File size: 1,646 Bytes
e6d2ce0 |
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 |
# Dataset settings
dataset = dict(
type="VariableVideoTextDataset",
transform_name="resize_crop",
)
# webvid
bucket_config = { # 12s/it
"144p": {1: (1.0, 475), 51: (1.0, 51), 102: ((1.0, 0.33), 27), 204: ((1.0, 0.1), 13), 408: ((1.0, 0.1), 6)},
# ---
"256": {1: (0.4, 297), 51: (0.5, 20), 102: ((0.5, 0.33), 10), 204: ((0.5, 0.1), 5), 408: ((0.5, 0.1), 2)},
"240p": {1: (0.3, 297), 51: (0.4, 20), 102: ((0.4, 0.33), 10), 204: ((0.4, 0.1), 5), 408: ((0.4, 0.1), 2)},
# ---
"360p": {1: (0.2, 141), 51: (0.15, 8), 102: ((0.15, 0.33), 4), 204: ((0.15, 0.1), 2), 408: ((0.15, 0.1), 1)},
"512": {1: (0.1, 141)},
# ---
"480p": {1: (0.1, 89)},
# ---
"720p": {1: (0.05, 36)},
"1024": {1: (0.05, 36)},
# ---
"1080p": {1: (0.1, 5)},
# ---
"2048": {1: (0.1, 5)},
}
# Acceleration settings
num_workers = 8
num_bucket_build_workers = 16
dtype = "bf16"
seed = 42
outputs = "outputs"
wandb = False
# Model settings
model = dict(
type="STDiT3-XL/2",
from_pretrained="/mnt/nfs-206/zangwei/opensora/outputs/1091-STDiT3-XL-2/epoch0-global_step8500",
qk_norm=True,
enable_flash_attn=True,
enable_layernorm_kernel=True,
)
vae = dict(
type="OpenSoraVAE_V1_2",
from_pretrained="pretrained_models/vae-pipeline",
micro_frame_size=17,
micro_batch_size=32,
)
text_encoder = dict(
type="t5",
from_pretrained="DeepFloyd/t5-v1_1-xxl",
model_max_length=300,
shardformer=True,
local_files_only=True,
)
# feature extraction settings
save_text_features = True
save_compressed_text_features = True
bin_size = 250 # 1GB, 4195 bins
log_time = False
|