|
pip install torch torchvision torchaudio gradio diffusers optimum numpy |
|
|
|
from __future__ import annotations |
|
import os |
|
import random |
|
import gradio as gr |
|
import spaces |
|
import numpy as np |
|
import uuid |
|
from optimum.quanto import freeze, qfloat8, quantize |
|
from diffusers import PixArtAlphaPipeline, LCMScheduler |
|
import torch |
|
from typing import Tuple |
|
|
|
|
|
DESCRIPTION = """ # Instant Image |
|
### Super fast text to Image Generator. |
|
### <span style='color: red;'>You may change the steps from 4 to 8, if you didn't get satisfied results. |
|
### First Image processing takes time then images generate faster. |
|
""" |
|
if not torch.cuda.is_available(): |
|
DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>" |
|
|
|
MAX_SEED = np.iinfo(np.int32).max |
|
CACHE_EXAMPLES = torch.cuda.is_available() and os.getenv("CACHE_EXAMPLES", "1") == "1" |
|
MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "4192")) |
|
USE_TORCH_COMPILE = os.getenv("USE_TORCH_COMPILE", "1") == "1" |
|
ENABLE_CPU_OFFLOAD = os.getenv("ENABLE_CPU_OFFLOAD", "0") == "1" |
|
|
|
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": "Realistic", |
|
"prompt": "Photorealistic {prompt} . Ulta-realistic, professional, 4k, highly detailed", |
|
"negative_prompt": "drawing, painting, crayon, sketch, graphite, impressionist, noisy, blurry, soft, deformed, 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": "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": "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)" |
|
NUM_IMAGES_PER_PROMPT = 1 |
|
|
|
pipe = PixArtAlphaPipeline.from_pretrained( |
|
"PixArt-alpha/PixArt-LCM-XL-2-1024-MS", |
|
torch_dtype=torch.float16, |
|
use_safetensors=True, |
|
).to("cuda:0") |
|
|
|
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 |
|
|
|
if USE_TORCH_COMPILE: |
|
pipe.transformer = torch.compile(pipe.transformer, mode="reduce-overhead", fullgraph=True) |
|
print("Model Compiled!") |
|
|
|
def randomize_seed_fn(seed: int, randomize_seed: bool) -> int: |
|
if randomize_seed: |
|
seed = random.randint(0, MAX_SEED) |
|
return seed |
|
|
|
@spaces.GPU(duration=30) |
|
def generate( |
|
prompt: str, |
|
negative_prompt: str = "", |
|
style: str = DEFAULT_STYLE_NAME, |
|
use_negative_prompt: bool = False, |
|
seed: int = 0, |
|
width: int = 1024, |
|
height: int = 1024, |
|
inference_steps: int = 12, |
|
randomize_seed: bool = False, |
|
use_resolution_binning: bool = True, |
|
progress=gr.Progress(track_tqdm=True), |
|
): |
|
seed = int(randomize_seed_fn(seed, randomize_seed)) |
|
generator = torch.Generator().manual_seed(seed) |
|
|
|
if not use_negative_prompt: |
|
negative_prompt = None |
|
prompt, negative_prompt = apply_style(style, prompt, negative_prompt) |
|
|
|
image = pipe( |
|
prompt=prompt, |
|
negative_prompt=negative_prompt, |
|
width=width, |
|
height=height, |
|
guidance_scale=0, |
|
num_inference_steps=inference_steps, |
|
generator=generator, |
|
use_resolution_binning=use_resolution_binning, |
|
).images[0] |
|
return image, seed |
|
|
|
|
|
examples = [ |
|
"A Monkey with a happy face in the Sahara desert.", |
|
"Eiffel Tower was Made up of ICE.", |
|
"photo of 8k ultra realistic harbour, nreal engine 5, port, boats, sunset, beautiful light, full of colour, cinematic lighting, battered, trending on artstation, 4k, hyperrealistic, focused, extreme details", |
|
"Color photo of a corgi made of transparent glass, standing on the riverside in Yosemite National Park.", |
|
"A close-up photo of a woman. She wore a blue coat with a gray dress underneath and has blue eyes.", |
|
"A litter of golden retriever puppies playing in the snow. Their heads pop out of the snow, covered in.", |
|
"an astronaut sitting in a diner, eating fries, cinematic, analog film", |
|
] |
|
|
|
css = ''' |
|
.gradio-container{max-width: 560px !important} |
|
h1{text-align:center} |
|
footer { |
|
visibility: hidden |
|
} |
|
''' |
|
|
|
with gr.Blocks(css=css) as demo: |
|
gr.Markdown(DESCRIPTION) |
|
with gr.Row(equal_height=False): |
|
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", scale=0) |
|
result = gr.Image(label="Result") |
|
|
|
with gr.Accordion("Advanced options", open=False): |
|
with gr.Group(): |
|
with gr.Row(): |
|
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=True, |
|
) |
|
style_selection = gr.Radio( |
|
show_label=True, |
|
container=True, |
|
interactive=True, |
|
choices=STYLE_NAMES, |
|
value=DEFAULT_STYLE_NAME, |
|
label="Image Style", |
|
) |
|
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(visible=True): |
|
width = gr.Slider( |
|
label="Width", |
|
minimum=256, |
|
maximum=MAX_IMAGE_SIZE, |
|
step=32, |
|
value=1024, |
|
) |
|
height = gr.Slider( |
|
label="Height", |
|
minimum=256, |
|
maximum=MAX_IMAGE_SIZE, |
|
step=32, |
|
value=1024, |
|
) |
|
with gr.Row(): |
|
inference_steps = gr.Slider( |
|
label="Steps", |
|
minimum=4, |
|
maximum=20, |
|
step=1, |
|
value=8, |
|
) |
|
|
|
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, |
|
style_selection, |
|
use_negative_prompt, |
|
seed, |
|
width, |
|
height, |
|
inference_steps, |
|
randomize_seed, |
|
], |
|
outputs=[result, seed], |
|
api_name="run", |
|
) |
|
|
|
if __name__ == "__main__": |
|
demo.queue(max_size=200).launch() |
