File size: 8,837 Bytes
aa8012e 159a237 aa8012e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 |
import os
import re
import time
from dataclasses import dataclass
from glob import iglob
import torch
from einops import rearrange
from fire import Fire
from PIL import ExifTags, Image
from transformers import pipeline
from flux.sampling import denoise, get_noise, get_schedule, prepare, unpack
from flux.util import (
configs,
load_ae,
load_clip,
load_flow_model,
load_t5,
)
NSFW_THRESHOLD = 0.85
@dataclass
class SamplingOptions:
prompt: str
width: int
height: int
num_steps: int
guidance: float
seed: int
def parse_prompt(options: SamplingOptions) -> SamplingOptions:
user_question = "Next prompt (write /h for help, /q to quit and leave empty to repeat):\n"
usage = (
"Usage: Either write your prompt directly, leave this field empty "
"to repeat the prompt or write a command starting with a slash:\n"
"- '/w <width>' will set the width of the generated image\n"
"- '/h <height>' will set the height of the generated image\n"
"- '/s <seed>' sets the next seed\n"
"- '/g <guidance>' sets the guidance (flux-dev only)\n"
"- '/n <steps>' sets the number of steps\n"
"- '/q' to quit"
)
while (prompt := input(user_question)).startswith("/"):
if prompt.startswith("/w"):
if prompt.count(" ") != 1:
print(f"Got invalid command '{prompt}'\n{usage}")
continue
_, width = prompt.split()
options.width = 16 * (int(width) // 16)
print(
f"Setting resolution to {options.width} x {options.height} "
f"({options.height * options.width / 1e6:.2f}MP)"
)
elif prompt.startswith("/h"):
if prompt.count(" ") != 1:
print(f"Got invalid command '{prompt}'\n{usage}")
continue
_, height = prompt.split()
options.height = 16 * (int(height) // 16)
print(
f"Setting resolution to {options.width} x {options.height} "
f"({options.height * options.width / 1e6:.2f}MP)"
)
elif prompt.startswith("/g"):
if prompt.count(" ") != 1:
print(f"Got invalid command '{prompt}'\n{usage}")
continue
_, guidance = prompt.split()
options.guidance = float(guidance)
print(f"Setting guidance to {options.guidance}")
elif prompt.startswith("/s"):
if prompt.count(" ") != 1:
print(f"Got invalid command '{prompt}'\n{usage}")
continue
_, seed = prompt.split()
options.seed = int(seed)
print(f"Setting seed to {options.seed}")
elif prompt.startswith("/n"):
if prompt.count(" ") != 1:
print(f"Got invalid command '{prompt}'\n{usage}")
continue
_, steps = prompt.split()
options.num_steps = int(steps)
print(f"Setting seed to {options.num_steps}")
elif prompt.startswith("/q"):
print("Quitting")
return None
else:
if not prompt.startswith("/h"):
print(f"Got invalid command '{prompt}'\n{usage}")
print(usage)
if prompt != "":
options.prompt = prompt
return options
@torch.inference_mode()
def main(
name: str = "flux-schnell",
width: int = 1360,
height: int = 768,
seed: int = None,
prompt: str = (
"a photo of a forest with mist swirling around the tree trunks. The word "
'"FLUX" is painted over it in big, red brush strokes with visible texture'
),
device: str = "cuda" if torch.cuda.is_available() else "cpu",
num_steps: int = None,
loop: bool = False,
guidance: float = 3.5,
offload: bool = False,
output_dir: str = "output",
add_sampling_metadata: bool = True,
):
"""
Sample the flux model. Either interactively (set `--loop`) or run for a
single image.
