app.py

import gradio as gr
import numpy as np
import random
import torch
import spaces

from PIL import Image
from diffusers import QwenImageEditPlusPipeline

import os
import base64
import json

from huggingface_hub import login
login(token=os.environ.get('hf'))

SYSTEM_PROMPT = '''
# Edit Prompt Enhancer
You are a professional edit prompt enhancer. Your task is to generate a direct and specific edit prompt based on the user-provided instruction and the image input conditions.  

Please strictly follow the enhancing rules below:

## 1. General Principles
- Keep the enhanced prompt **direct and specific**.  
- If the instruction is contradictory, vague, or unachievable, prioritize reasonable inference and correction, and supplement details when necessary.  
- Keep the core intention of the original instruction unchanged, only enhancing its clarity, rationality, and visual feasibility.  
- All added objects or modifications must align with the logic and style of the edited input image’s overall scene.  

## 2. Task-Type Handling Rules
### 1. Add, Delete, Replace Tasks
- If the instruction is clear (already includes task type, target entity, position, quantity, attributes), preserve the original intent and only refine the grammar.  
- If the description is vague, supplement with minimal but sufficient details (category, color, size, orientation, position, etc.). For example:  
    > Original: "Add an animal"  
    > Rewritten: "Add a light-gray cat in the bottom-right corner, sitting and facing the camera"  
- Remove meaningless instructions: e.g., "Add 0 objects" should be ignored or flagged as invalid.  
- For replacement tasks, specify "Replace Y with X" and briefly describe the key visual features of X.  

### 2. Text Editing Tasks
- All text content must be enclosed in English double quotes `" "`. Keep the original language of the text, and keep the capitalization.  
- Both adding new text and replacing existing text are text replacement tasks, For example:  
    - Replace "xx" to "yy"  
    - Replace the mask / bounding box to "yy"  
    - Replace the visual object to "yy"  
- Specify text position, color, and layout only if user has required.  
- If font is specified, keep the original language of the font.  

### 3. Human (ID) Editing Tasks
- Emphasize maintaining the person’s core visual consistency (ethnicity, gender, age, hairstyle, expression, outfit, etc.).  
- If modifying appearance (e.g., clothes, hairstyle), ensure the new element is consistent with the original style.  
- **For expression changes / beauty / make up changes, they must be natural and subtle, never exaggerated.**  
- Example:  
    > Original: "Change the person’s hat"  
    > Rewritten: "Replace the man’s hat with a dark brown beret; keep smile, short hair, and gray jacket unchanged"  

### 4. Style Conversion or Enhancement Tasks
- If a style is specified, describe it concisely using key visual features. For example:  
    > Original: "Disco style"  
    > Rewritten: "1970s disco style: flashing lights, disco ball, mirrored walls, colorful tones"  
- For style reference, analyze the original image and extract key characteristics (color, composition, texture, lighting, artistic style, etc.), integrating them into the instruction.  
- **Colorization tasks (including old photo restoration) must use the fixed template:**  
  "Restore and colorize the photo."  
- Clearly specify the object to be modified. For example:  
    > Original: Modify the subject in Picture 1 to match the style of Picture 2.  
    > Rewritten: Change the girl in Picture 1 to the ink-wash style of Picture 2 — rendered in black-and-white watercolor with soft color transitions.

- If there are other changes, place the style description at the end.

### 5. Content Filling Tasks
- For inpainting tasks, always use the fixed template: "Perform inpainting on this image. The original caption is: ".
- For outpainting tasks, always use the fixed template: ""Extend the image beyond its boundaries using outpainting. The original caption is: ".

### 6. Multi-Image Tasks
- Rewritten prompts must clearly point out which image’s element is being modified. For example:  
    > Original: "Replace the subject of picture 1 with the subject of picture 2"  
    > Rewritten: "Replace the girl of picture 1 with the boy of picture 2, keeping picture 2’s background unchanged"  
- For stylization tasks, describe the reference image’s style in the rewritten prompt, while preserving the visual content of the source image.  

## 3. Rationale and Logic Checks
- Resolve contradictory instructions: e.g., "Remove all trees but keep all trees" should be logically corrected.  
- Add missing key information: e.g., if position is unspecified, choose a reasonable area based on composition (near subject, empty space, center/edge, etc.).  

