app.py

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

from huggingface_hub import InferenceClient
import math
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file

import os
import base64
from io import BytesIO
import json
import time  # Added for history update delay

from gradio_client import Client, handle_file
import tempfile
from PIL import Image
import os
import gradio as gr

    
def encode_image(pil_image):
    import io
    buffered = io.BytesIO()
    pil_image.save(buffered, format="PNG")
    return base64.b64encode(buffered.getvalue()).decode("utf-8")

# --- 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(
        "lovis93/next-scene-qwen-image-lora-2509", 
        weight_name="next-scene_lora-v2-3000.safetensors", adapter_name="next-scene"
    )
pipe.set_adapters(["next-scene"], adapter_weights=[1.])
pipe.fuse_lora(adapter_names=["next-scene"], lora_scale=1.)
pipe.unload_lora_weights()


# Apply the same optimizations from the first version
pipe.transformer.__class__ = QwenImageTransformer2DModel
pipe.transformer.set_attn_processor(QwenDoubleStreamAttnProcessorFA3())

# --- Ahead-of-time compilation ---
optimize_pipeline_(pipe, image=[Image.new("RGB", (1024, 1024)), Image.new("RGB", (1024, 1024))], prompt="prompt")

# --- UI Constants and Helpers ---
MAX_SEED = np.iinfo(np.int32).max

def use_output_as_input(output_images):
    """Convert output images to input format for the gallery"""
    if output_images is None or len(output_images) == 0:
        return []
    return output_images


# --- Main Inference Function (with hardcoded negative prompt) ---
@spaces.GPU(duration=120)
def infer(
    image,
    prompt,
    seed=120,
    randomize_seed=False,
    true_guidance_scale=1.0,
    num_inference_steps=4,
    progress=gr.Progress(track_tqdm=True),
):
    """
    Generates an image using the local Qwen-Image diffusers pipeline.
    """
    # Hardcode the negative prompt as requested
    negative_prompt = " "
    
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)

    # Set up the generator for reproducibility
    generator = torch.Generator(device=device).manual_seed(seed)
    
    print(f"Calling pipeline with prompt: '{prompt}'")
    print(f"Negative Prompt: '{negative_prompt}'")
    print(f"Seed: {seed}, Steps: {num_inference_steps}, Guidance: {true_guidance_scale}")

    # Generate the image
    images = pipe(
        image,
        prompt=prompt,
        negative_prompt=negative_prompt,
        num_inference_steps=num_inference_steps,
        generator=generator,
        true_cfg_scale=true_guidance_scale,
        num_images_per_prompt=1
    ).images
    
    return images[0], seed

# --- Examples and UI Layout ---
examples = []

css = """
#col-container {
    margin: 0 auto;
    max-width: 1024px;
}
#edit_text{
    margin-top: -62px !important
}
"""

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.HTML('<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/qwen_image_edit_logo.png" alt="Qwen-Image Logo" width="400" style="display: block; margin: 0 auto;">')
        gr.Markdown("[Learn more](https://github.com/QwenLM/Qwen-Image) about the Qwen-Image series. Try on [Qwen Chat](https://chat.qwen.ai/), or [download model](https://huggingface.co/Qwen/Qwen-Image-Edit) to run locally with ComfyUI or diffusers.")
        with gr.Row():
            with gr.Column():
                input_image = gr.Image(label="Input Image", show_label=False, type="pil")

            result = gr.Image(label="Result", show_label=False, type="pil")
        with gr.Row():
            prompt = gr.Text(
                    label="Prompt",
                    show_label=False,
                    placeholder="describe the edit instruction",
                    container=False,
            )
            run_button = gr.Button("Edit!", variant="primary")

        with gr.Accordion("Advanced Settings", open=False):
            # Negative prompt UI element is removed here

            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():

                true_guidance_scale = gr.Slider(
                    label="True guidance scale",
                    minimum=1.0,
                    maximum=10.0,
                    step=0.1,
                    value=1.0
                )

                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=6,
                )

        gr.Examples(examples=[
                ["neon_sign.png", "change the text to read 'Qwen Image Edit is here'"],
                ["cat_sitting.jpg", "make the cat floating in the air and holding a sign that reads 'this is fun' written with a blue crayon"],
                ["pie.png", "turn the style of the photo to vintage comic book"]],
                    inputs=[input_image, prompt], 
                    outputs=[result, seed], 
                    fn=infer, 
                    cache_examples="lazy")

    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[
            input_image,
            prompt,
            seed,
            randomize_seed,
            true_guidance_scale,
            num_inference_steps
        ],
        outputs=[result, seed],
    )

if __name__ == "__main__":
    demo.launch()