Update app.py

app.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 import os
 import random
 import uuid
@@ -8,34 +10,127 @@ import numpy as np
 from PIL import Image
 import spaces
 import torch
-from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
+from diffusers import DiffusionPipeline
+from typing import Tuple
+
+#Check for the Model Base..//
+
+
+
+bad_words = json.loads(os.getenv('BAD_WORDS', "[]"))
+bad_words_negative = json.loads(os.getenv('BAD_WORDS_NEGATIVE', "[]"))
+default_negative = os.getenv("default_negative","")
+
+def check_text(prompt, negative=""):
+    for i in bad_words:
+        if i in prompt:
+            return True
+    for i in bad_words_negative:
+        if i in negative:
+            return True
+    return False
+
+
+
+style_list = [
+
+    {
+        "name": "2560 x 1440",
+        "prompt": "hyper-realistic 4K image of {prompt}. ultra-detailed, lifelike, high-resolution, sharp, vibrant colors, photorealistic",
+        "negative_prompt": "cartoonish, low resolution, blurry, simplistic, abstract, deformed, ugly",
+    },
+
+    {
+        "name": "Photo",
+        "prompt": "cinematic photo {prompt}. 35mm photograph, film, bokeh, professional, 4k, highly detailed",
+        "negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, ugly",
+    },   
+
+    {
+        "name": "Cinematic",
+        "prompt": "cinematic still {prompt}. emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy",
+        "negative_prompt": "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured",
+    },
+
+    {
+        "name": "Anime",
+        "prompt": "anime artwork {prompt}. anime style, key visual, vibrant, studio anime, highly detailed",
+        "negative_prompt": "photo, deformed, black and white, realism, disfigured, low contrast",
+    },
+    {
+        "name": "3D Model",
+        "prompt": "professional 3d model {prompt}. octane render, highly detailed, volumetric, dramatic lighting",
+        "negative_prompt": "ugly, deformed, noisy, low poly, blurry, painting",
+    },
+    {
+        "name": "(No style)",
+        "prompt": "{prompt}",
+        "negative_prompt": "",
+    },
+]
+
+styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}
+STYLE_NAMES = list(styles.keys())
+DEFAULT_STYLE_NAME = "2560 x 1440"
+
+def apply_style(style_name: str, positive: str, negative: str = "") -> Tuple[str, str]:
+    p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
+    if not negative:
+        negative = ""
+    return p.replace("{prompt}", positive), n + negative
+
+
+
+    
 
-# Use environment variables for flexibility
-MODEL_ID = os.getenv("MODEL_ID", "Corcelio/mobius")
-MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "4096"))
+DESCRIPTION = """## MidJourney
+Drop your best results in the community: [rb.gy/klkbs7](http://rb.gy/klkbs7)
+"""
+
+
+
+
+
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>⚠️Running on CPU, This may not work on CPU.</p>"
+
+MAX_SEED = np.iinfo(np.int32).max
+CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES", "0") == "1"
+MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "2048"))
 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"))  # Allow generating multiple images at once
 
-# Determine device and load model outside of function for efficiency
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-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)
-
-# Torch compile for potential speedup (experimental)
-if USE_TORCH_COMPILE:
-    pipe.compile()
-
-# CPU offloading for larger RAM capacity (experimental)
-if ENABLE_CPU_OFFLOAD:
-    pipe.enable_model_cpu_offload()
 
-MAX_SEED = np.iinfo(np.int32).max
+NUM_IMAGES_PER_PROMPT = 1
+
+if torch.cuda.is_available():
+    pipe = DiffusionPipeline.from_pretrained(
+        "SG161222/RealVisXL_V3.0_Turbo",
+        torch_dtype=torch.float16,
+        use_safetensors=True,
+        add_watermarker=False,
+        variant="fp16"
+    )
+    pipe2 = DiffusionPipeline.from_pretrained(
+        "SG161222/RealVisXL_V2.02_Turbo",
+        torch_dtype=torch.float16,
+        use_safetensors=True,
+        add_watermarker=False,
+        variant="fp16"
+    )
+    if ENABLE_CPU_OFFLOAD:
+        pipe.enable_model_cpu_offload()
+        pipe2.enable_model_cpu_offload()
+    else:
+        pipe.to(device)    
+        pipe2.to(device)    
+        print("Loaded on Device!")
