import random
import os
import uuid
from datetime import datetime
import gradio as gr
import numpy as np
import spaces
import torch
from diffusers import DiffusionPipeline
from PIL import Image
# Create permanent storage directory
SAVE_DIR = "saved_images" # Gradio will handle the persistence
if not os.path.exists(SAVE_DIR):
os.makedirs(SAVE_DIR, exist_ok=True)
device = "cuda" if torch.cuda.is_available() else "cpu"
repo_id = "black-forest-labs/FLUX.1-dev"
adapter_id = "seawolf2357/flux-lora-car-rolls-royce"
pipeline = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.bfloat16)
pipeline.load_lora_weights(adapter_id)
pipeline = pipeline.to(device)
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024
def save_generated_image(image, prompt):
# Generate unique filename with timestamp
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
unique_id = str(uuid.uuid4())[:8]
filename = f"{timestamp}_{unique_id}.png"
filepath = os.path.join(SAVE_DIR, filename)
# Save the image
image.save(filepath)
# Save metadata
metadata_file = os.path.join(SAVE_DIR, "metadata.txt")
with open(metadata_file, "a", encoding="utf-8") as f:
f.write(f"{filename}|{prompt}|{timestamp}\n")
return filepath
def load_generated_images():
if not os.path.exists(SAVE_DIR):
return []
# Load all images from the directory
image_files = [os.path.join(SAVE_DIR, f) for f in os.listdir(SAVE_DIR)
if f.endswith(('.png', '.jpg', '.jpeg', '.webp'))]
# Sort by creation time (newest first)
image_files.sort(key=lambda x: os.path.getctime(x), reverse=True)
return image_files
def load_predefined_images():
# Return empty list since we're not using predefined images
return []
@spaces.GPU(duration=120)
def inference(
prompt: str,
seed: int,
randomize_seed: bool,
width: int,
height: int,
guidance_scale: float,
num_inference_steps: int,
lora_scale: float,
progress: gr.Progress = gr.Progress(track_tqdm=True),
):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator(device=device).manual_seed(seed)
image = pipeline(
prompt=prompt,
guidance_scale=guidance_scale,
num_inference_steps=num_inference_steps,
width=width,
height=height,
generator=generator,
joint_attention_kwargs={"scale": lora_scale},
).images[0]
# Save the generated image
filepath = save_generated_image(image, prompt)
# Return the image, seed, and updated gallery
return image, seed, load_generated_images()
examples = [
"A majestic Rolls-Royce Phantom parked in front of a grand Mediterranean villa at golden hour, its iconic Spirit of Ecstasy gleaming in the sunset. The celestial silver paintwork catches the warm light, while blooming jasmine and bougainvillea frame the scene. The handcrafted details of the grill reflect the sophistication of old-world luxury. [trigger]",
"A Rolls-Royce Ghost gliding through misty London streets at dawn, its starlight headliner illuminating the bespoke interior. Rain droplets on the flawless black paint create a constellation of reflections, while the illuminated Pantheon grille casts a gentle glow on the wet cobblestones. [trigger]",
"A pristine Rolls-Royce Cullinan ascending a snow-covered Alpine road, its Arctic White exterior complementing the winter landscape. The SUV's powerful presence is highlighted by the rising sun glinting off its chrome details, while the heated interior cocoons its passengers in ultimate luxury. [trigger]",
"A vintage Rolls-Royce Silver Cloud III positioned in the courtyard of a historic English manor, surrounded by perfectly manicured topiary gardens. The classic two-tone paint scheme gleams under the afternoon sun, while its polished wooden dashboard and leather interior speak of timeless craftsmanship. [trigger]",
"A Rolls-Royce Wraith Black Badge cruising along the Monaco coastline at twilight, its dark chrome finish absorbing the neon lights of the principality. The sleek fastback silhouette cuts through the Mediterranean air, while its illuminated starlight roof mirrors the emerging stars above. [trigger]",
"A bespoke Rolls-Royce Dawn convertible beneath cherry blossoms in Kyoto, its custom champagne paintwork harmonizing with the falling petals. The handstitched leather interior matches the color of the sunset, while the polished teak deck echoes the traditional architecture of nearby temples. [trigger]"
]
css = """
footer {
visibility: hidden;
}
"""
with gr.Blocks(theme="Yntec/HaleyCH_Theme_Orange", css=css, analytics_enabled=False) as demo:
gr.HTML(' Flux lora RollsRoyce
')
gr.HTML('')
with gr.Tabs() as tabs:
with gr.Tab("Generation"):
with gr.Column(elem_id="col-container"):
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", show_label=False)
with gr.Accordion("Advanced Settings", open=False):
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=MAX_SEED,
step=1,
value=42,
)
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=768,
)
with gr.Row():
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=10.0,
step=0.1,
value=3.5,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=50,
step=1,
value=30,
)
lora_scale = gr.Slider(
label="LoRA scale",
minimum=0.0,
maximum=1.0,
step=0.1,
value=1.0,
)
gr.Examples(
examples=examples,
inputs=[prompt],
outputs=[result, seed],
)
with gr.Tab("Gallery"):
gallery_header = gr.Markdown("### Generated Images Gallery")
generated_gallery = gr.Gallery(
label="Generated Images",
columns=6,
show_label=False,
value=load_generated_images(),
elem_id="generated_gallery",
height="auto"
)
refresh_btn = gr.Button("🔄 Refresh Gallery")
# Event handlers
def refresh_gallery():
return load_generated_images()
refresh_btn.click(
fn=refresh_gallery,
inputs=None,
outputs=generated_gallery,
)
gr.on(
triggers=[run_button.click, prompt.submit],
fn=inference,
inputs=[
prompt,
seed,
randomize_seed,
width,
height,
guidance_scale,
num_inference_steps,
lora_scale,
],
outputs=[result, seed, generated_gallery],
)
demo.queue()
demo.launch()