mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2025-09-12 20:48:22 +00:00
Implement EasyCache and Invent LazyCache (#9496)
* Attempting a universal implementation of EasyCache, starting with flux as test; I screwed up the math a bit, but when I set it just right it works. * Fixed math to make threshold work as expected, refactored code to use EasyCacheHolder instead of a dict wrapped by object * Use sigmas from transformer_options instead of timesteps to be compatible with a greater amount of models, make end_percent work * Make log statement when not skipping useful, preparing for per-cond caching * Added DIFFUSION_MODEL wrapper around forward function for wan model * Add subsampling for heuristic inputs * Add subsampling to output_prev (output_prev_subsampled now) * Properly consider conds in EasyCache logic * Created SuperEasyCache to test what happens if caching and reuse is moved outside the scope of conds, added PREDICT_NOISE wrapper to facilitate this test * Change max reuse_threshold to 3.0 * Mark EasyCache/SuperEasyCache as experimental (beta) * Make Lumina2 compatible with EasyCache * Add EasyCache support for Qwen Image * Fix missing comma, curse you Cursor * Add EasyCache support to AceStep * Add EasyCache support to Chroma * Added EasyCache support to Cosmos Predict t2i * Make EasyCache not crash with Cosmos Predict ImagToVideo latents, but does not work well at all * Add EasyCache support to hidream * Added EasyCache support to hunyuan video * Added EasyCache support to hunyuan3d * Added EasyCache support to LTXV (not very good, but does not crash) * Implemented EasyCache for aura_flow * Renamed SuperEasyCache to LazyCache, hardcoded subsample_factor to 8 on nodes * Eatra logging when verbose is true for EasyCache
This commit is contained in:
@@ -1,5 +1,6 @@
|
||||
import torch
|
||||
from torch import nn
|
||||
import comfy.patcher_extension
|
||||
import comfy.ldm.modules.attention
|
||||
import comfy.ldm.common_dit
|
||||
from einops import rearrange
|
||||
@@ -420,6 +421,13 @@ class LTXVModel(torch.nn.Module):
|
||||
self.patchifier = SymmetricPatchifier(1)
|
||||
|
||||
def forward(self, x, timestep, context, attention_mask, frame_rate=25, transformer_options={}, keyframe_idxs=None, **kwargs):
|
||||
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
|
||||
self._forward,
|
||||
self,
|
||||
comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.DIFFUSION_MODEL, transformer_options)
|
||||
).execute(x, timestep, context, attention_mask, frame_rate, transformer_options, keyframe_idxs, **kwargs)
|
||||
|
||||
def _forward(self, x, timestep, context, attention_mask, frame_rate=25, transformer_options={}, keyframe_idxs=None, **kwargs):
|
||||
patches_replace = transformer_options.get("patches_replace", {})
|
||||
|
||||
orig_shape = list(x.shape)
|
||||
|
Reference in New Issue
Block a user