+    
+    if USE_TORCH_COMPILE:
+        pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+        pipe2.unet = torch.compile(pipe2.unet, mode="reduce-overhead", fullgraph=True)
+        print("Model Compiled!")
 
 def save_image(img):
     unique_name = str(uuid.uuid4()) + ".png"
@@ -47,553 +142,180 @@ def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
         seed = random.randint(0, MAX_SEED)
     return seed
 
-@spaces.GPU(duration=35, enable_queue=True)
+@spaces.GPU(enable_queue=True)
 def generate(
     prompt: str,
     negative_prompt: str = "",
     use_negative_prompt: bool = False,
-    seed: int = 1,
+    style: str = DEFAULT_STYLE_NAME,
+    seed: int = 0,
     width: int = 1024,
     height: int = 1024,
     guidance_scale: float = 3,
-    num_inference_steps: int = 30,
     randomize_seed: bool = False,
-    use_resolution_binning: bool = True, 
-    num_images: int = 1,  # Number of images to generate
+    use_resolution_binning: bool = True,
     progress=gr.Progress(track_tqdm=True),
 ):
+    if check_text(prompt, negative_prompt):
+        raise ValueError("Prompt contains restricted words.")
+    
+    prompt, negative_prompt = apply_style(style, prompt, negative_prompt)
     seed = int(randomize_seed_fn(seed, randomize_seed))
-    generator = torch.Generator(device=device).manual_seed(seed)
+    generator = torch.Generator().manual_seed(seed)
+
+    if not use_negative_prompt:
+        negative_prompt = ""  # type: ignore
+    negative_prompt += default_negative    
 
-    # Improved options handling
     options = {
-        "prompt": [prompt] * num_images,
-        "negative_prompt": [negative_prompt] * num_images if use_negative_prompt else None,
+        "prompt": prompt,
+        "negative_prompt": negative_prompt,
         "width": width,
         "height": height,
         "guidance_scale": guidance_scale,
-        "num_inference_steps": num_inference_steps,
+        "num_inference_steps": 25,
         "generator": generator,
+        "num_images_per_prompt": NUM_IMAGES_PER_PROMPT,
+        "use_resolution_binning": use_resolution_binning,
         "output_type": "pil",
     }
-
-    # Use resolution binning for faster generation with less VRAM usage
-    if use_resolution_binning:
-        options["use_resolution_binning"] = True
-
-    # Generate images potentially in batches
-    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)
+    
+    images = pipe(**options).images + pipe2(**options).images
 
     image_paths = [save_image(img) for img in images]
     return image_paths, seed
 
 examples = [
-    "a cat eating a piece of cheese",
-    "a ROBOT riding a BLUE horse on Mars, photorealistic, 4k",
-    "Ironman VS Hulk, ultrarealistic",
-    "Astronaut in a jungle, cold color palette, oil pastel, detailed, 8k",
-    "An alien holding a sign board containing the word 'Flash', futuristic, neonpunk",
-    "Kids going to school, Anime style"
+    "A closeup of a cat, a window, in a rustic cabin, close up, with a shallow depth of field, with a vintage film grain, in the style of Annie Leibovitz and in the style of Wes Anderson. --ar 85:128 --v 6.0 --style raw",
+    "Daria Morgendorffer the main character of the animated series Daria, serious expression, very excites sultry look, so hot girl, beautiful charismatic girl, so hot shot, a woman wearing eye glasses, gorgeous figure, interesting shapes, life-size figures",
+    "Dark green large leaves of anthurium, close up, photography, aerial view, in the style of unsplash, hasselblad h6d400c  --ar 85:128 --v 6.0 --style raw",
+    "Closeup of blonde woman depth of field, bokeh, shallow focus, minimalism, fujifilm xh2s with Canon EF lens, cinematic --ar 85:128 --v 6.0 --style raw"
 ]
 
 css = '''
 .gradio-container{max-width: 700px !important}
 h1{text-align:center}
-footer {
-    visibility: hidden
-}
-.wheel-and-hamster {
-  --dur: 1s;
-  position: relative;
-  width: 12em;
-  height: 12em;
-  font-size: 14px;
-}
-.wheel,
-.hamster,
-.hamster div,
-.spoke {
-  position: absolute;
-}
-.wheel,
-.spoke {
-  border-radius: 50%;
-  top: 0;
-  left: 0;
-  width: 100%;
-  height: 100%;
-}
-.wheel {
-  background: radial-gradient(100% 100% at center,hsla(0,0%,60%,0) 47.8%,hsl(0,0%,60%) 48%);
-  z-index: 2;
-}
-.hamster {
-  animation: hamster var(--dur) ease-in-out infinite;
-  top: 50%;
-  left: calc(50% - 3.5em);
-  width: 7em;
-  height: 3.75em;
-  transform: rotate(4deg) translate(-0.8em,1.85em);
-  transform-origin: 50% 0;
-  z-index: 1;
-}
-.hamster__head {
-  animation: hamsterHead var(--dur) ease-in-out infinite;
-  background: hsl(30,90%,55%);
-  border-radius: 70% 30% 0 100% / 40% 25% 25% 60%;
-  box-shadow: 0 -0.25em 0 hsl(30,90%,80%) inset,
-		0.75em -1.55em 0 hsl(30,90%,90%) inset;
-  top: 0;
-  left: -2em;
-  width: 2.75em;
-  height: 2.5em;
-  transform-origin: 100% 50%;
-}
-.hamster__ear {
-  animation: hamsterEar var(--dur) ease-in-out infinite;
-  background: hsl(0,90%,85%);
-  border-radius: 50%;
-  box-shadow: -0.25em 0 hsl(30,90%,55%) inset;
-  top: -0.25em;
-  right: -0.25em;
-  width: 0.75em;
-  height: 0.75em;
-  transform-origin: 50% 75%;
-}
-.hamster__eye {
-  animation: hamsterEye var(--dur) linear infinite;
-  background-color: hsl(0,0%,0%);
-  border-radius: 50%;
-  top: 0.375em;
-  left: 1.25em;
-  width: 0.5em;
-  height: 0.5em;
-}
-.hamster__nose {
-  background: hsl(0,90%,75%);
-  border-radius: 35% 65% 85% 15% / 70% 50% 50% 30%;
-  top: 0.75em;
-  left: 0;
-  width: 0.2em;
-  height: 0.25em;
-}
-.hamster__body {
-  animation: hamsterBody var(--dur) ease-in-out infinite;
-  background: hsl(30,90%,90%);
-  border-radius: 50% 30% 50% 30% / 15% 60% 40% 40%;
-  box-shadow: 0.1em 0.75em 0 hsl(30,90%,55%) inset,
-		0.15em -0.5em 0 hsl(30,90%,80%) inset;
-  top: 0.25em;
-  left: 2em;
-  width: 4.5em;
-  height: 3em;
-  transform-origin: 17% 50%;
-  transform-style: preserve-3d;
-}
-.hamster__limb--fr,
-.hamster__limb--fl {
-  clip-path: polygon(0 0,100% 0,70% 80%,60% 100%,0% 100%,40% 80%);
-  top: 2em;
-  left: 0.5em;
-  width: 1em;
-  height: 1.5em;
-  transform-origin: 50% 0;
-}
-.hamster__limb--fr {
-  animation: hamsterFRLimb var(--dur) linear infinite;
-  background: linear-gradient(hsl(30,90%,80%) 80%,hsl(0,90%,75%) 80%);
-  transform: rotate(15deg) translateZ(-1px);
-}
-.hamster__limb--fl {
-  animation: hamsterFLLimb var(--dur) linear infinite;
-  background: linear-gradient(hsl(30,90%,80%) 80%,hsl(0,90%,75%) 80%);
-  transform: rotate(-60deg) translateZ(-1px);
-}
-.hamster__limb--br,
-.hamster__limb--bl {
-  clip-path: polygon(0 0,100% 0,100% 30%,70% 80%,60% 100%,40% 100%,30% 80%);
-  top: 2.3em;
-  left: 2.8em;
-  width: 1.25em;
-  height: 2.5em;
-  transform-origin: 50% 10%;
-}
-.hamster__limb--br {
-  animation: hamsterBRLimb var(--dur) linear infinite;
-  background: linear-gradient(hsl(0,90%,75%) 40%,hsl(30,90%,80%) 40%);
-  transform: rotate(45deg) translateZ(-1px);
-}
-.hamster__limb--bl {
-  animation: hamsterBLLimb var(--dur) linear infinite;
-  background: linear-gradient(hsl(0,90%,75%) 40%,hsl(30,90%,80%) 40%);
-  transform: rotate(-30deg) translateZ(-1px);
-}
-.hamster__tail {
-  animation: hamsterTail var(--dur) linear infinite;
-  background: hsl(0,90%,85%);
-  border-radius: 0.25em 50% 50% 0.25em;
-  box-shadow: 0.1em 0.5em 0 hsl(30,90%,55%) inset,
-		0.1em -0.25em 0 hsl(30,90%,90%) inset;
-  top: 3em;
-  left: 6em;
-  width: 0.75em;
-  height: 0.75em;
-  transform: rotate(30deg) translateZ(-1px);
-}
-.spoke {
-  --s: 0.2;
-  background: hsl(0,0%,100%);
-  box-shadow: 0 0 0 0.2em hsl(0,0%,0%);
-  left: calc(50% - var(--s)/2);
-  width: var(--s);
-  height: var(--s);
-}
-.spoke:nth-child(1) {
-  --rotation: 15deg;
-  transform: rotate(var(--rotation));
-}
-.spoke:nth-child(2) {
-  --rotation: 45deg;
-  transform: rotate(var(--rotation));
-}
-.spoke:nth-child(3) {
-  --rotation: 75deg;
-  transform: rotate(var(--rotation));
-}
-.spoke:nth-child(4) {
