File size: 6,589 Bytes
09fc7e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9b104c4
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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
import gradio as gr
import numpy as np
import random
# import spaces
import torch
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 gradio_imageslider import ImageSlider
from PIL import Image, ImageDraw, ImageFont

dtype = torch.bfloat16
#model_id = "black-forest-labs/FLUX.1-dev"
model_id = "camenduru/FLUX.1-dev-diffusers"
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(model_id, subfolder="vae", torch_dtype=dtype).to(device)
#pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=dtype, vae=taef1).to(device)
pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=dtype, vae=good_vae).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)

def get_cmp_image(im1: Image.Image, im2: Image.Image, sigmas: float):
    dst = Image.new('RGB', (im1.width + im2.width, im1.height))
    dst.paste(im1.convert('RGB'), (0, 0))
    dst.paste(im2.convert('RGB'), (im1.width, 0))
    font = ImageFont.truetype('Roboto-Regular.ttf', 72, encoding='unic')
    draw = ImageDraw.Draw(dst)
    draw.text((64, im1.height - 128), 'Default Flux', 'red', font=font)
    draw.text((im1.width + 64, im1.height - 128), f'Sigmas * factor {sigmas}', 'red', font=font)
    return dst

# @spaces.GPU(duration=90)
def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28, mul_sigmas=0.95, is_cmp=True, progress=gr.Progress(track_tqdm=True)):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
    generator = torch.Generator().manual_seed(seed)
    
    sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps)
    sigmas = sigmas * mul_sigmas

    image_sigmas = pipe(
            prompt=prompt,
            guidance_scale=guidance_scale,
            num_inference_steps=num_inference_steps,
            width=width,
            height=height,
            generator=generator,
            output_type="pil",
            sigmas=sigmas
        ).images[0]
    
    if is_cmp:
        image_def = pipe(
                prompt=prompt,
                guidance_scale=guidance_scale,
                num_inference_steps=num_inference_steps,
                width=width,
                height=height,
                generator=generator,
                output_type="pil",
            ).images[0]
        return [image_def, image_sigmas], get_cmp_image(image_def, image_sigmas, mul_sigmas), seed
    else: return [image_sigmas, image_sigmas], None, 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] sigmas test
12B param rectified flow transformer guidance-distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/)  
[[non-commercial license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md)] [[blog](https://blackforestlabs.ai/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)
        result = ImageSlider(label="Result", show_label=False, type="pil", slider_color="pink")
        result_cmp = gr.Image(label="Result (comparing)", show_label=False, type="pil", format="png", height=256, show_download_button=True, show_share_button=False)
        
        with gr.Accordion("Advanced Settings", open=True):
            with gr.Row():
                sigmas = gr.Slider(
                    label="Sigmas",
                    minimum=0,
                    maximum=1.0,
                    step=0.01,
                    value=0.95,
                )
                is_cmp = gr.Checkbox(label="Compare images with/without sigmas", value=True)
            
            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=9119,
            )
            
            randomize_seed = gr.Checkbox(label="Randomize seed", value=False)
            
            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, result_cmp, 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, sigmas, is_cmp],
        outputs = [result, result_cmp, seed]
    )

demo.launch()