Update app.py

app.py

@@ -1,70 +1,312 @@
+#!/usr/bin/env python
+import os
+import random
+import uuid
 import gradio as gr
 import numpy as np
-import random
-from diffusers import DiffusionPipeline
+from PIL import Image
+import spaces
+from typing import Tuple
 import torch
+from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
 
-if torch.cuda.is_available():
-    torch.cuda.max_memory_allocated(device=device)
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
-    pipe.enable_xformers_memory_efficient_attention()
-    pipe = pipe.to(device)
-else: 
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
-    pipe = pipe.to(device)
+DESCRIPTION = """# InterDiffusion-3.8"""
 
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
 
-def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
+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)
-        
-    generator = torch.Generator().manual_seed(seed)
+    return seed
+
+
+
+MAX_SEED = np.iinfo(np.int32).max
+
+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
+
+USE_TORCH_COMPILE = 0
+ENABLE_CPU_OFFLOAD = 0
+
+
+
+
+if torch.cuda.is_available():
+    pipe = StableDiffusionXLPipeline.from_pretrained(
+        "cutycat2000x/InterDiffusion-3.8",
+        torch_dtype=torch.float16,
+        use_safetensors=True,
+    )
+    pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)  
+    pipe.load_lora_weights("cutycat2000x/InterDiffusion-LoRA", weight_name="lora.safetensors", adapter_name="InterDiffusion-3.8")
+    pipe.set_adapters("InterDiffusion-3.8")
+    pipe.to("cuda")
+
+
+
+
+    
+style_list = [
+
+    {
+        "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": "8K",
+    "prompt": "hyper-realistic 8K image of {prompt} . ultra-detailed, lifelike, high-resolution, sharp, vibrant colors, photorealistic",
+    "negative_prompt": "cartoonish, low resolution, blurry, simplistic, abstract, deformed, ugly",
+    },
     
-    image = pipe(
-        prompt = prompt, 
-        negative_prompt = negative_prompt,
-        guidance_scale = guidance_scale, 
-        num_inference_steps = num_inference_steps, 
-        width = width, 
-        height = height,
-        generator = generator
-    ).images[0] 
+    {
+    "name": "4K",
+    "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": "HDR",
+    "prompt": "HDR photo of {prompt} . high dynamic range, vivid colors, sharp contrast, realistic, detailed, high resolution, professional",
+    "negative_prompt": "dull, low contrast, blurry, unrealistic, cartoonish, ugly, deformed",
+    },
+  
+    {
+        "name": "Photographic",
+        "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": "Disney Style",
+    "prompt": "Disney style cartoon of {prompt} . whimsical, colorful, expressive, magical, highly detailed, animated movie style, family-friendly",
+    "negative_prompt": "realistic, photographic, detailed textures, dark, scary, ugly, deformed",
+    },
+    
+    {
+        "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": "Manga",
+        "prompt": "manga style {prompt} . vibrant, high-energy, detailed, iconic, Japanese comic style",
+        "negative_prompt": "ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, Western comic style",
+    },
+    {
+        "name": "Digital Art",
+        "prompt": "concept art {prompt} . digital artwork, illustrative, painterly, matte painting, highly detailed",
+        "negative_prompt": "photo, photorealistic, realism, ugly",
+    },
+    {
+        "name": "Pixel art",
+        "prompt": "pixel-art {prompt} . low-res, blocky, pixel art style, 8-bit graphics",
+        "negative_prompt": "sloppy, messy, blurry, noisy, highly detailed, ultra textured, photo, realistic",
+    },
+    {
+        "name": "Fantasy art",
+        "prompt": "ethereal fantasy concept art of  {prompt} . magnificent, celestial, ethereal, painterly, epic, majestic, magical, fantasy art, cover art, dreamy",
+        "negative_prompt": "photographic, realistic, realism, 35mm film, dslr, cropped, frame, text, deformed, glitch, noise, noisy, off-center, deformed, cross-eyed, closed eyes, bad anatomy, ugly, disfigured, sloppy, duplicate, mutated, black and white",
+    },
+
+    {
+    "name": "Cyberpunk",
+    "prompt": "cyberpunk style {prompt} . neon lights, futuristic, gritty, dark, highly detailed, urban, high contrast, high-tech, dystopian",
+    "negative_prompt": "natural, bright, cheerful, plain, simplistic, ugly, deformed",
+    },
+
+    {
+    "name": "Graffiti Art",
+    "prompt": "graffiti art of {prompt} . street art style, vibrant colors, bold lines, urban, edgy, highly detailed, spray paint texture",
+    "negative_prompt": "realistic, photographic, plain, clean, formal, ugly, deformed",
+    },
     
-    return image
+    {
+        "name": "Neonpunk",
+        "prompt": "neonpunk style {prompt} . cyberpunk, vaporwave, neon, vibes, vibrant, stunningly beautiful, crisp, detailed, sleek, ultramodern, magenta highlights, dark purple shadows, high contrast, cinematic, ultra detailed, intricate, professional",
+        "negative_prompt": "painting, drawing, illustration, glitch, deformed, mutated, cross-eyed, ugly, disfigured",
+    },
+    {
+        "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": "Steampunk",
+    "prompt": "steampunk {prompt} . Victorian era, mechanical, gears, steam-powered, brass, intricate, detailed, retrofuturistic",
+    "negative_prompt": "modern, digital, plain, clean, simplistic, messy, ugly, deformed, low contrast",
+    },
+
+    {
+    "name": "Retro Futurism",
+    "prompt": "retro-futuristic {prompt} . 1960s sci-fi, sleek, bold colors, imaginative, space age, mid-century modern, detailed",
+    "negative_prompt": "realistic, modern, plain, clean, minimalist, messy, ugly, deformed",
+    },
+
+    {
+    "name": "Baroque",
+    "prompt": "baroque style {prompt} . ornate, dramatic, rich colors, contrast, grandeur, detailed, historical, 17th century",
+    "negative_prompt": "modern, plain, clean, minimalist, simplistic, ugly, deformed",
+    },
+ 
+    {
+    "name": "Surreal Art",
+    "prompt": "surreal art of {prompt} . dreamlike, abstract, otherworldly, bizarre, fantastical, imaginative, highly detailed, Salvador Dalí inspired",
+    "negative_prompt": "realistic, photographic, normal, plain, ordinary, ugly, deformed, low contrast",
+    },
+
+    {
+    "name": "Impressionist",
+    "prompt": "impressionist painting of {prompt} . vibrant, textured, brush strokes, light, movement, Monet inspired, painterly, colorful",
+    "negative_prompt": "realistic, photographic, detailed, digital, sharp, clean, cartoon, ugly, deformed",
+    },
+
+    {
+    "name": "Art Deco",
+    "prompt": "art deco style {prompt} . elegant, geometric, rich colors, decorative, 1920s, luxury, sophisticated, stylish, highly detailed",
+    "negative_prompt": "modern, plain, minimalist, messy, disorganized, ugly, deformed, low contrast",
+    },
+
+    {
+    "name": "Minimalist",
+    "prompt": "minimalist {prompt} . clean, simple, sparse, monochrome, elegant, subtle, understated, high contrast",
+    "negative_prompt": "detailed, busy, cluttered, colorful, messy, noisy, ugly, deformed",
+    },
+
+    {
+    "name": "Abstract",
+    "prompt": "abstract {prompt} . expressive, non-representational, bold colors, shapes, forms, textures, highly detailed, modern art",
+    "negative_prompt": "realistic, photographic, detailed, recognizable, plain, ugly, deformed",
+    },
+
+    {
+    "name": "Gothic",
+    "prompt": "gothic {prompt} . dark, eerie, ornate, medieval, mysterious, detailed, shadowy, dramatic, gothic architecture",
+    "negative_prompt": "bright, colorful, modern, plain, clean, minimalist, ugly, deformed",
+    },
+
+    {
+    "name": "Vaporwave",
+    "prompt": "vaporwave {prompt} . neon colors, 80s aesthetics, retro, synthwave, glitch art, nostalgic, surreal, highly detailed",
+    "negative_prompt": "modern, plain, realistic, clean, simple, ugly, deformed",
+    },
+
+    {
+    "name": "HDR Urban",
+    "prompt": "HDR urban scene of {prompt} . high dynamic range, vibrant, detailed, sharp contrast, cityscape, realistic, high resolution, professional",
+    "negative_prompt": "dull, low contrast, blurry, unrealistic, cartoonish, ugly, deformed",
+    },
+
+    {
+    "name": "Classic Oil Painting",
+    "prompt": "classic oil painting of {prompt} . rich textures, brush strokes, warm colors, realistic, traditional, highly detailed, canvas texture",
+    "negative_prompt": "photographic, modern, simplistic, digital, cartoonish, ugly, deformed",
+    },
+
+    {
+    "name": "HDR Nature",
+    "prompt": "HDR nature scene of {prompt} . high dynamic range, vivid colors, detailed, sharp contrast, realistic, high resolution, professional",
+    "negative_prompt": "dull, low contrast, blurry, unrealistic, cartoonish, ugly, deformed",
+    },
+
+    {
+    "name": "Modern Advertisement Logo",
+    "prompt": "high-resolution modern advertisement logo of {prompt} . sleek, minimalist, vibrant colors, clean lines, sharp, professional, eye-catching",
+    "negative_prompt": "vintage, messy, low resolution, blurry, dull, deformed, ugly",
+
+    },
+
+    {
+        "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 = "(No style)"
+
+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
+
+@spaces.GPU(enable_queue=True)
+def generate(
+    prompt: str,
+    negative_prompt: str = "",
+    style: str = DEFAULT_STYLE_NAME,
+    use_negative_prompt: bool = False,
+    num_inference_steps: int = 30,
+    num_images_per_prompt: int = 2,
+    seed: int = 0,
+    width: int = 1024,
+    height: int = 1024,
+    guidance_scale: float = 3,
+    randomize_seed: bool = False,
+    progress=gr.Progress(track_tqdm=True),
+):
+
+    
+    seed = int(randomize_seed_fn(seed, randomize_seed))
+
+    if not use_negative_prompt:
+        negative_prompt = ""  # type: ignore
+    prompt, negative_prompt = apply_style(style, prompt, negative_prompt)
+
+    images = pipe(
+        prompt=prompt,
+        negative_prompt=negative_prompt,
+        width=width,
+        height=height,
+        guidance_scale=guidance_scale,
+        num_inference_steps=num_inference_steps,
+        num_images_per_prompt=num_images_per_prompt,
+        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
 
 examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
+    "A castle sitting on top of a snow covered mountain, inspired by Raphael Lacoste, medieval village on the plains, wintry rumpelstiltskin, full res, ingame image, wallpaper, cliffside town, highdetailed, winter storm, thomas kincade, concept illustartion, tuomas korpi and wlop, concept art",
+    "Lost city of Atlantis, chaotic ocean, detailed, octane render, tall architectures, sharks + sealife, fish + corral, Unreal engine 5, 8k, --q 5 --s 7500 --ar 4:5",
+    "Photo illustration from a world in the clouds, in the style of tanya shatseva, the stars art group (xing xing), meghan howland, dark indigo and light cyan, mind-bending sculptures, realistic hyper-detail, fluid simplicity --ar 63:128 --stylize 750 --v 6",
+    "A confident woman detective with a sleek bobbed hairstyle cut and observant brown eyes, wearing a gray detective coat, is examining clues in a dimly lit crime scene, half-body:: portraited, face drawn by the masterful artist Wes Anderson, detailed, against a gritty background --ar 2:3 --niji 5 --style expressive --q 2"
 ]
 
-css="""
-#col-container {
-    margin: 0 auto;
-    max-width: 520px;
+css = '''
+.gradio-container{max-width: 560px !important}
+h1{text-align:center}
+footer {
+    visibility: hidden
 }
-"""
+'''
 
-if torch.cuda.is_available():
-    power_device = "GPU"
-else:
-    power_device = "CPU"
+with gr.Blocks(css=css, theme="xiaobaiyuan/theme_brief") as demo:
+    gr.Markdown(DESCRIPTION)
+    gr.DuplicateButton(
+        value="Duplicate Space for private use",
+        elem_id="duplicate-button",
+        visible=False,
+    )
 
-with gr.Blocks(css=css) as demo:
-    
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""
-        # Text-to-Image Gradio Template
-        Currently running on {power_device}.
-        """)
-        
+    with gr.Group():
         with gr.Row():
-            
             prompt = gr.Text(
                 label="Prompt",
                 show_label=False,
@@ -72,75 +314,117 @@ with gr.Blocks(css=css) as demo:
                 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):
-            
-            negative_prompt = gr.Text(
+            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=False, visible=True)
+        negative_prompt = gr.Text(
                 label="Negative prompt",
                 max_lines=1,
                 placeholder="Enter a negative prompt",
-                visible=False,
+                visible=True,
             )
-            
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
+        with gr.Row():
+            num_inference_steps = gr.Slider(
+                label="Steps",
+                minimum=10,
+                maximum=60,
                 step=1,
-                value=0,
+                value=30,
             )
-            
-            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=512,
-                )
-                
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
-            
-            with gr.Row():
-                
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,
-                )
-                
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=12,
-                    step=1,
-                    value=2,
-                )
-        
-        gr.Examples(
-            examples = examples,
-            inputs = [prompt]
+        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():
+            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",
+            )
+        
+
+    gr.Examples(
+        examples=examples,
+        inputs=prompt,
+        outputs=[result, seed],
+        fn=generate,
+        cache_examples=False,
+    )
 
-    run_button.click(
-        fn = infer,
-        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result]
+    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,
+            style_selection,
+            use_negative_prompt,
+            num_inference_steps,
+            num_images_per_prompt,
+            seed,
+            width,
+            height,
+            guidance_scale,
+            randomize_seed,
+        ],
+        outputs=[result, seed],
+        api_name="run",
+    )
+
+
 
-demo.queue().launch()
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch(show_api=False, debug=False)