-  --rotation: 105deg;
-  transform: rotate(var(--rotation));
-}
-.spoke:nth-child(5) {
-  --rotation: 135deg;
-  transform: rotate(var(--rotation));
-}
-.spoke:nth-child(6) {
-  --rotation: 165deg;
-  transform: rotate(var(--rotation));
-}
-.spoke:nth-child(7) {
-  --rotation: 195deg;
-  transform: rotate(var(--rotation));
-}
-.spoke:nth-child(8) {
-  --rotation: 225deg;
-  transform: rotate(var(--rotation));
-}
-.spoke:nth-child(9) {
-  --rotation: 255deg;
-  transform: rotate(var(--rotation));
-}
-.spoke:nth-child(10) {
-  --rotation: 285deg;
-  transform: rotate(var(--rotation));
-}
-.spoke:nth-child(11) {
-  --rotation: 315deg;
-  transform: rotate(var(--rotation));
-}
-.spoke:nth-child(12) {
-  --rotation: 345deg;
-  transform: rotate(var(--rotation));
-}
-
-@keyframes hamster {
-  50% {
-	transform: rotate(-4deg) translate(-0.8em,1.85em);
-  }
-}
-
-@keyframes hamsterHead {
-  50% {
-	transform: rotate(-8deg);
-  }
-}
-
-@keyframes hamsterEye {
-  50% {
-	transform: translateY(0.1em);
-  }
-}
-
-@keyframes hamsterEar {
-  50% {
-	transform: rotate(8deg);
-  }
-}
-
-@keyframes hamsterBody {
-  50% {
-	transform: rotate(2deg);
-  }
-}
-
-@keyframes hamsterFRLimb {
-  8%,70% {
-	transform: rotate(15deg) translateZ(-1px);
-  }
-  33% {
-	transform: rotate(-60deg) translateZ(-1px);
-  }
-  83% {
-	transform: rotate(45deg) translateZ(-1px);
-  }
-}
-
-@keyframes hamsterFLLimb {
-  8%,70% {
-	transform: rotate(-60deg) translateZ(-1px);
-  }
-  33% {
-	transform: rotate(15deg) translateZ(-1px);
-  }
-  83% {
-	transform: rotate(-45deg) translateZ(-1px);
-  }
-}
-
-@keyframes hamsterBRLimb {
-  0%,50% {
-	transform: rotate(45deg) translateZ(-1px);
-  }
-  25% {
-	transform: rotate(-30deg) translateZ(-1px);
-  }
-  75% {
-	transform: rotate(60deg) translateZ(-1px);
-  }
-}
-
-@keyframes hamsterBLLimb {
-  0%,50% {
-	transform: rotate(-30deg) translateZ(-1px);
-  }
-  25% {
-	transform: rotate(45deg) translateZ(-1px);
-  }
-  75% {
-	transform: rotate(-45deg) translateZ(-1px);
-  }
-}
-
-@keyframes hamsterTail {
-  50% {
-	transform: rotate(-30deg) translateZ(-1px);
-  }
-}
-
-#wrapper {
-  position: relative;
-  height: 100vh;
-  display: flex;
-  justify-content: center;
-  align-items: center;
-}
-.loading-container {
-  position: relative;
-  display: flex;
-  justify-content: center;
-  align-items: center;
-  width: 100%;
-  height: 100%;
-  top: 50%;
-  transform: translateY(-50%);
-}
-.hidden {
-  display: none;
-}
 '''
-
-html = '''
-<div id="wrapper">
-  <div class="loading-container">
-    <div class="wheel-and-hamster">
-      <div class="wheel">
-        <div class="spoke"></div>
-        <div class="spoke"></div>
-        <div class="spoke"></div>
-        <div class="spoke"></div>
-        <div class="spoke"></div>
-        <div class="spoke"></div>
-        <div class="spoke"></div>
-        <div class="spoke"></div>
-        <div class="spoke"></div>
-        <div class="spoke"></div>
-        <div class="spoke"></div>
-        <div class="spoke"></div>
-      </div>
-      <div class="hamster">
-        <div class="hamster__body">
-          <div class="hamster__head">
-            <div class="hamster__ear"></div>
-            <div class="hamster__eye"></div>
-            <div class="hamster__nose"></div>
-          </div>
-          <div class="hamster__limb hamster__limb--fr"></div>
-          <div class="hamster__limb hamster__limb--fl"></div>
-          <div class="hamster__limb hamster__limb--br"></div>
-          <div class="hamster__limb hamster__limb--bl"></div>
-          <div class="hamster__tail"></div>
-        </div>
-      </div>
-    </div>
-  </div>
-</div>
-<script>
-  // Wait for the Gradio app to load
-  document.addEventListener("DOMContentLoaded", function() {
-    const observer = new MutationObserver(function(mutationsList, observer) {
-      for (const mutation of mutationsList) {
-        if (mutation.type === "childList" && mutation.addedNodes.length > 0) {
