Hugging Face's logo

Spaces:
yerang
/
LivePortrait
Running on Zero

App Files Community
LivePortrait
File size: 5,206 Bytes 
336b8ba
 
 
 
 
 
 
 
 
2532f22
336b8ba
2532f22
 
336b8ba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57736d1
 
336b8ba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57736d1
 
 
336b8ba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57736d1
 
 
 
 
 
336b8ba
 
 
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 diffusers import DiffusionPipeline, FlowMatchEulerDiscreteScheduler, AutoencoderTiny, AutoencoderKL
from transformers import CLIPTextModel, CLIPTokenizer,T5EncoderModel, T5TokenizerFast
from live_preview_helpers import calculate_shift, retrieve_timesteps, flux_pipe_call_that_returns_an_iterable_of_images

from huggingface_hub import login
import os
token = os.getenv("HF_TOKEN")
login(token=token)

dtype = torch.bfloat16
device = "cuda" if torch.cuda.is_available() else "cpu"

taef1 = AutoencoderTiny.from_pretrained("madebyollin/taef1", torch_dtype=dtype).to(device)
good_vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-dev", subfolder="vae", torch_dtype=dtype).to(device)
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=dtype, vae=taef1).to(device)
torch.cuda.empty_cache()

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 2048

pipe.flux_pipe_call_that_returns_an_iterable_of_images = flux_pipe_call_that_returns_an_iterable_of_images.__get__(pipe)

@spaces.GPU(duration=75)
def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    generator = torch.Generator().manual_seed(seed)
    
    for img in pipe.flux_pipe_call_that_returns_an_iterable_of_images(
            prompt=prompt,
            guidance_scale=guidance_scale,
            num_inference_steps=num_inference_steps,
            width=width,
            height=height,
            generator=generator,
            output_type="pil",
            good_vae=good_vae,
        ):
        yield img, seed


#def create_flux_tab():
def create_flux_tab(image_input):
    examples = [
        "a tiny astronaut hatching from an egg on the moon",
        "a cat holding a sign that says hello world",
        "an anime illustration of a wiener schnitzel",
    ]

    css = """
    #col-container {
        margin: 0 auto;
        max-width: 520px;
    }
    """
    
    with gr.Blocks(css=css) as flux_demo:
        with gr.Column(elem_id="col-container"):
            gr.Markdown(f"""# FLUX.1 [dev]""")
            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.Row():
                use_in_text2lipsync_button = gr.Button("Use this image in [Txt2LipSync] Tab")  # 새로운 버튼 추가
            
            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)
                
                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=1024,
                    )
                
                with gr.Row():
                    guidance_scale = gr.Slider(
                        label="Guidance Scale",
                        minimum=1,
                        maximum=15,
                        step=0.1,
                        value=3.5,
                    )
                    num_inference_steps = gr.Slider(
                        label="Number of inference steps",
                        minimum=1,
                        maximum=50,
                        step=1,
                        value=28,
                    )
            
            gr.Examples(
                examples=examples,
                fn=infer,
                inputs=[prompt],
                outputs=[result, seed],
                cache_examples="lazy"
            )
        
        gr.on(
            triggers=[run_button.click, prompt.submit],
            fn=infer,
            inputs=[prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
            outputs=[result, seed]
        )
        # 새로운 버튼 클릭 이벤트 정의
        use_in_text2lipsync_button.click(
            fn=lambda img: img,  # 간단한 람다 함수를 사용하여 이미지를 그대로 전달
            inputs=[result],  # 생성된 이미지를 입력으로 사용
            outputs=[image_input]  # Text to LipSync 탭의 image_input을 업데이트
        )
    
    return flux_demo