stanford-vision-lab/gpic
Updated โข 67.6k โข 172
flow_match_checkpoint = {
'model': raw_model.state_dict(),
'optimizer': optimizer.state_dict(),
'ema': ema.state_dict,
'step': step
}
vae_checkpoint = vae.state_dict(),
@dataclass
class TrainConfig:
lr: float = 1e-4
batch_size: int = 8
total_steps: int = 10000 # 50k steps is ideal.
lr_cooldown_steps: int = 20000
starting_step: int = 0
logging_interval: int = 100
grad_accum_steps: int = 2 # not really needed
save_dir: str = "./saved_models/"
ckpt: str = "flowmatch-ckpt.pt"
@dataclass
class VAEConfig:
kl_beta: float = 5e-2
fft_weight: float = 0.05
lpips_weight: float = 0.5
latent_channels: tuple[int, ...] = (128, 256, 512, 512)
z_channels: int = 32
n_heads: int = 8
resnet_blocks: int = 2
@dataclass
class mmDiTConfig:
d_model: int = 768
n_heads: int = 32
n_blocks: int = 16
patch_size: int = 2
color_channels: int = 32 # z_channels
height: int = 32 # latent
width: int = 32 # latent
t_channels: int = 64