import gradio as gr
import numpy as np
import random
import torch
import spaces
from PIL import Image
from diffusers import FlowMatchEulerDiscreteScheduler
from optimization import optimize_pipeline_
from qwenimage.pipeline_qwenimage_edit_plus import QwenImageEditPlusPipeline
from qwenimage.transformer_qwenimage import QwenImageTransformer2DModel
from qwenimage.qwen_fa3_processor import QwenDoubleStreamAttnProcessorFA3
import math
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
from PIL import Image
import os
import gradio as gr
from gradio_client import Client, handle_file
import tempfile
# --- Model Loading ---
dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"
pipe = QwenImageEditPlusPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2509",
transformer= QwenImageTransformer2DModel.from_pretrained("linoyts/Qwen-Image-Edit-Rapid-AIO",
subfolder='transformer',
torch_dtype=dtype,
device_map='cuda'),torch_dtype=dtype).to(device)
pipe.load_lora_weights(
"dx8152/Qwen-Image-Edit-2509-Light_restoration",
weight_name="移除光影.safetensors", adapter_name="light_restoration"
)
pipe.set_adapters(["light_restoration"], adapter_weights=[1.])
pipe.fuse_lora(adapter_names=["light_restoration"], lora_scale=1.0)
pipe.unload_lora_weights()
pipe.transformer.__class__ = QwenImageTransformer2DModel
pipe.transformer.set_attn_processor(QwenDoubleStreamAttnProcessorFA3())
optimize_pipeline_(pipe, image=[Image.new("RGB", (1024, 1024)), Image.new("RGB", (1024, 1024))], prompt="prompt")
MAX_SEED = np.iinfo(np.int32).max
def build_light_restoration_prompt():
return "Remove the shadows and use soft lighting to relight the image"
@spaces.GPU
def infer_light_restoration(
image,
seed,
randomize_seed,
true_guidance_scale,
num_inference_steps,
height,
width,
progress=gr.Progress(track_tqdm=True)
):
prompt = build_light_restoration_prompt()
print(f"Generated Prompt: {prompt}")
if randomize_seed:
seed = random.randint(0, MAX_SEED)
generator = torch.Generator(device=device).manual_seed(seed)
# Choose input image
pil_images = []
if image is not None:
if isinstance(image, Image.Image):
pil_images.append(image.convert("RGB"))
elif hasattr(image, "name"):
pil_images.append(Image.open(image.name).convert("RGB"))
if len(pil_images) == 0:
raise gr.Error("Please upload an image first.")
result = pipe(
image=pil_images,
prompt=prompt,
height=height if height != 0 else None,
width=width if width != 0 else None,
num_inference_steps=num_inference_steps,
generator=generator,
true_cfg_scale=true_guidance_scale,
num_images_per_prompt=1,
).images[0]
return result, seed, prompt
# --- UI ---
css = '''
#col-container {
max-width: 900px;
margin: 0 auto;
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
}
.dark .progress-text{color: white !important}
#examples{max-width: 900px; margin: 0 auto; }
.gradio-container {
background: linear-gradient(135deg, #f5f7fa 0%, #c3cfe2 100%);
}
.gr-button-primary {
background: linear-gradient(135deg, #667eea 0%, #764ba2 100%) !important;
border: none !important;
border-radius: 12px !important;
padding: 12px 24px !important;
font-weight: 600 !important;
}
.gr-button {
border-radius: 12px !important;
padding: 10px 20px !important;
}
.gr-box {
border-radius: 16px !important;
box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1) !important;
}
'''
def update_dimensions_on_upload(image):
if image is None:
return 1024, 1024
original_width, original_height = image.size
if original_width > original_height:
new_width = 1024
aspect_ratio = original_height / original_width
new_height = int(new_width * aspect_ratio)
else:
new_height = 1024
aspect_ratio = original_width / original_height
new_width = int(new_height * aspect_ratio)
# Ensure dimensions are multiples of 8
new_width = (new_width // 8) * 8
new_height = (new_height // 8) * 8
return new_width, new_height
with gr.Blocks(theme=gr.themes.Soft(), css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown("# ✨ Shadow Removal & Relighting")
gr.Markdown("""
Remove shadows and apply soft lighting to your images
Using [dx8152's Light Restoration LoRA](https://huggingface.co/dx8152/Qwen-Image-Edit-2509-Light_restoration)
and [Phr00t/Qwen-Image-Edit-Rapid-AIO](https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO) for fast inference 💨
Built with [anycoder](https://huggingface.co/spaces/akhaliq/anycoder)
"""
)
with gr.Row():
with gr.Column(scale=1):
image = gr.Image(label="📸 Input Image", type="pil", height=500)
run_btn = gr.Button("✨ Remove Shadows & Relight", variant="primary", size="lg")
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)
true_guidance_scale = gr.Slider(label="Guidance Scale", minimum=1.0, maximum=10.0, step=0.1, value=1.0)
num_inference_steps = gr.Slider(label="Inference Steps", minimum=1, maximum=40, step=1, value=4)
height = gr.Slider(label="Height", minimum=256, maximum=2048, step=8, value=1024)
width = gr.Slider(label="Width", minimum=256, maximum=2048, step=8, value=1024)
with gr.Column(scale=1):
result = gr.Image(label="✨ Output Image", interactive=False, height=500)
prompt_preview = gr.Textbox(label="Prompt Used", interactive=False, value="Remove the shadows and use soft lighting to relight the image")
inputs = [
image,
seed, randomize_seed, true_guidance_scale, num_inference_steps, height, width
]
outputs = [result, seed, prompt_preview]
# Manual generation
run_btn.click(
fn=infer_light_restoration,
inputs=inputs,
outputs=outputs
)
# Image upload triggers dimension update
image.upload(
fn=update_dimensions_on_upload,
inputs=[image],
outputs=[width, height]
)
demo.launch(mcp_server=False)