Spaces:
Running
Running
File size: 6,205 Bytes
966325b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 |
import gradio as gr
import numpy as np
import random
import spaces
import torch
from diffusers import DiffusionPipeline, AutoencoderTiny, AutoencoderKL
from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5TokenizerFast
from live_preview_helpers import calculate_shift, retrieve_timesteps, flux_pipe_call_that_returns_an_iterable_of_images
import requests
import base64
import os
from PIL import Image
from io import BytesIO
from gradio_imageslider import ImageSlider # Assicurati di avere questa libreria installata
from loadimg import load_img # Assicurati che questa funzione sia disponibile
from dotenv import load_dotenv
# Carica le variabili di ambiente dal file .env
load_dotenv()
dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"
taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).to(device)
good_vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev", subfolder="vae", torch_dtype=dtype).to(device)
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=dtype, vae=taef1).to(device)
torch.cuda.empty_cache()
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 2048
pipe.flux_pipe_call_that_returns_an_iterable_of_images = flux_pipe_call_that_returns_an_iterable_of_images.__get__(pipe)
output_folder = 'output_images'
if not os.path.exists(output_folder):
os.makedirs(output_folder)
def numpy_to_pil(image):
"""Convert a numpy array to a PIL Image."""
if image.dtype == np.uint8: # Most common case
mode = "RGB"
else:
mode = "F" # Floating point
return Image.fromarray(image.astype('uint8'), mode)
def process_image(image):
image = numpy_to_pil(image) # Convert numpy array to PIL Image
buffered = BytesIO()
image.save(buffered, format="PNG")
img_str = base64.b64encode(buffered.getvalue()).decode('utf-8')
response = requests.post(
os.getenv('BACKEND_URL'),
files={"file": ("image.png", base64.b64decode(img_str), "image/png")}
)
result = response.json()
processed_image_b64 = result["processed_image"]
processed_image = Image.open(BytesIO(base64.b64decode(processed_image_b64)))
image_path = os.path.join(output_folder, "no_bg_image.png")
processed_image.save(image_path)
return (processed_image, image), image_path
@spaces.GPU(duration=75)
def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28,
progress=gr.Progress(track_tqdm=True)):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator().manual_seed(seed)
for img in pipe.flux_pipe_call_that_returns_an_iterable_of_images(
prompt=prompt,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
width=width,
height=height,
generator=generator,
output_type="pil",
good_vae=good_vae,
):
img_np = np.array(img)
processed_images, image_path = process_image(img_np)
yield processed_images[0], seed, processed_images[1], image_path
examples = [
"a tiny astronaut hatching from an egg on the moon",
"a cat holding a sign that says hello world",
"an anime illustration of a wiener schnitzel",
]
css = """
#col-container {
margin: 0 auto;
max-width: 520px;
}
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown(f"""# FLUX.1 [dev]
12B param rectified flow transformer guidance-distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/) [[non-commercial license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)] [[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1-dev)]
""")
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="Generated Image", show_label=False)
output_slider = ImageSlider(label="Processed Photo", type="pil")
output_file = gr.File(label="Output PNG file")
with gr.Accordion("Advanced Settings", open=False):
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=1,
maximum=15,
step=0.1,
value=3.5,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=50,
step=1,
value=28,
)
gr.Examples(
examples=examples,
fn=infer,
inputs=[prompt],
outputs=[result, seed, output_slider, output_file],
cache_examples="lazy"
)
gr.on(
triggers=[run_button.click, prompt.submit],
fn=infer,
inputs=[prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
outputs=[result, seed, output_slider, output_file]
)
demo.launch() |