wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-03-06 09:47:35 +08:00
Code Issues Actions 17 Packages Projects Releases Wiki Activity

fix: handle substep sigmas in context window set_step (#12719)

Browse Source 
Multi-step samplers (eg. dpmpp_2s_ancestral) call the model at intermediate sigma values not present in the schedule. This caused set_step to crash with "No sample_sigmas matched current timestep" when context windows were enabled.

The fix is to keep self._step from the last exact match when a substep sigma is encountered, since substeps are still logically part of their parent step and should use the same context windows.

Co-authored-by: ozbayb <17261091+ozbayb@users.noreply.github.com>
This commit is contained in:
drozbay 2026-03-01 10:38:30 -07:00 committed by GitHub
parent 850e8b42ff
commit 4d79f4f028
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/context_windows.py
View File

@ -214,7 +214,7 @@ class IndexListContextHandler(ContextHandlerABC):
mask = torch.isclose(model_options["transformer_options"]["sample_sigmas"], timestep[0], rtol=0.0001) mask = torch.isclose(model_options["transformer_options"]["sample_sigmas"], timestep[0], rtol=0.0001)
matches = torch.nonzero(mask) matches = torch.nonzero(mask)
if torch.numel(matches) == 0: if torch.numel(matches) == 0:
raise Exception("No sample_sigmas matched current timestep; something went wrong.") return # substep from multi-step sampler: keep self._step from the last full step
self._step = int(matches[0].item()) self._step = int(matches[0].item())
def get_context_windows(self, model: BaseModel, x_in: torch.Tensor, model_options: dict[str]) -> list[IndexListContextWindow]: def get_context_windows(self, model: BaseModel, x_in: torch.Tensor, model_options: dict[str]) -> list[IndexListContextWindow]: