Spaces:
Running
on
Zero
Running
on
Zero
File size: 4,076 Bytes
f0e942d b635626 f0e942d |
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 |
from dataclasses import dataclass
import torch
from torch import Tensor, nn
from src.flux.modules.layers import (DoubleStreamBlock, EmbedND, LastLayer,
MLPEmbedder, SingleStreamBlock,
timestep_embedding)
@dataclass
class FluxParams:
in_channels: int
vec_in_dim: int
context_in_dim: int
hidden_size: int
mlp_ratio: float
num_heads: int
depth: int
depth_single_blocks: int
axes_dim: list[int]
theta: int
qkv_bias: bool
guidance_embed: bool
class Flux(nn.Module):
"""
Transformer model for flow matching on sequences.
"""
def __init__(self, params: FluxParams):
super().__init__()
self.params = params
self.in_channels = params.in_channels
self.out_channels = self.in_channels
if params.hidden_size % params.num_heads != 0:
raise ValueError(
f"Hidden size {params.hidden_size} must be divisible by num_heads {params.num_heads}"
)
pe_dim = params.hidden_size // params.num_heads
if sum(params.axes_dim) != pe_dim:
raise ValueError(f"Got {params.axes_dim} but expected positional dim {pe_dim}")
self.hidden_size = params.hidden_size
self.num_heads = params.num_heads
self.pe_embedder = EmbedND(dim=pe_dim, theta=params.theta, axes_dim=params.axes_dim)
self.img_in = nn.Linear(self.in_channels, self.hidden_size, bias=True)
self.time_in = MLPEmbedder(in_dim=256, hidden_dim=self.hidden_size)
self.vector_in = MLPEmbedder(params.vec_in_dim, self.hidden_size)
self.guidance_in = (
MLPEmbedder(in_dim=256, hidden_dim=self.hidden_size) if params.guidance_embed else nn.Identity()
)
self.txt_in = nn.Linear(params.context_in_dim, self.hidden_size)
self.double_blocks = nn.ModuleList(
[
DoubleStreamBlock(
self.hidden_size,
self.num_heads,
mlp_ratio=params.mlp_ratio,
qkv_bias=params.qkv_bias,
cur_block=i,
)
for i in range(params.depth)
]
)
self.single_blocks = nn.ModuleList(
[
SingleStreamBlock(self.hidden_size, self.num_heads, mlp_ratio=params.mlp_ratio)
for _ in range(params.depth_single_blocks)
]
)
self.final_layer = LastLayer(self.hidden_size, 1, self.out_channels)
def forward(
self,
img: Tensor,
img_ids: Tensor,
txt: Tensor, # t5 text
txt_ids: Tensor,
timesteps: Tensor,
y: Tensor, # clip text
cur_step: int,
guidance: Tensor | None = None,
info = None,
) -> Tensor:
if img.ndim != 3 or txt.ndim != 3:
raise ValueError("Input img and txt tensors must have 3 dimensions.")
# running on sequences img
img = self.img_in(img)
vec = self.time_in(timestep_embedding(timesteps, 256))
if self.params.guidance_embed:
if guidance is None:
raise ValueError("Didn't get guidance strength for guidance distilled model.")
vec = vec + self.guidance_in(timestep_embedding(guidance, 256))
vec = vec + self.vector_in(y)
txt = self.txt_in(txt)
ids = torch.cat((txt_ids, img_ids), dim=1)
pe = self.pe_embedder(ids)
for block in self.double_blocks:
img, txt = block(img=img, txt=txt, vec=vec, pe=pe, cur_step=cur_step, info=info)
cnt = 0
img = torch.cat((txt, img), 1)
info['type'] = 'single'
for block in self.single_blocks:
info['id'] = cnt
img, info = block(img, vec=vec, pe=pe, info=info)
cnt += 1
img = img[:, txt.shape[1] :, ...]
img = self.final_layer(img, vec) # (N, T, patch_size ** 2 * out_channels)
return img, info |