frankleeeee's picture
update
e6d2ce0
raw
history blame contribute delete
697 Bytes
num_frames = 64
fps = 24 // 2
image_size = (512, 512)
# Define model
model = dict(
type="STDiT-XL/2",
space_scale=1.0,
time_scale=2 / 3,
enable_flash_attn=True,
enable_layernorm_kernel=True,
from_pretrained="PRETRAINED_MODEL",
)
vae = dict(
type="VideoAutoencoderKL",
from_pretrained="stabilityai/sd-vae-ft-ema",
micro_batch_size=128,
)
text_encoder = dict(
type="t5",
from_pretrained="DeepFloyd/t5-v1_1-xxl",
model_max_length=120,
)
scheduler = dict(
type="iddpm",
num_sampling_steps=100,
cfg_scale=7.0,
)
dtype = "bf16"
# Others
batch_size = 1
seed = 42
prompt_path = "./assets/texts/t2v_samples.txt"
save_dir = "./samples/samples/"