File size: 4,899 Bytes
8ccf632
 
 
 
 
06f0278
 
 
 
 
 
b213a9c
 
06f0278
 
b213a9c
 
 
ffca250
8ccf632
 
 
06f0278
 
 
 
 
 
 
 
8ccf632
 
 
06f0278
8ccf632
 
b213a9c
54192f0
 
8ccf632
 
 
 
 
 
06f0278
b213a9c
8ccf632
 
 
 
06f0278
 
 
8ccf632
 
 
 
 
e2944a6
8ccf632
 
 
 
 
 
dc55004
 
 
8ccf632
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b213a9c
 
 
 
 
 
 
 
8ccf632
 
 
 
 
 
b213a9c
8ccf632
 
 
 
0a779d1
8ccf632
 
 
 
 
 
2b62414
8ccf632
b213a9c
8ccf632
 
 
9aa8809
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
144
145
146
147
148
149
import gradio as gr
import numpy as np
import random
import spaces
import torch
from diffusers import  FluxPipeline, FluxTransformer2DModel,FlowMatchEulerDiscreteScheduler, AutoencoderKL
from transformers import CLIPTextModel, CLIPTokenizer,T5EncoderModel, T5TokenizerFast

dtype = torch.bfloat16
device = "cuda"

bfl_repo = "black-forest-labs/FLUX.1-schnell"
scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(bfl_repo, subfolder="scheduler", revision="refs/pr/1")
text_encoder = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
text_encoder_2 = T5EncoderModel.from_pretrained(bfl_repo, subfolder="text_encoder_2", torch_dtype=dtype, revision="refs/pr/1")
tokenizer_2 = T5TokenizerFast.from_pretrained(bfl_repo, subfolder="tokenizer_2", torch_dtype=dtype, revision="refs/pr/1")
vae = AutoencoderKL.from_pretrained(bfl_repo, subfolder="vae", torch_dtype=dtype, revision="refs/pr/1")
transformer = FluxTransformer2DModel.from_pretrained("diffusers-internal-dev/FLUX.1-dev", torch_dtype=dtype)

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

pipe = FluxPipeline(
    scheduler=scheduler,
    text_encoder=text_encoder,
    tokenizer=tokenizer,
    text_encoder_2=text_encoder_2,
    tokenizer_2=tokenizer_2,
    vae=vae,
    transformer=transformer,
).to("cuda")

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

@spaces.GPU()
def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=5.0, 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)
    image = pipe(
            prompt = prompt, 
            width = width,
            height = height,
            num_inference_steps = num_inference_steps, 
            generator = generator,
            guidance_scale=guidance_scale
    ).images[0] 
    return image, seed
 
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 demo:
    
    with gr.Column(elem_id="col-container"):
        gr.Markdown(f"""# FLUX.1 [dev]
12B param rectified flow transformer guidance-distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/)
[[blog](https://blackforestlabs.ai/2024/07/31/announcing-black-forest-labs/)] [[model](https://huggingface.co./black-forest-labs/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.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=1,
                    value=5.0,
                )
  
                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]
    )

demo.launch()