in the mountains. Low-angle view, Minimal background, Geometric shapes theme, Pottery, Split-complementary colors, Bicolored light, UHD",
+  #  "Man in brown leather jacket posing for camera, in the style of sleek and stylized, clockpunk, subtle shades, exacting precision, ferrania p30  --ar 67:101 --v 5",
+   # "Commercial photography, giant burger, white lighting, studio light, 8k octane rendering, high resolution photography, insanely detailed, fine details, on white isolated plain, 8k, commercial photography, stock photo, professional color grading, --v 4 --ar 9:16 "
+#]
+
 MODEL_OPTIONS = {
     "Lightning": "SG161222/RealVisXL_V4.0_Lightning",
     "Realvision": "SG161222/RealVisXL_V4.0",
-    "AuraFlow": "fal/AuraFlow",
 }
 
 MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "4096"))
@@ -36,29 +43,23 @@ BATCH_SIZE = int(os.getenv("BATCH_SIZE", "1"))
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
 def load_and_prepare_model(model_id):
-    if model_id == "fal/AuraFlow":
-        pipe = AuraFlowPipeline.from_pretrained(
-            model_id,
-            torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
-        ).to(device)
-    else:
-        pipe = StableDiffusionXLPipeline.from_pretrained(
-            model_id,
-            torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
-            use_safetensors=True,
-            add_watermarker=False,
-        ).to(device)
-        pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
-
+    pipe = StableDiffusionXLPipeline.from_pretrained(
+        model_id,
+        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+        use_safetensors=True,
+        add_watermarker=False,
+    ).to(device)
+    pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
+    
     if USE_TORCH_COMPILE:
         pipe.compile()
-
+    
     if ENABLE_CPU_OFFLOAD:
         pipe.enable_model_cpu_offload()
-
+    
     return pipe
 
-# Preload and compile all models
+# Preload and compile both models
 models = {key: load_and_prepare_model(value) for key, value in MODEL_OPTIONS.items()}
 
 MAX_SEED = np.iinfo(np.int32).max
@@ -91,7 +92,7 @@ def generate(
 ):
     global models
     pipe = models[model_choice]
-
+    
     seed = int(randomize_seed_fn(seed, randomize_seed))
     generator = torch.Generator(device=device).manual_seed(seed)
 
@@ -138,7 +139,7 @@ def load_predefined_images():
     return predefined_images
 
 with gr.Blocks(css=css) as demo:
-    gr.Markdown(DESCRIPTIONx)
+    gr.Markdown(DESCRIPTIONx)    
     with gr.Row():
         prompt = gr.Text(
             label="Prompt",
@@ -149,7 +150,7 @@ with gr.Blocks(css=css) as demo:
             container=False,
         )
         run_button = gr.Button("Run⚡", scale=0)
-    result = gr.Gallery(label="Result", columns=1, show_label=False)
+    result = gr.Gallery(label="Result", columns=1, show_label=False) 
 
     with gr.Row():
         model_choice = gr.Dropdown(
@@ -216,13 +217,19 @@ with gr.Blocks(css=css) as demo:
                 value=20,
             )
 
+   # gr.Examples(
+    #    examples=examples,
+    #    inputs=prompt,
+     #   cache_examples=False
+    #)
+
     use_negative_prompt.change(
         fn=lambda x: gr.update(visible=x),
         inputs=use_negative_prompt,
         outputs=negative_prompt,
         api_name=False,
     )
-
+    
     gr.on(
         triggers=[
             prompt.submit,
@@ -246,6 +253,266 @@ with gr.Blocks(css=css) as demo:
         outputs=[result, seed],
         api_name="run",
     )
+#!/usr/bin/env python
+import os
+import random
+import uuid
+import gradio as gr
+import numpy as np
+from PIL import Image
+import spaces
+import torch
+from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
+
+DESCRIPTIONx = """
+
+
+"""
+
+css = '''
+.gradio-container{max-width: 570px !important}
+h1{text-align:center}
+footer {
+    visibility: hidden
+}
+'''
+
+examples = [
+    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
+    "Chocolate dripping from a donut against a yellow background, 8k",
+    "Illustration of A starry night camp in the mountains, 4k",
+    "A photo of a lavender cat, hdr, 4k",
+    "A delicious ceviche cheesecake slice, 4k"
+]
+
+MODEL_OPTIONS = {
+    "Lightning": "SG161222/RealVisXL_V4.0_Lightning",
+    "Realvision": "SG161222/RealVisXL_V4.0",
+}
+
+MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "4096"))
+USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "0") == "1"
+ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1"
+BATCH_SIZE = int(os.getenv("BATCH_SIZE", "1"))
+
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+
+def load_and_prepare_model(model_id):
+    pipe = StableDiffusionXLPipeline.from_pretrained(
+        model_id,
+        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+        use_safetensors=True,
+        add_watermarker=False,
+    ).to(device)
+    pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
+    
+    if USE_TORCH_COMPILE:
+        pipe.compile()
+    
+    if ENABLE_CPU_OFFLOAD:
+        pipe.enable_model_cpu_offload()
+    
+    return pipe
+
+# Preload and compile both models
+models = {key: load_and_prepare_model(value) for key, value in MODEL_OPTIONS.items()}
+
+MAX_SEED = np.iinfo(np.int32).max
 
