Fix blur and sharpen nodes not working with fp16 intermediates. (#13181)
Some checks are pending
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Execution Tests / test (macos-latest) (push) Waiting to run
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Test server launches without errors / test (push) Waiting to run
Unit Tests / test (macos-latest) (push) Waiting to run
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Execution Tests / test (windows-latest) (push) Waiting to run
Unit Tests / test (windows-2022) (push) Waiting to run
Python Linting / Run Ruff (push) Waiting to run
Python Linting / Run Pylint (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run

This commit is contained in:
comfyanonymous 2026-03-26 19:18:16 -07:00 committed by GitHub
parent 1dc64f3526
commit b1fdbeb9a7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -67,11 +67,11 @@ class Blend(io.ComfyNode):
def g(cls, x):
return torch.where(x <= 0.25, ((16 * x - 12) * x + 4) * x, torch.sqrt(x))
def gaussian_kernel(kernel_size: int, sigma: float, device=None):
def gaussian_kernel(kernel_size: int, sigma: float, device=None, dtype=torch.float32):
x, y = torch.meshgrid(torch.linspace(-1, 1, kernel_size, device=device), torch.linspace(-1, 1, kernel_size, device=device), indexing="ij")
d = torch.sqrt(x * x + y * y)
g = torch.exp(-(d * d) / (2.0 * sigma * sigma))
return g / g.sum()
return (g / g.sum()).to(dtype)
class Blur(io.ComfyNode):
@classmethod
@ -99,7 +99,7 @@ class Blur(io.ComfyNode):
batch_size, height, width, channels = image.shape
kernel_size = blur_radius * 2 + 1
kernel = gaussian_kernel(kernel_size, sigma, device=image.device).repeat(channels, 1, 1).unsqueeze(1)
kernel = gaussian_kernel(kernel_size, sigma, device=image.device, dtype=image.dtype).repeat(channels, 1, 1).unsqueeze(1)
image = image.permute(0, 3, 1, 2) # Torch wants (B, C, H, W) we use (B, H, W, C)
padded_image = F.pad(image, (blur_radius,blur_radius,blur_radius,blur_radius), 'reflect')
@ -200,7 +200,7 @@ class Sharpen(io.ComfyNode):
image = image.to(comfy.model_management.get_torch_device())
kernel_size = sharpen_radius * 2 + 1
kernel = gaussian_kernel(kernel_size, sigma, device=image.device) * -(alpha*10)
kernel = gaussian_kernel(kernel_size, sigma, device=image.device, dtype=image.dtype) * -(alpha*10)
kernel = kernel.to(dtype=image.dtype)
center = kernel_size // 2
kernel[center, center] = kernel[center, center] - kernel.sum() + 1.0