Spaces:
Runtime error
Runtime error
File size: 5,234 Bytes
30bbb9e |
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 |
import math
from typing import Callable
import torch
from einops import rearrange, repeat
from torch import Tensor
from .model import Flux
from .modules.conditioner import HFEmbedder
def get_noise(
num_samples: int,
height: int,
width: int,
device: torch.device,
dtype: torch.dtype,
seed: int,
):
return torch.randn(
num_samples,
16,
# allow for packing
2 * math.ceil(height / 16),
2 * math.ceil(width / 16),
device=device,
dtype=dtype,
generator=torch.Generator(device=device).manual_seed(seed),
)
def prepare(t5: HFEmbedder, clip: HFEmbedder, img: Tensor, prompt: str | list[str]) -> dict[str, Tensor]:
bs, c, h, w = img.shape
if bs == 1 and not isinstance(prompt, str):
bs = len(prompt)
img = rearrange(img, "b c (h ph) (w pw) -> b (h w) (c ph pw)", ph=2, pw=2)
if img.shape[0] == 1 and bs > 1:
img = repeat(img, "1 ... -> bs ...", bs=bs)
img_ids = torch.zeros(h // 2, w // 2, 3)
img_ids[..., 1] = img_ids[..., 1] + torch.arange(h // 2)[:, None]
img_ids[..., 2] = img_ids[..., 2] + torch.arange(w // 2)[None, :]
img_ids = repeat(img_ids, "h w c -> b (h w) c", b=bs)
if isinstance(prompt, str):
prompt = [prompt]
txt = t5(prompt)
if txt.shape[0] == 1 and bs > 1:
txt = repeat(txt, "1 ... -> bs ...", bs=bs)
txt_ids = torch.zeros(bs, txt.shape[1], 3)
vec = clip(prompt)
if vec.shape[0] == 1 and bs > 1:
vec = repeat(vec, "1 ... -> bs ...", bs=bs)
return {
"img": img,
"img_ids": img_ids.to(img.device),
"txt": txt.to(img.device),
"txt_ids": txt_ids.to(img.device),
"vec": vec.to(img.device),
}
def time_shift(mu: float, sigma: float, t: Tensor):
return math.exp(mu) / (math.exp(mu) + (1 / t - 1) ** sigma)
def get_lin_function(
x1: float = 256, y1: float = 0.5, x2: float = 4096, y2: float = 1.15
) -> Callable[[float], float]:
m = (y2 - y1) / (x2 - x1)
b = y1 - m * x1
return lambda x: m * x + b
def get_schedule(
num_steps: int,
image_seq_len: int,
base_shift: float = 0.5,
max_shift: float = 1.15,
shift: bool = True,
) -> list[float]:
# extra step for zero
timesteps = torch.linspace(1, 0, num_steps + 1)
# shifting the schedule to favor high timesteps for higher signal images
if shift:
# eastimate mu based on linear estimation between two points
mu = get_lin_function(y1=base_shift, y2=max_shift)(image_seq_len)
timesteps = time_shift(mu, 1.0, timesteps)
return timesteps.tolist()
def denoise(
model: Flux,
# model input
img: Tensor,
img_ids: Tensor,
txt: Tensor,
txt_ids: Tensor,
vec: Tensor,
# sampling parameters
timesteps: list[float],
guidance: float = 4.0,
use_gs=False,
gs=4,
):
# this is ignored for schnell
guidance_vec = torch.full((img.shape[0],), guidance, device=img.device, dtype=img.dtype)
for t_curr, t_prev in zip(timesteps[:-1], timesteps[1:]):
t_vec = torch.full((img.shape[0],), t_curr, dtype=img.dtype, device=img.device)
pred = model(
img=img,
img_ids=img_ids,
txt=txt,
txt_ids=txt_ids,
y=vec,
timesteps=t_vec,
guidance=guidance_vec,
)
if use_gs:
pred_uncond, pred_text = pred.chunk(2)
pred = pred_uncond + gs * (pred_text - pred_uncond)
img = img + (t_prev - t_curr) * pred
#if use_gs:
# img = torch.cat([img] * 2)
return img
def denoise_controlnet(
model: Flux,
controlnet:None,
# model input
img: Tensor,
img_ids: Tensor,
txt: Tensor,
txt_ids: Tensor,
vec: Tensor,
controlnet_cond,
# sampling parameters
timesteps: list[float],
guidance: float = 4.0,
controlnet_gs=0.7,
):
# this is ignored for schnell
guidance_vec = torch.full((img.shape[0],), guidance, device=img.device, dtype=img.dtype)
for t_curr, t_prev in zip(timesteps[:-1], timesteps[1:]):
t_vec = torch.full((img.shape[0],), t_curr, dtype=img.dtype, device=img.device)
block_res_samples = controlnet(
img=img,
img_ids=img_ids,
controlnet_cond=controlnet_cond,
txt=txt,
txt_ids=txt_ids,
y=vec,
timesteps=t_vec,
guidance=guidance_vec,
)
pred = model(
img=img,
img_ids=img_ids,
txt=txt,
txt_ids=txt_ids,
y=vec,
timesteps=t_vec,
guidance=guidance_vec,
block_controlnet_hidden_states=[i * controlnet_gs for i in block_res_samples]
)
img = img + (t_prev - t_curr) * pred
#if use_gs:
# img = torch.cat([img] * 2)
return img
def unpack(x: Tensor, height: int, width: int) -> Tensor:
return rearrange(
x,
"b (h w) (c ph pw) -> b c (h ph) (w pw)",
h=math.ceil(height / 16),
w=math.ceil(width / 16),
ph=2,
pw=2,
)
|