Args:
name: Name of the model to load
height: height of the sample in pixels (should be a multiple of 16)
width: width of the sample in pixels (should be a multiple of 16)
seed: Set a seed for sampling
output_name: where to save the output image, `{idx}` will be replaced
by the index of the sample
prompt: Prompt used for sampling
device: Pytorch device
num_steps: number of sampling steps (default 4 for schnell, 50 for guidance distilled)
loop: start an interactive session and sample multiple times
guidance: guidance value used for guidance distillation
add_sampling_metadata: Add the prompt to the image Exif metadata
"""
nsfw_classifier = pipeline("image-classification", model="Falconsai/nsfw_image_detection")
if name not in configs:
available = ", ".join(configs.keys())
raise ValueError(f"Got unknown model name: {name}, chose from {available}")
torch_device = torch.device(device)
if num_steps is None:
num_steps = 4 if name == "flux-schnell" else 50
# allow for packing and conversion to latent space
height = 16 * (height // 16)
width = 16 * (width // 16)
output_name = os.path.join(output_dir, "img_{idx}.jpg")
if not os.path.exists(output_dir):
os.makedirs(output_dir)
idx = 0
else:
fns = [fn for fn in iglob(output_name.format(idx="*")) if re.search(r"img_[0-9]\.jpg$", fn)]
if len(fns) > 0:
idx = max(int(fn.split("_")[-1].split(".")[0]) for fn in fns) + 1
else:
idx = 0
# init all components
t5 = load_t5(torch_device, max_length=256 if name == "flux-schnell" else 512)
clip = load_clip(torch_device)
model = load_flow_model(name, device="cpu" if offload else torch_device)
ae = load_ae(name, device="cpu" if offload else torch_device)
rng = torch.Generator(device="cpu")
opts = SamplingOptions(
prompt=prompt,
width=width,
height=height,
num_steps=num_steps,
guidance=guidance,
seed=seed,
)
if loop:
opts = parse_prompt(opts)
while opts is not None:
if opts.seed is None:
opts.seed = rng.seed()
print(f"Generating with seed {opts.seed}:\n{opts.prompt}")
t0 = time.perf_counter()
# prepare input
x = get_noise(
1,
opts.height,
opts.width,
device=torch_device,
dtype=torch.bfloat16,
seed=opts.seed,
)
opts.seed = None
if offload:
ae = ae.cpu()
torch.cuda.empty_cache()
t5, clip = t5.to(torch_device), clip.to(torch_device)
inp = prepare(t5, clip, x, prompt=opts.prompt)
timesteps = get_schedule(opts.num_steps, inp["img"].shape[1], shift=(name != "flux-schnell"))
# offload TEs to CPU, load model to gpu
if offload:
t5, clip = t5.cpu(), clip.cpu()
torch.cuda.empty_cache()
model = model.to(torch_device)
# denoise initial noise
x = denoise(model, **inp, timesteps=timesteps, guidance=opts.guidance)
# offload model, load autoencoder to gpu
if offload:
model.cpu()
torch.cuda.empty_cache()
ae.decoder.to(x.device)
# decode latents to pixel space
x = unpack(x.float(), opts.height, opts.width)
with torch.autocast(device_type=torch_device.type, dtype=torch.bfloat16):
x = ae.decode(x)
t1 = time.perf_counter()
fn = output_name.format(idx=idx)
print(f"Done in {t1 - t0:.1f}s. Saving {fn}")
# bring into PIL format and save
x = x.clamp(-1, 1)
# x = embed_watermark(x.float())
x = rearrange(x[0], "c h w -> h w c")
img = Image.fromarray((127.5 * (x + 1.0)).cpu().byte().numpy())
nsfw_score = [x["score"] for x in nsfw_classifier(img) if x["label"] == "nsfw"][0]
if nsfw_score < NSFW_THRESHOLD:
exif_data = Image.Exif()
exif_data[ExifTags.Base.Software] = "AI generated;txt2img;flux"
exif_data[ExifTags.Base.Make] = "Black Forest Labs"
exif_data[ExifTags.Base.Model] = name
if add_sampling_metadata:
exif_data[ExifTags.Base.ImageDescription] = prompt
img.save(fn, exif=exif_data, quality=95, subsampling=0)
idx += 1
else:
print("Your generated image may contain NSFW content.")
if loop:
print("-" * 80)
opts = parse_prompt(opts)
else:
opts = None
def app():
Fire(main)
if __name__ == "__main__":
app()
|