import gradio as gr import numpy as np import random from diffusers import DiffusionPipeline import torch from typing import Tuple style_list = [ { "name": "(No style)", "prompt": "{prompt}", "negative_prompt": "", }, { "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": "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": "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": "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", }, ] 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]) return p.replace("{prompt}", positive), n + negative 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) 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): if randomize_seed: seed = random.randint(0, MAX_SEED) generator = torch.Generator().manual_seed(seed) 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] return image examples = [ "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", "An astronaut riding a green horse", "A delicious ceviche cheesecake slice", ] css=""" #col-container { margin: 0 auto; max-width: 520px; } """ if torch.cuda.is_available(): power_device = "GPU" else: power_device = "CPU" 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.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.Image(label="Result", show_label=False) with gr.Accordion("Advanced Settings", open=False): style_selection = gr.Radio( show_label=True, container=True, interactive=True, choices=STYLE_NAMES, value=DEFAULT_STYLE_NAME, label='Image Style' ) negative_prompt = gr.Textbox( label="Enter your negative prompt", show_label=False, max_lines=1, placeholder="Enter a negative prompt", elem_id="negative-prompt-text-input", ) 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=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] ) run_button.click( fn = infer, inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps], outputs = [result] ) demo.queue().launch()