+def save_image(img):
+    unique_name = str(uuid.uuid4()) + ".png"
+    img.save(unique_name)
+    return unique_name
+
+def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+    return seed
+
+@spaces.GPU(duration=60, enable_queue=True)
+def generate(
+    model_choice: str,
+    prompt: str,
+    negative_prompt: str = "",
+    use_negative_prompt: bool = False,
+    seed: int = 1,
+    width: int = 1024,
+    height: int = 1024,
+    guidance_scale: float = 3,
+    num_inference_steps: int = 25,
+    randomize_seed: bool = False,
+    use_resolution_binning: bool = True, 
+    num_images: int = 1,  
+    progress=gr.Progress(track_tqdm=True),
+):
+    global models
+    pipe = models[model_choice]
+    
+    seed = int(randomize_seed_fn(seed, randomize_seed))
+    generator = torch.Generator(device=device).manual_seed(seed)
+
+    options = {
+        "prompt": [prompt] * num_images,
+        "negative_prompt": [negative_prompt] * num_images if use_negative_prompt else None,
+        "width": width,
+        "height": height,
+        "guidance_scale": guidance_scale,
+        "num_inference_steps": num_inference_steps,
+        "generator": generator,
+        "output_type": "pil",
+    }
+
+    if use_resolution_binning:
+        options["use_resolution_binning"] = True
+
+    images = []
+    for i in range(0, num_images, BATCH_SIZE):
+        batch_options = options.copy()
+        batch_options["prompt"] = options["prompt"][i:i+BATCH_SIZE]
+        if "negative_prompt" in batch_options:
+            batch_options["negative_prompt"] = options["negative_prompt"][i:i+BATCH_SIZE]
+        images.extend(pipe(**batch_options).images)
+
+    image_paths = [save_image(img) for img in images]
+    return image_paths, seed
+
+#def load_predefined_images():
+  #  predefined_images = [
+ #       "assets/1.png",
+    #    "assets/2.png",
+    #    "assets/3.png",
+    #    "assets/4.png",
+    #    "assets/5.png",
+   #     "assets/6.png",
+    #    "assets/7.png",
+     #   "assets/8.png",
+    #    "assets/9.png",
+     #   "assets/10.png",
+   #     "assets/11.png",
+ #       "assets/12.png",
+ #   ]
+  #  return predefined_images
+
+with gr.Blocks(css=css) as demo:
+    gr.Markdown(DESCRIPTIONx)    
+    with gr.Row():
+        prompt = gr.Text(
+            label="Prompt",
+            show_label=False,
+            max_lines=1,
+            placeholder="Enter your prompt",
+            value="Chocolate dripping from a donut against a yellow background, 8k",
+            container=False,
+        )
+        run_button = gr.Button("Run⚡", scale=0)
+    result = gr.Gallery(label="Result", columns=1, show_label=False) 
+
+    with gr.Row():
+        model_choice = gr.Dropdown(
+            label="Model Selection",
+            choices=list(MODEL_OPTIONS.keys()),
+            value="Lightning"
+        )
+
+    with gr.Accordion("Advanced options", open=True, visible=False):
+        num_images = gr.Slider(
+            label="Number of Images",
+            minimum=1,
+            maximum=1,
+            step=1,
+            value=1,
+        )
+        with gr.Row():
+            with gr.Column(scale=1):
+                use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True)
+                negative_prompt = gr.Text(
+                    label="Negative prompt",
+                    max_lines=5,
+                    lines=4,
+                    placeholder="Enter a negative prompt",
+                    value="(deformed, distorted, disfigured:1.3), poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation",
+                    visible=True,
+                )
+        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=512,
+                maximum=MAX_IMAGE_SIZE,
+                step=64,
+                value=1024,
+            )
+            height = gr.Slider(
+                label="Height",
+                minimum=512,
+                maximum=MAX_IMAGE_SIZE,
+                step=64,
+                value=1024,
+            )
+        with gr.Row():
+            guidance_scale = gr.Slider(
+                label="Guidance Scale",
+                minimum=0.1,
+                maximum=6,
+                step=0.1,
+                value=3.0,
+            )
+            num_inference_steps = gr.Slider(
+                label="Number of inference steps",
+                minimum=1,
+                maximum=35,
+                step=1,
+                value=20,
+            )
+
+    gr.Examples(
+        examples=examples,
+        inputs=prompt,
+        cache_examples=False
+    )
+
+    use_negative_prompt.change(
+        fn=lambda x: gr.update(visible=x),
+        inputs=use_negative_prompt,
+        outputs=negative_prompt,
+        api_name=False,
+    )
+    
+    gr.on(
+        triggers=[
+            prompt.submit,
+            negative_prompt.submit,
+            run_button.click,
+        ],
+        fn=generate,
+        inputs=[
+            model_choice,
+            prompt,
+            negative_prompt,
+            use_negative_prompt,
+            seed,
+            width,
+            height,
+            guidance_scale,
+            num_inference_steps,
+            randomize_seed,
+            num_images
+        ],
+        outputs=[result, seed],
+        api_name="run",
+    )
+ #   with gr.Column(scale=3):
+    #    gr.Markdown("### Image Gallery")
+     #   predefined_gallery = gr.Gallery(label="Image Gallery", columns=4, show_label=False, value=load_predefined_images())       
+if __name__ == "__main__":
+    demo.queue(max_size=40).launch(show_api=False)
+           
 if __name__ == "__main__":
     demo.queue(max_size=40).launch(show_api=False)