Update app.py

app.py

@@ -1,59 +1,26 @@
-#!/usr/bin/env python
-#patch 0.01 ()
-# Permission is hereby granted, free of charge, to any person obtaining a copy
-# of this software and associated documentation files (the "Software"), to deal
-# in the Software without restriction, including without limitation the rights
-# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-# copies of the Software, and to permit persons to whom the Software is
-# furnished to do so, subject to the following conditions:
-#
-# ..
-
-import os
-import random
-import uuid
-from typing import Tuple
 import gradio as gr
 import numpy as np
-from PIL import Image
+import random
+
 import spaces
+from diffusers import DiffusionPipeline
 import torch
-from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
 
-DESCRIPTIONz= """## EPIC REALISM
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model_repo_id = "stabilityai/stable-diffusion-3.5-large-turbo"
 
-"""
-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
-
-MAX_SEED = np.iinfo(np.int32).max
+if torch.cuda.is_available():
+    torch_dtype = torch.bfloat16
+else:
+    torch_dtype = torch.float32
 
-if not torch.cuda.is_available():
-    DESCRIPTION += "\n<p>⚠️Running on CPU, This may not work on CPU.</p>"
+pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
+pipe = pipe.to(device)
 
 MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 1024
 
-USE_TORCH_COMPILE = 0
-ENABLE_CPU_OFFLOAD = 0
-
-if torch.cuda.is_available():
-    pipe = StableDiffusionXLPipeline.from_pretrained(
-        "SG161222/RealVisXL_V5.0_Lightning",
-        torch_dtype=torch.float16,
-        use_safetensors=True,
-    )
-    pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
-    pipe.load_lora_weights("prithivMLmods/Canopus-Realism-LoRA", weight_name="Canopus-Realism-LoRA.safetensors", adapter_name="rlms")
-    pipe.set_adapters("rlms")
-    pipe.to("cuda")
-
+# Define styles
 style_list = [
     {
         "name": "3840 x 2160",
@@ -77,208 +44,152 @@ style_list = [
     },
 ]
 
-styles = {k["name"]: (k["prompt"], k["negative_prompt"]) for k in style_list}
-
-DEFAULT_STYLE_NAME = "3840 x 2160"
-STYLE_NAMES = list(styles.keys())
-
-def apply_style(style_name: str, positive: str, negative: str = "") -> Tuple[str, str]:
-    if style_name in styles:
-        p, n = styles.get(style_name, styles[DEFAULT_STYLE_NAME])
-    else:
-        p, n = styles[DEFAULT_STYLE_NAME]
-
-    if not negative:
-        negative = ""
-    return p.replace("{prompt}", positive), n + negative
-
-@spaces.GPU(duration=60, enable_queue=True)
-def generate(
-    prompt: str,
-    negative_prompt: str = "",
-    use_negative_prompt: bool = False,
-    seed: int = 0,
-    width: int = 1024,
-    height: int = 1024,
-    guidance_scale: float = 3,
-    randomize_seed: bool = False,
-    style_name: str = DEFAULT_STYLE_NAME,
+STYLE_NAMES = [style["name"] for style in style_list]
+DEFAULT_STYLE_NAME = STYLE_NAMES[0]
+
+@spaces.GPU
+def infer(
+    prompt,
+    negative_prompt="",
+    seed=42,
+    randomize_seed=False,
+    width=1024,
+    height=1024,
+    guidance_scale=0.0,
+    num_inference_steps=4,
+    style="Style Zero",
     progress=gr.Progress(track_tqdm=True),
 ):
-    seed = int(randomize_seed_fn(seed, randomize_seed))
-
-    positive_prompt, effective_negative_prompt = apply_style(style_name, prompt, negative_prompt)
     
-    if not use_negative_prompt:
-        effective_negative_prompt = ""  # type: ignore
+    selected_style = next(s for s in style_list if s["name"] == style)
+    styled_prompt = selected_style["prompt"].format(prompt=prompt)
+    styled_negative_prompt = selected_style["negative_prompt"]
 
-    images = pipe(
-        prompt=positive_prompt,
-        negative_prompt=effective_negative_prompt,
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+
+    generator = torch.Generator().manual_seed(seed)
+
+    image = pipe(
+        prompt=styled_prompt,
+        negative_prompt=styled_negative_prompt,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
         width=width,
         height=height,
-        guidance_scale=guidance_scale,
-        num_inference_steps=20,
-        num_images_per_prompt=1,
-        cross_attention_kwargs={"scale": 0.65},
-        output_type="pil",
-    ).images
-    image_paths = [save_image(img) for img in images]
-    print(image_paths)
-    return image_paths, seed
+        generator=generator,
+    ).images[0]
+
+    return image, seed
 
 examples = [
-    "A man in ski mask, in the style of smokey background, androgynous, imaginative prison scenes, light indigo and black, close-up, michelangelo, street-savvy  --ar 125:187 --v 5.1 --style raw",
-    "Photography, front view, dynamic range, female model, upper-body, black T-shirt, dark khaki cargo pants, urban backdrop, dusk, dramatic sunlights, bokeh, cityscape, photorealism, natural, UHD --ar 9:16 --stylize 300"
+    "A capybara wearing a suit holding a sign that reads Hello World",
 ]
 
-css = '''
-.gradio-container{max-width: 585px !important}
-h1{text-align:center}
-footer {
-    visibility: hidden
+css = """
+#col-container {
+    margin: 0 auto;
+    max-width: 640px;
 }
-'''
+"""
 
