File size: 5,814 Bytes
04ff8fc ab78c01 04ff8fc ab78c01 04ff8fc 88dc9bb c94fbf5 0934b8b 5b3714e c94fbf5 04ff8fc c94fbf5 04ff8fc c94fbf5 04ff8fc c94fbf5 62b1efd 8ddfacb c94fbf5 62b1efd c94fbf5 04ff8fc c94fbf5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 |
import os
import sys
sys.path.append("./")
import torch
from torchvision import transforms
from src.transformer import Transformer2DModel
from src.pipeline import Pipeline
from src.scheduler import Scheduler
from transformers import (
CLIPTextModelWithProjection,
CLIPTokenizer,
)
from diffusers import VQModel
import gradio as gr
import spaces
device = 'cuda' if torch.cuda.is_available() else 'cpu'
model_path = "MeissonFlow/Meissonic"
model = Transformer2DModel.from_pretrained(model_path, subfolder="transformer")
vq_model = VQModel.from_pretrained(model_path, subfolder="vqvae")
text_encoder = CLIPTextModelWithProjection.from_pretrained(model_path, subfolder="text_encoder")
tokenizer = CLIPTokenizer.from_pretrained(model_path, subfolder="tokenizer")
scheduler = Scheduler.from_pretrained(model_path, subfolder="scheduler")
pipe = Pipeline(vq_model, tokenizer=tokenizer, text_encoder=text_encoder, transformer=model, scheduler=scheduler)
pipe.to(device)
MAX_SEED = 2**32 - 1
MAX_IMAGE_SIZE = 1024
@spaces.GPU
def generate_image(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, progress=gr.Progress(track_tqdm=True)):
if randomize_seed or seed == 0:
seed = torch.randint(0, MAX_SEED, (1,)).item()
torch.manual_seed(seed)
image = pipe(
prompt=prompt,
negative_prompt=negative_prompt,
height=height,
width=width,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps
).images[0]
return image, seed
# Default negative prompt
default_negative_prompt = "worst quality, normal quality, low quality, low res, blurry, distortion, text, watermark, logo, banner, extra digits, cropped, jpeg artifacts, signature, username, error, sketch, duplicate, ugly, monochrome, horror, geometry, mutation, disgusting, bad anatomy, bad proportions, bad quality, deformed, disconnected limbs, out of frame, out of focus, dehydrated, disfigured, extra arms, extra limbs, extra hands, fused fingers, gross proportions, long neck, jpeg, malformed limbs, mutated, mutated hands, mutated limbs, missing arms, missing fingers, picture frame, poorly drawn hands, poorly drawn face, collage, pixel, pixelated, grainy, color aberration, amputee, autograph, bad illustration, beyond the borders, blank background, body out of frame, boring background, branding, cut off, dismembered, disproportioned, distorted, draft, duplicated features, extra fingers, extra legs, fault, flaw, grains, hazy, identifying mark, improper scale, incorrect physiology, incorrect ratio, indistinct, kitsch, low resolution"
css = """
#col-container {
margin: 0 auto;
max-width: 640px;
}
"""
examples = [
"Modern Architecture render with pleasing aesthetics.",
"Two actors are posing for a pictur with one wearing a black and white face paint.",
"A large body of water with a rock in the middle and mountains in the background.",
"A white and blue coffee mug with a picture of a man on it.",
"A statue of a man with a crown on his head.",
"A man in a yellow wet suit is holding a big black dog in the water.",
"A white table with a vase of flowers and a cup of coffee on top of it.",
"A woman stands on a dock in the fog.",
"A woman is standing next to a picture of another woman."
]
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown("# Meissonic Text-to-Image Generator")
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.Accordion("Advanced Settings", open=False):
negative_prompt = gr.Text(
label="Negative prompt",
max_lines=1,
placeholder="Enter a negative prompt",
value=default_negative_prompt,
)
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=1024,
)
height = gr.Slider(
label="Height",
minimum=256,
maximum=MAX_IMAGE_SIZE,
step=32,
value=1024,
)
with gr.Row():
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=20.0,
step=0.1,
value=9.0,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=100,
step=1,
value=50,
)
gr.Examples(examples=examples, inputs=[prompt])
gr.on(
triggers=[run_button.click, prompt.submit],
fn=generate_image,
inputs=[
prompt,
negative_prompt,
seed,
randomize_seed,
width,
height,
guidance_scale,
num_inference_steps,
],
outputs=[result, seed],
)
demo.launch() |