File size: 4,960 Bytes
4f48282
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import gradio as gr
import numpy as np
import random
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
import modal
import random
import io
from config.config import prompts, models  # Indirect import
import os
import sentencepiece
from huggingface_hub import login
from transformers import AutoTokenizer
from datetime import datetime


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

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

CACHE_DIR = "/model_cache"

image = (
    modal.Image.from_registry("nvidia/cuda:12.2.0-devel-ubuntu22.04", add_python="3.9")
    .pip_install_from_requirements("requirements.txt")
    .env({
        "HF_HUB_ENABLE_HF_TRANSFER": "1", "HF_HOME": "HF_HOME", "HF_HUB_CACHE": CACHE_DIR
    })
)

app = modal.App("img-gen-modal-live", image=image)
with image.imports():
    import os

flux_model_vol = modal.Volume.from_name("flux-model-vol", create_if_missing=True)

@app.function(volumes={"/data": flux_model_vol},
              secrets=[modal.Secret.from_name("huggingface-token")],
              gpu="L40S",
              timeout=300)
def infer(prompt, seed=42, randomize_seed=False, width=640, height=360, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
    taef1 = AutoencoderTiny.from_pretrained("/data/taef1", torch_dtype=dtype).to(device)
    good_vae = AutoencoderKL.from_pretrained("/data/FLUX.1-dev", subfolder="vae", torch_dtype=dtype).to(device)
    pipe = DiffusionPipeline.from_pretrained("/data/FLUX.1-dev", torch_dtype=dtype, vae=taef1).to(device)
    torch.cuda.empty_cache()
    
    pipe.flux_pipe_call_that_returns_an_iterable_of_images = flux_pipe_call_that_returns_an_iterable_of_images.__get__(pipe)

    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 

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;
}
"""

hf_token = os.environ["HF_TOKEN"]
print("Initializing HF TOKEN")
print(hf_token)
print("HF TOKEN:")
login(token=hf_token)

with gr.Blocks(css=css) as demo:
    f = modal.Function.from_name("img-gen-modal-live", "infer")
    
    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/)  
[[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)
        
        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=640)
                height = gr.Slider(label="Height", minimum=256, maximum=MAX_IMAGE_SIZE, step=32, value=360)
            
            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=f.remote,
            inputs=[prompt],
            outputs=[result, seed],
            cache_examples="lazy"
        )

    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=lambda *args: [next(f.remote_gen(*args)), seed],  # Adjusted to process generator
        inputs=[prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
        outputs=[result, seed]
    )

demo.launch()