Closed shuminghu closed 6 months ago
parser.add_argument(
"--unet_time_cond_proj_dim",
type=int,
default=256,
help=(
"The dimension of the guidance scale embedding in the U-Net, which will be used if the teacher U-Net"
" does not have `time_cond_proj_dim` set."
)
I found this new args in latest diffusers repo, hope could help you
Running either train_lcm_distill_sd_wds.py or train_lcm_distill_sdxl_wds.py would running into missing argument error:
In train_lcm_distill_sd_wds.py, this argument configures guidance_scale_embedding dimension to be used as timestep conditional: https://github.com/luosiallen/latent-consistency-model/blob/main/LCM_Training_Script/consistency_distillation/train_lcm_distill_sd_wds.py#L1143-L1156
, whereas in train_lcm_distill_sdxl_wds.py, guidance_scale_embedding is not used at all. https://github.com/luosiallen/latent-consistency-model/blob/main/LCM_Training_Script/consistency_distillation/train_lcm_distill_sdxl_wds.py#L1248
Is the use of guidance_scale_embedding as timestamp_cond actually helpful? if yes, please fix with a default dim.