The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Support Pruna LTX VAE (#15129)
Jukka Seppänenc38171ddb933
diff --git a/comfy/ldm/lightricks/vae/causal_conv3d.py b/comfy/ldm/lightricks/vae/causal_conv3d.pyindex 7515f0d4e..bb1803f12 100644--- a/comfy/ldm/lightricks/vae/causal_conv3d.py+++ b/comfy/ldm/lightricks/vae/causal_conv3d.py@@ -49,6 +49,12 @@ class CausalConv3d(nn.Module):)self.temporal_cache_state={}+ def _empty_output(self, x):+ # empty (0 frame) outputs must still have the conv's output channels and spatial dims+ h = (x.shape[3] + 2 * self.conv.padding[1] - self.conv.kernel_size[1]) // self.conv.stride[1] + 1+ w = (x.shape[4] + 2 * self.conv.padding[2] - self.conv.kernel_size[2]) // self.conv.stride[2] + 1+ return x.new_empty((x.shape[0], self.out_channels, 0, h, w))+def forward(self, x, causal: bool = True):tid = threading.get_ident()@@ -58,7 +64,7 @@ class CausalConv3d(nn.Module):if not causal:padding_length = padding_length // 2if x.shape[2] == 0:- return x+ return self._empty_output(x)cached = x[:, :, :1, :, :].repeat((1, 1, padding_length, 1, 1))pieces = [ cached, x ]if is_end and not causal:@@ -83,7 +89,7 @@ class CausalConv3d(nn.Module):elif is_end:self.temporal_cache_state[tid] = (None, True)- return self.conv(x) if x.shape[2] >= self.time_kernel_size else x[:, :, :0, :, :]+ return self.conv(x) if x.shape[2] >= self.time_kernel_size else self._empty_output(x)@propertydef weight(self):diff --git a/comfy/ldm/lightricks/vae/causal_video_autoencoder.py b/comfy/ldm/lightricks/vae/causal_video_autoencoder.pyindex 5975015e2..5d0eec5b8 100644--- a/comfy/ldm/lightricks/vae/causal_video_autoencoder.py+++ b/comfy/ldm/lightricks/vae/causal_video_autoencoder.py@@ -390,10 +390,10 @@ class Decoder(nn.Module):# Compute output channel to be product of all channel-multiplier blocksoutput_channel = base_channels- for block_name, block_params in list(reversed(blocks)):+ for block_name, block_params in blocks:block_params = block_params if isinstance(block_params, dict) else {}if block_name == "res_x_y":- output_channel = output_channel * block_params.get("multiplier", 2)+ output_channel = block_params.get("in_channels", output_channel * block_params.get("multiplier", 2))if block_name == "compress_all":output_channel = output_channel * block_params.get("multiplier", 1)if block_name == "compress_space":@@ -432,7 +432,7 @@ class Decoder(nn.Module):spatial_padding_mode=spatial_padding_mode,)elif block_name == "res_x_y":- output_channel = output_channel // block_params.get("multiplier", 2)+ output_channel = block_params.get("out_channels", output_channel // block_params.get("multiplier", 2))block = ResnetBlock3D(dims=dims,in_channels=input_channel,