when i test the unet_1D, why there is a error

[wuyueteng]

from diffusers import UNet1DModel,DDPMScheduler
noise_scheduler = DDPMScheduler(num_train_timesteps=1000, beta_schedule='squaredcos_cap_v2')
import torch
model=UNet1DModel( sample_size=1024,
in_channels=1,
out_channels=1,
layers_per_block=2,
block_out_channels=(32, 64,128),time_embedding_type="positional")

x=torch.randn(2,1,1024)
noise = torch.randn_like(x)
timesteps = torch.randint(0, 999, (x.shape[0],)).long()
noisy_x = noise_scheduler.add_noise(x, noise, timesteps)
pred = model(noisy_x, timesteps)

RuntimeError: Given groups=1, weight of size [32, 1, 1], expected input[2, 33, 1024] to have 1 channels, but got 33 channels instead

[tdme7]

"I encountered the same issue as you. I removed the line hidden_states = torch.cat([hidden_states, temb], dim=1) from unet_1d_blocks.py at line 516 in the class DownBlock1DNoSkip(nn.Module)."

[Gittulal]

"I encountered the same issue as you. I removed the line hidden_states = torch.cat([hidden_states, temb], dim=1) from unet_1d_blocks.py at line 516 in the class DownBlock1DNoSkip(nn.Module)."
I ave deployed this one but not got the results.