-          // Check if Gradio has loaded by looking for a specific element
-          const gradioApp = document.querySelector("#root");
-          if (gradioApp) {
-            // Hide the loading animation and observer
-            document.querySelector(".loading-container").classList.add("hidden");
-            observer.disconnect();
-          }
-        }
-      }
-    });
-
-    // Start observing the body for changes
-    observer.observe(document.body, { childList: true, subtree: true });
-  });
-</script>
-'''
-
-block = gr.Blocks(css=css)
-
-with block as demo:
-    gr.HTML(html)
-    with gr.Column(elem_id="main-app"):
-        gr.Markdown(
-            """
-            # Generate images with Stable Diffusion XL
-            """
+with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(
+        value="Duplicate Space for private use",
+        elem_id="duplicate-button",
+        visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
+    )
+    with gr.Group():
+        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")
+        result = gr.Gallery(label="Result", columns=1, preview=True)
+    with gr.Accordion("Advanced options", open=False):
+        use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True, visible=True)
+        negative_prompt = gr.Text(
+            label="Negative prompt",
+            max_lines=1,
+            placeholder="Enter a negative prompt",
+            value="(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck",
+            visible=True,
+        )
+        with gr.Row():
+            num_inference_steps = gr.Slider(
+                label="Steps",
+                minimum=10,
+                maximum=60,
+                step=1,
+                value=30,
+            )
+        with gr.Row():
+            num_images_per_prompt = gr.Slider(
+                label="Images",
+                minimum=1,
+                maximum=5,
+                step=1,
+                value=2,
+            )
+        seed = gr.Slider(
+            label="Seed",
+            minimum=0,
+            maximum=MAX_SEED,
+            step=1,
+            value=0,
+            visible=True
         )
+        randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+        with gr.Row(visible=True):
+            width = gr.Slider(
+                label="Width",
+                minimum=512,
+                maximum=2048,
+                step=8,
+                value=1024,
+            )
+            height = gr.Slider(
+                label="Height",
+                minimum=512,
+                maximum=2048,
+                step=8,
+                value=1024,
+            )
         with gr.Row():
-            with gr.Column():
-                text = gr.Textbox(
-                    label="Prompt",
-                    placeholder="Enter your prompt",
-                    lines=1,
-                )
-                negative_text = gr.Textbox(
-                    label="Negative Prompt",
-                    placeholder="Enter negative prompt",
-                    lines=1,
-                )
-                negative_prompt_chk = gr.Checkbox(
-                    label="Use Negative Prompt",
-                    value=True
-                )
-                seed = gr.Number(
-                    label="Seed",
-                    value=1,
-                    precision=0
-                )
-                randomize_seed = gr.Checkbox(
-                    label="Randomize Seed",
-                    value=False
-                )
-                width = gr.Slider(
-                    label="Width",
-                    value=1024,
-                    minimum=64,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=8
-                )
-                height = gr.Slider(
-                    label="Height",
-                    value=1024,
-                    minimum=64,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=8
-                )
