Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

percent_to_sigma now returns a float instead of a tensor.

comfyanonymousd9d8702d8dd2
diff --git a/comfy/model_sampling.py b/comfy/model_sampling.py
index d5b1642ef..37a3ac725 100644
--- a/comfy/model_sampling.py
+++ b/comfy/model_sampling.py
@@ -77,9 +77,9 @@ class ModelSamplingDiscrete(torch.nn.Module):
def percent_to_sigma(self, percent):
if percent <= 0.0:
- return torch.tensor(999999999.9)
+ return 999999999.9
if percent >= 1.0:
- return torch.tensor(0.0)
+ return 0.0
percent = 1.0 - percent
- return self.sigma(torch.tensor(percent * 999.0))
+ return self.sigma(torch.tensor(percent * 999.0)).item()
diff --git a/comfy_extras/nodes_model_advanced.py b/comfy_extras/nodes_model_advanced.py
index c8c4b4a1e..0f4ddd9c3 100644
--- a/comfy_extras/nodes_model_advanced.py
+++ b/comfy_extras/nodes_model_advanced.py
@@ -67,11 +67,11 @@ class ModelSamplingDiscreteLCM(torch.nn.Module):
def percent_to_sigma(self, percent):
if percent <= 0.0:
- return torch.tensor(999999999.9)
+ return 999999999.9
if percent >= 1.0:
- return torch.tensor(0.0)
+ return 0.0
percent = 1.0 - percent
- return self.sigma(torch.tensor(percent * 999.0))
+ return self.sigma(torch.tensor(percent * 999.0)).item()
def rescale_zero_terminal_snr_sigmas(sigmas):
diff --git a/comfy_extras/nodes_model_downscale.py b/comfy_extras/nodes_model_downscale.py
index 8850d0948..f65ef05e1 100644
--- a/comfy_extras/nodes_model_downscale.py
+++ b/comfy_extras/nodes_model_downscale.py
@@ -16,8 +16,8 @@ class PatchModelAddDownscale:
CATEGORY = "_for_testing"
def patch(self, model, block_number, downscale_factor, start_percent, end_percent, downscale_after_skip):
- sigma_start = model.model.model_sampling.percent_to_sigma(start_percent).item()
- sigma_end = model.model.model_sampling.percent_to_sigma(end_percent).item()
+ sigma_start = model.model.model_sampling.percent_to_sigma(start_percent)
+ sigma_end = model.model.model_sampling.percent_to_sigma(end_percent)
def input_block_patch(h, transformer_options):
if transformer_options["block"][1] == block_number: