#!/usr/bin/env python #Patch0.1x import os import random import uuid import json import gradio as gr import numpy as np from PIL import Image import spaces import torch 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 #End of the - Prompt Con style_list = [ { "name": "3840 x 2160", "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", }, { "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": "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 = "3840 x 2160" 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 DESCRIPTION = """## STABLE HAMSTER """ if not torch.cuda.is_available(): DESCRIPTION += "\n

⚠️Running on CPU, This may not work on CPU.

" 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" device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") NUM_IMAGES_PER_PROMPT = 1 if torch.cuda.is_available(): pipe = DiffusionPipeline.from_pretrained( "yodayo-ai/kivotos-xl-2.0", torch_dtype=torch.float16, use_safetensors=True, add_watermarker=False, variant="fp16" ) pipe2 = DiffusionPipeline.from_pretrained( "Yntec/3Danimation", 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" 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(enable_queue=True) def generate( prompt: str, negative_prompt: str = "", use_negative_prompt: bool = False, style: str = DEFAULT_STYLE_NAME, seed: int = 0, width: int = 1024, height: int = 1024, guidance_scale: float = 3, randomize_seed: bool = False, 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().manual_seed(seed) if not use_negative_prompt: negative_prompt = "" # type: ignore negative_prompt += default_negative options = { "prompt": prompt, "negative_prompt": negative_prompt, "width": width, "height": height, "guidance_scale": guidance_scale, "num_inference_steps": 25, "generator": generator, "num_images_per_prompt": NUM_IMAGES_PER_PROMPT, "use_resolution_binning": use_resolution_binning, "output_type": "pil", } images = pipe(**options).images + pipe2(**options).images image_paths = [save_image(img) for img in images] return image_paths, seed examples = [ "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: 580px !important} h1{text-align:center} ''' 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, 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(): 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=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()