Skip to content

EasyCache: Fix for mismatch in input/output channels with some models #10788

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Kosinkadink merged 1 commit into from
Nov 18, 2025
Merged

EasyCache: Fix for mismatch in input/output channels with some models #10788

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
22 changes: 12 additions & 10 deletions comfy_extras/nodes_easycache.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,13 @@

def easycache_forward_wrapper(executor, *args, **kwargs):
# get values from args
x: torch.Tensor = args[0]
transformer_options: dict[str] = args[-1]
if not isinstance(transformer_options, dict):
transformer_options = kwargs.get("transformer_options")
if not transformer_options:
transformer_options = args[-2]
easycache: EasyCacheHolder = transformer_options["easycache"]
x: torch.Tensor = args[0][:, :easycache.output_channels]
sigmas = transformer_options["sigmas"]
uuids = transformer_options["uuids"]
if sigmas is not None and easycache.is_past_end_timestep(sigmas):
Expand Down Expand Up @@ -82,13 +82,13 @@ def easycache_forward_wrapper(executor, *args, **kwargs):

def lazycache_predict_noise_wrapper(executor, *args, **kwargs):
# get values from args
x: torch.Tensor = args[0]
timestep: float = args[1]
model_options: dict[str] = args[2]
easycache: LazyCacheHolder = model_options["transformer_options"]["easycache"]
if easycache.is_past_end_timestep(timestep):
return executor(*args, **kwargs)
# prepare next x_prev
x: torch.Tensor = args[0][:, :easycache.output_channels]
next_x_prev = x
input_change = None
do_easycache = easycache.should_do_easycache(timestep)
Expand Down Expand Up @@ -173,7 +173,7 @@ def easycache_sample_wrapper(executor, *args, **kwargs):


class EasyCacheHolder:
def __init__(self, reuse_threshold: float, start_percent: float, end_percent: float, subsample_factor: int, offload_cache_diff: bool, verbose: bool=False):
def __init__(self, reuse_threshold: float, start_percent: float, end_percent: float, subsample_factor: int, offload_cache_diff: bool, verbose: bool=False, output_channels: int=None):
self.name = "EasyCache"
self.reuse_threshold = reuse_threshold
self.start_percent = start_percent
Expand Down Expand Up @@ -202,6 +202,7 @@ def __init__(self, reuse_threshold: float, start_percent: float, end_percent: fl
self.allow_mismatch = True
self.cut_from_start = True
self.state_metadata = None
self.output_channels = output_channels

def is_past_end_timestep(self, timestep: float) -> bool:
return not (timestep[0] > self.end_t).item()
Expand Down Expand Up @@ -264,7 +265,7 @@ def apply_cache_diff(self, x: torch.Tensor, uuids: list[UUID]):
else:
slicing.append(slice(None))
batch_slice = batch_slice + slicing
x[batch_slice] += self.uuid_cache_diffs[uuid].to(x.device)
x[tuple(batch_slice)] += self.uuid_cache_diffs[uuid].to(x.device)
return x

def update_cache_diff(self, output: torch.Tensor, x: torch.Tensor, uuids: list[UUID]):
Expand All @@ -283,7 +284,7 @@ def update_cache_diff(self, output: torch.Tensor, x: torch.Tensor, uuids: list[U
else:
slicing.append(slice(None))
skip_dim = False
x = x[slicing]
x = x[tuple(slicing)]
diff = output - x
batch_offset = diff.shape[0] // len(uuids)
for i, uuid in enumerate(uuids):
Expand Down Expand Up @@ -323,7 +324,7 @@ def reset(self):
return self

def clone(self):
return EasyCacheHolder(self.reuse_threshold, self.start_percent, self.end_percent, self.subsample_factor, self.offload_cache_diff, self.verbose)
return EasyCacheHolder(self.reuse_threshold, self.start_percent, self.end_percent, self.subsample_factor, self.offload_cache_diff, self.verbose, output_channels=self.output_channels)


class EasyCacheNode(io.ComfyNode):
Expand All @@ -350,15 +351,15 @@ def define_schema(cls) -> io.Schema:
@classmethod
def execute(cls, model: io.Model.Type, reuse_threshold: float, start_percent: float, end_percent: float, verbose: bool) -> io.NodeOutput:
model = model.clone()
model.model_options["transformer_options"]["easycache"] = EasyCacheHolder(reuse_threshold, start_percent, end_percent, subsample_factor=8, offload_cache_diff=False, verbose=verbose)
model.model_options["transformer_options"]["easycache"] = EasyCacheHolder(reuse_threshold, start_percent, end_percent, subsample_factor=8, offload_cache_diff=False, verbose=verbose, output_channels=model.model.latent_format.latent_channels)
model.add_wrapper_with_key(comfy.patcher_extension.WrappersMP.OUTER_SAMPLE, "easycache", easycache_sample_wrapper)
model.add_wrapper_with_key(comfy.patcher_extension.WrappersMP.CALC_COND_BATCH, "easycache", easycache_calc_cond_batch_wrapper)
model.add_wrapper_with_key(comfy.patcher_extension.WrappersMP.DIFFUSION_MODEL, "easycache", easycache_forward_wrapper)
return io.NodeOutput(model)


class LazyCacheHolder:
def __init__(self, reuse_threshold: float, start_percent: float, end_percent: float, subsample_factor: int, offload_cache_diff: bool, verbose: bool=False):
def __init__(self, reuse_threshold: float, start_percent: float, end_percent: float, subsample_factor: int, offload_cache_diff: bool, verbose: bool=False, output_channels: int=None):
self.name = "LazyCache"
self.reuse_threshold = reuse_threshold
self.start_percent = start_percent
Expand All @@ -382,6 +383,7 @@ def __init__(self, reuse_threshold: float, start_percent: float, end_percent: fl
self.approx_output_change_rates = []
self.total_steps_skipped = 0
self.state_metadata = None
self.output_channels = output_channels

def has_cache_diff(self) -> bool:
return self.cache_diff is not None
Expand Down Expand Up @@ -456,7 +458,7 @@ def reset(self):
return self

def clone(self):
return LazyCacheHolder(self.reuse_threshold, self.start_percent, self.end_percent, self.subsample_factor, self.offload_cache_diff, self.verbose)
return LazyCacheHolder(self.reuse_threshold, self.start_percent, self.end_percent, self.subsample_factor, self.offload_cache_diff, self.verbose, output_channels=self.output_channels)

class LazyCacheNode(io.ComfyNode):
@classmethod
Expand All @@ -482,7 +484,7 @@ def define_schema(cls) -> io.Schema:
@classmethod
def execute(cls, model: io.Model.Type, reuse_threshold: float, start_percent: float, end_percent: float, verbose: bool) -> io.NodeOutput:
model = model.clone()
model.model_options["transformer_options"]["easycache"] = LazyCacheHolder(reuse_threshold, start_percent, end_percent, subsample_factor=8, offload_cache_diff=False, verbose=verbose)
model.model_options["transformer_options"]["easycache"] = LazyCacheHolder(reuse_threshold, start_percent, end_percent, subsample_factor=8, offload_cache_diff=False, verbose=verbose, output_channels=model.model.latent_format.latent_channels)
model.add_wrapper_with_key(comfy.patcher_extension.WrappersMP.OUTER_SAMPLE, "lazycache", easycache_sample_wrapper)
model.add_wrapper_with_key(comfy.patcher_extension.WrappersMP.PREDICT_NOISE, "lazycache", lazycache_predict_noise_wrapper)
return io.NodeOutput(model)
Expand Down