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

comfy/ldm/cosmos/predict2.py

@@ -11,6 +11,7 @@ import math
 from .position_embedding import VideoRopePosition3DEmb, LearnablePosEmbAxis
 from torchvision import transforms
 
+import comfy.patcher_extension
 from comfy.ldm.modules.attention import optimized_attention
 
 def apply_rotary_pos_emb(
@@ -805,7 +806,21 @@ class MiniTrainDIT(nn.Module):
         )
         return x_B_C_Tt_Hp_Wp
 
-    def forward(
+    def forward(self,
+        x: torch.Tensor,
+        timesteps: torch.Tensor,
+        context: torch.Tensor,
+        fps: Optional[torch.Tensor] = None,
+        padding_mask: Optional[torch.Tensor] = 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, kwargs.get("transformer_options", {}))
+        ).execute(x, timesteps, context, fps, padding_mask, **kwargs)
+
+    def _forward(
         self,
         x: torch.Tensor,
         timesteps: torch.Tensor,