FloodDiffusionTiny / ldf.yaml
herrscher0's picture
Initial commit: FloodDiffusionTiny - Tiny text-to-motion model with UMT5-Base
e86746e
exp_name: ldf
seed: 1234
debug: false
train: false
save_dir: ./outputs
resume_ckpt: null
test_ckpt: "model.safetensors"
test_vae_ckpt: "vae.safetensors"
test_vae:
target: ldf_models.vae_wan_1d.VAEWanModel
ema_decay: 0.99
params:
input_dim: 263
z_dim: 4
test_setting:
render: false
simple: true
recover_dim: 263
val_repeat: 1
model:
target: ldf_models.diffusion_forcing_wan_tiny.DiffForcingWanModel
ema_decay: 0.99
params:
model_name: "google/umt5-base"
input_dim: 4
noise_steps: 10
hidden_dim: 256
ffn_dim: 1024
freq_dim: 64
num_heads: 8
num_layers: 8
time_embedding_scale: 1.0
chunk_size: 5
use_text_cond: True
text_len: 128
drop_out: 0.1
cfg_scale: 5.0
prediction_type: "vel"
causal: False