images / app.py
aimersion's picture
Update app.py
80a2167 verified
raw
history blame
4.88 kB
import gradio as gr
import numpy as np
import random
import spaces
import torch
import os
import time
from diffusers import DiffusionPipeline
from huggingface_hub import login
# Ensure sentencepiece is installed in your environment
try:
import sentencepiece
except ImportError:
raise ImportError("The 'sentencepiece' library is required but not installed. Please add it to your environment.")
# Access the API token securely from Hugging Face Secrets
hf_api_token = os.getenv("HF_API_TOKEN")
if hf_api_token:
login(token=hf_api_token)
else:
raise ValueError("Hugging Face API token not found in secrets.")
# Set the device and dtype
dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"
# Load the diffusion pipeline from the gated repository
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=dtype).to(device)
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 2048
@spaces.GPU()
def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, num_inference_steps=4, guidance_scale=7.5, progress=gr.Progress(track_tqdm=True)):
start_time = time.time()
if width > MAX_IMAGE_SIZE or height > MAX_IMAGE_SIZE:
raise ValueError("Image size exceeds the maximum allowed dimensions.")
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator().manual_seed(seed)
try:
image = pipe(
prompt=prompt,
width=width,
height=height,
num_inference_steps=num_inference_steps,
generator=generator,
guidance_scale=guidance_scale
).images[0]
except Exception as e:
print(f"Error generating image: {e}")
return None, seed, f"Error: {str(e)}"
# Check if it took too long
if time.time() - start_time > 60: # 60 seconds timeout
return None, seed, "Image generation took too long and was cancelled."
return image, seed, None
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"""# Custom Image Creator
12B param rectified flow transformer distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/) for 4 step generation
[[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1)]
""")
with gr.Row():
prompt = gr.Textbox(
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):
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():
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=50,
step=1,
value=4,
)
guidance_scale = gr.Slider(
label="Guidance Scale",
minimum=0.0,
maximum=20.0,
step=0.5,
value=7.5,
)
gr.Examples(
examples=examples,
fn=infer,
inputs=[prompt],
outputs=[result, seed],
cache_examples="lazy"
)
run_button.click(
fn=infer,
inputs=[prompt, seed, randomize_seed, width, height, num_inference_steps, guidance_scale],
outputs=[result, seed],
)
gr.Markdown("""
## Save Your Image
Right-click on the image and select 'Save As' to download the generated image.
""")
demo.launch()