Hugging Face's logo

Spaces:
multimodalart
/
Qwen-Image-Edit-Fast
Running on Zero

App Files Community
Qwen-Image-Edit-Fast
File size: 4,550 Bytes 
51a1e24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
605406e
 
 
 
51a1e24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9332ef4
51a1e24
 
 
 
cf8719a
605406e
51a1e24
 
 
 
 
 
 
 
 
 
a79e9c8
51a1e24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
605406e
51a1e24
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
 
import gradio as gr
import numpy as np
import random
import torch
import spaces

from PIL import Image
from diffusers import QwenImageEditPipeline

import os

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

# Load the model pipeline
pipe = QwenImageEditPipeline.from_pretrained("Qwen/Qwen-Image-Edit", torch_dtype=dtype).to(device)
pipe.load_lora_weights(
    "lightx2v/Qwen-Image-Lightning", weight_name="Qwen-Image-Lightning-8steps-V1.1.safetensors"
)
pipe.fuse_lora()

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

# --- Main Inference Function (with hardcoded negative prompt) ---
@spaces.GPU(duration=120)
def infer(
    image,
    prompt,
    seed=42,
    randomize_seed=False,
    guidance_scale=4.0,
    num_inference_steps=50,
    progress=gr.Progress(track_tqdm=True),
):
    """
    Generates an image using the local Qwen-Image diffusers pipeline.
    """
    # Hardcode the negative prompt as requested
    negative_prompt = "text, watermark, copyright, blurry, low resolution"
    
    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: {guidance_scale}")

    # Generate the image
    image = pipe(
        image,
        prompt=prompt,
        negative_prompt=negative_prompt,
        num_inference_steps=num_inference_steps,
        generator=generator,
        true_cfg_scale=guidance_scale,
        guidance_scale=1.0  # Use a fixed default for distilled guidance
    ).images[0]

    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_logo.png" alt="Qwen-Image Logo" width="400" style="display: block; margin: 0 auto;">')
        gr.HTML('<h1 style="text-align: center;margin-left: 80px;color: #5b47d1;font-style: italic;">Edit Fast</h1>', elem_id="edit_text")
        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")
                prompt = gr.Text(
                    label="Prompt",
                    show_label=False,
                    placeholder="describe the edit instruction",
                    container=False,
                )
                run_button = gr.Button("Edit!", variant="primary")

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

        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():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    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=8,
                )

        # 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_image,
            prompt,
            # negative_prompt is no longer an input from the UI
            seed,
            randomize_seed,
            guidance_scale,
            num_inference_steps,
        ],
        outputs=[result, seed],
    )

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