-def load_predefined_images():
-    predefined_images = [
-        "assets/22222.png",
-        "assets/11111.png",
-        "assets/33333.png",
-        "assets/44444.png",
-        "assets/7.png",
-        "assets/8.png",
-        "assets/9.png",
-        "assets/10.png",
-        "assets/11.png",
-    ]
-    return predefined_images
+with gr.Blocks(css=css) as demo:
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(" # [Stable Diffusion 3.5 Large Turbo (8B)](https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo)")
+        gr.Markdown("[Learn more](https://stability.ai/news/introducing-stable-diffusion-3-5) about the Stable Diffusion 3.5 series. Try on [Stability AI API](https://platform.stability.ai/docs/api-reference#tag/Generate/paths/~1v2beta~1stable-image~1generate~1sd3/post), or [download model](https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo) to run locally with ComfyUI or diffusers.")
+        
+        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, variant="primary")
 
+        result = gr.Image(label="Result", show_label=False)
 
-with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
-    gr.Markdown(DESCRIPTIONz)  
-    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.Gallery(label="Result", columns=1, preview=True, show_label=False)
-    
-    with gr.Accordion("Advanced options", open=False, visible=False):
-        use_negative_prompt = gr.Checkbox(label="Use negative prompt", value=True)
-        negative_prompt = gr.Text(
-            label="Negative prompt",
-            lines=4,
-            max_lines=6,
-            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",
-            placeholder="Enter a negative prompt",
-            visible=True,
-        )
-        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=64,
-                value=1024,
+        with gr.Accordion("Advanced Settings", open=False):
+            negative_prompt = gr.Text(
+                label="Negative prompt",
+                max_lines=1,
+                placeholder="Enter a negative prompt",
+                visible=False,
             )
-            height = gr.Slider(
-                label="Height",
-                minimum=512,
-                maximum=2048,
-                step=64,
-                value=1024,
-            )
-        
-        with gr.Row():
-            guidance_scale = gr.Slider(
-                label="Guidance Scale",
-                minimum=0.1,
-                maximum=20.0,
-                step=0.1,
-                value=3.0,
+
+            seed = gr.Slider(
+                label="Seed",
+                minimum=0,
+                maximum=MAX_SEED,
+                step=1,
+                value=0,
             )
 
-        style_selection = gr.Radio(
-            show_label=True,
-            container=True,
-            interactive=True,
-            choices=STYLE_NAMES,
-            value=DEFAULT_STYLE_NAME,
-            label="Quality Style",
-        )
+            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
 
-    gr.Examples(
-        examples=examples,
-        inputs=prompt,
-        outputs=[result, seed],
-        fn=generate,
-        cache_examples=False,
-    )
-
-    use_negative_prompt.change(
-        fn=lambda x: gr.update(visible=x),
-        inputs=use_negative_prompt,
-        outputs=negative_prompt,
-        api_name=False,
-    )
+            style_selection = gr.Radio(
+                show_label=True,
+                container=True,
+                interactive=True,
+                choices=STYLE_NAMES,
+                value=DEFAULT_STYLE_NAME,
+                label="Quality Style",
+            )
 
+            with gr.Row():
+                width = gr.Slider(
+                    label="Width",
+                    minimum=512,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                )
+
+                height = gr.Slider(
+                    label="Height",
+                    minimum=512,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                )
+
+            with gr.Row():
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.0,
+                    maximum=7.5,
+                    step=0.1,
+                    value=0.0,
+                )
+
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=50,
+                    step=1,
+                    value=4,
+                )
+
+        gr.Examples(examples=examples, inputs=[prompt], outputs=[result, seed], fn=infer, cache_examples=True, cache_mode="lazy")
+        
     gr.on(
-        triggers=[
-            prompt.submit,
-            negative_prompt.submit,
-            run_button.click,
-        ],
-        fn=generate,
+        triggers=[run_button.click, prompt.submit],
+        fn=infer,
         inputs=[
             prompt,
             negative_prompt,
-            use_negative_prompt,
             seed,
+            randomize_seed,
             width,
             height,
             guidance_scale,
-            randomize_seed,
+            num_inference_steps,
             style_selection,
         ],
         outputs=[result, seed],
-        api_name="run",
     )
-    # Adding a predefined gallery section
-    
-    gr.Markdown("### Generated Images")
-    predefined_gallery = gr.Gallery(label="Generated Images", columns=3, show_label=False, value=load_predefined_images())
-    
-    gr.Markdown("**Disclaimer/Note:**")
-    
-    #gr.Markdown("🙀This space provides realistic image generation, which works better for human faces and portraits. Realistic trigger works properly, better for photorealistic trigger words, close-up shots, face diffusion, male, female characters.")
-   
-    #gr.Markdown("⚠️users are accountable for the content they generate and are responsible for ensuring it meets appropriate ethical standards.")
-    
-    gr.Markdown("""
-    <div style='text-align: justify;'>
-    🙀This space provides realistic image generation, which works better for human faces and portraits. Realistic trigger works properly, better for photorealistic trigger words, close-up shots, face diffusion, male, female characters.
-    </div>""")
-
-    gr.Markdown("""
-    <div style='text-align: justify;'>
-    ⚠️Users are accountable for the content they generate and are responsible for ensuring it meets appropriate ethical standards.
-    </div>""")
 
 if __name__ == "__main__":
-    demo.queue(max_size=30).launch()
+    demo.launch()