# Output Format Example
```json
{
   "Rewritten": "..."
}
'''

def polish_prompt(prompt, img):
    prompt = f"{SYSTEM_PROMPT}\n\nUser Input: {prompt}\n\nRewritten Prompt:"
    success=False
    while not success:
        try:
            result = api(prompt, [img])
            # print(f"Result: {result}")
            # print(f"Polished Prompt: {polished_prompt}")
            if isinstance(result, str):
                result = result.replace('```json','')
                result = result.replace('```','')
                result = json.loads(result)
            else:
                result = json.loads(result)

            polished_prompt = result['Rewritten']
            polished_prompt = polished_prompt.strip()
            polished_prompt = polished_prompt.replace("\n", " ")
            success = True
        except Exception as e:
            print(f"[Warning] Error during API call: {e}")
    return polished_prompt


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




def api(prompt, img_list, model="qwen-vl-max-latest", kwargs={}):
    import dashscope
    api_key = os.environ.get('DASH_API_KEY')
    if not api_key:
        raise EnvironmentError("DASH_API_KEY is not set")
    assert model in ["qwen-vl-max-latest"], f"Not implemented model {model}"
    sys_promot = "you are a helpful assistant, you should provide useful answers to users."
    messages = [
        {"role": "system", "content": sys_promot},
        {"role": "user", "content": []}]
    for img in img_list:
        messages[1]["content"].append(
            {"image": f"data:image/png;base64,{encode_image(img)}"})
    messages[1]["content"].append({"text": f"{prompt}"})

    response_format = kwargs.get('response_format', None)

    response = dashscope.MultiModalConversation.call(
        api_key=api_key,
        model=model, # For example, use qwen-plus here. You can change the model name as needed. Model list: https://help.aliyun.com/zh/model-studio/getting-started/models
        messages=messages,
        result_format='message',
        response_format=response_format,
        )

    if response.status_code == 200:
        return response.output.choices[0].message.content[0]['text']
    else:
        raise Exception(f'Failed to post: {response}')

# --- Model Loading ---
dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"

# Load the model pipeline
pipe = QwenImageEditPlusPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2511", torch_dtype=dtype).to(device)

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

# --- Main Inference Function (with hardcoded negative prompt) ---
@spaces.GPU(duration=180)
def infer(
    images,
    prompt,
    seed=42,
    randomize_seed=False,
    true_guidance_scale=1.0,
    num_inference_steps=50,
    height=None,
    width=None,
    rewrite_prompt=True,
    num_images_per_prompt=1,
    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)
    
    # Load input images into PIL Images
    pil_images = []
    if images is not None:
        for item in images:
            try:
                if isinstance(item[0], Image.Image):
                    pil_images.append(item[0].convert("RGB"))
                elif isinstance(item[0], str):
                    pil_images.append(Image.open(item[0]).convert("RGB"))
                elif hasattr(item, "name"):
                    pil_images.append(Image.open(item.name).convert("RGB"))
            except Exception:
                continue

    if height==256 and width==256:
        height, width = None, None
    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}, Size: {width}x{height}")
    if rewrite_prompt and len(pil_images) > 0:
        prompt = polish_prompt(prompt, pil_images[0])
        print(f"Rewritten Prompt: {prompt}")
    

    # Generate the image
    image = pipe(
        image=pil_images if len(pil_images) > 0 else None,
        prompt=prompt,
        height=height,
        width=width,
        negative_prompt=negative_prompt,
        num_inference_steps=num_inference_steps,
        generator=generator,
        true_cfg_scale=true_guidance_scale,
        num_images_per_prompt=num_images_per_prompt,
    ).images

    return image, 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_images = gr.Gallery(label="Input Images", show_label=False, type="pil", interactive=True)

            # result = gr.Image(label="Result", show_label=False, type="pil")
            result = gr.Gallery(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=4.0
                )

                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=40,
                )
                
                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=2048,
                    step=8,
                    value=None,
                )
                
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=2048,
                    step=8,
                    value=None,
                )
                
                
                rewrite_prompt = gr.Checkbox(label="Rewrite prompt", value=True)

        # gr.Examples(examples=examples, inputs=[prompt], outputs=[result, seed], fn=infer, cache_examples=False)

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

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