mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-09-13 21:16:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Implement EasyCache and Invent LazyCache (#9496)

Browse Source 
* 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:
Jedrzej Kosinski
2025-08-22 19:41:08 -07:00
committed by GitHub
parent fe31ad0276
commit fc247150fe
17 changed files with 639 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
comfy/ldm/ace/model.py
View File

@@ -19,6 +19,7 @@ import torch
from torch import nn
import comfy.model_management
import comfy.patcher_extension
from comfy.ldm.lightricks.model import TimestepEmbedding, Timesteps
from .attention import LinearTransformerBlock, t2i_modulate
@@ -343,7 +344,28 @@ class ACEStepTransformer2DModel(nn.Module):
output = self.final_layer(hidden_states, embedded_timestep, output_length)
return output
def forward(
def forward(self,
x,
timestep,
attention_mask=None,
context: Optional[torch.Tensor] = None,
text_attention_mask: Optional[torch.LongTensor] = None,
speaker_embeds: Optional[torch.FloatTensor] = None,
lyric_token_idx: Optional[torch.LongTensor] = None,
lyric_mask: Optional[torch.LongTensor] = None,
block_controlnet_hidden_states: Optional[Union[List[torch.Tensor], torch.Tensor]] = None,
controlnet_scale: Union[float, torch.Tensor] = 1.0,
lyrics_strength=1.0,
**kwargs
):
return comfy.patcher_extension.WrapperExecutor.new_class_executor(
self._forward,
self,
comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.DIFFUSION_MODEL, kwargs.get("transformer_options", {}))
).execute(x, timestep, attention_mask, context, text_attention_mask, speaker_embeds, lyric_token_idx, lyric_mask, block_controlnet_hidden_states,
controlnet_scale, lyrics_strength, **kwargs)
def _forward(
self,
x,
timestep,