-                guidance_scale = gr.Slider(
-                    label="Guidance Scale",
-                    value=3,
-                    minimum=0,
-                    maximum=50,
-                    step=0.5
-                )
-                num_inference_steps = gr.Slider(
-                    label="Number of Inference Steps",
-                    value=30,
-                    minimum=1,
-                    maximum=100,
-                    step=1
-                )
-                use_resolution_binning = gr.Checkbox(
-                    label="Use Resolution Binning",
-                    value=True
-                )
-                num_images = gr.Number(
-                    label="Number of Images to Generate",
-                    value=1,
-                    minimum=1,
-                    maximum=10,
-                    step=1
-                )
-                generate_button = gr.Button("Generate Images")
-            with gr.Column():
-                gr.Label("Examples:")
-                for example in examples:
-                    gr.Label(f"- {example}")
-
-        generated_images = gr.Image(
-            label="Generated Images",
-            type="pil"  # Display the PIL image
+            guidance_scale = gr.Slider(
+                label="Guidance Scale",
+                minimum=0.1,
+                maximum=20.0,
+                step=0.1,
+                value=6,
+            )
+    with gr.Row(visible=True):
+        style_selection = gr.Radio(
+            show_label=True,
+            container=True,
+            interactive=True,
+            choices=STYLE_NAMES,
+            value=DEFAULT_STYLE_NAME,
+            label="Image Style",
         )
-
-        
-        # Define the first gr.Image component
-       # generated_images1 = gr.Image(
-        #    label="Generated Images 1",
-         #   type="PIL",  # Display the PIL image
-          #  source=None
-        #)
-        
-        # Define the second gr.Image component
-        #generated_images2 = gr.Image(
-         #   label="Generated Images 2",
-          #  type="PIL",  # Display the PIL image
-           # source=None
-       # )
-
-    def generate_images_interface():
-        args = {
-            "prompt": text.value,
-            "negative_prompt": negative_text.value if negative_prompt_chk.value else "",
-            "use_negative_prompt": negative_prompt_chk.value,
-            "seed": seed.value,
-            "width": int(width.value),
-            "height": int(height.value),
-            "guidance_scale": float(guidance_scale.value),
-            "num_inference_steps": int(num_inference_steps.value),
-            "randomize_seed": randomize_seed.value,
-            "use_resolution_binning": use_resolution_binning.value,
-            "num_images": int(num_images.value),
-            "progress": gr.Progress()
-        }
-        image_paths, _ = generate(**args)
-        images = [Image.open(image_path) for image_path in image_paths]
-        return images
-
-    def on_generate_click():
-        generated_images.set_value(generate_images_interface())
-
-    gr.Interface(
-        fn=on_generate_click,
-        live=True,
-        title="Diffusion Generator",
-        description="Generate images using Stable Diffusion XL.",
-        layout="vertical",
-        blocking=True
-    ).launch()
+    gr.Examples(
+        examples=examples,
+        inputs=prompt,
+        outputs=[result, seed],
+        fn=generate,
+        cache_examples=CACHE_EXAMPLES,
+    )
+
+    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=[
+            prompt,
+            negative_prompt,
+            use_negative_prompt,
+            style_selection,
+            seed,
+            width,
+            height,
+            guidance_scale,
+            randomize_seed,
+        ],
+        outputs=[result, seed],
+        api_name="run",
+    )
+
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch()