wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-02-14 23:42:35 +08:00
Code Issues Actions 14 Packages Projects Releases Wiki Activity

Make tonemap latent work on any dim latents. (#12363)
Some checks are pending
Python Linting / Run Ruff (push) Waiting to run
Details
Python Linting / Run Pylint (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Details
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Details
Execution Tests / test (macos-latest) (push) Waiting to run
Details
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Details
Execution Tests / test (windows-latest) (push) Waiting to run
Details
Test server launches without errors / test (push) Waiting to run
Details
Unit Tests / test (macos-latest) (push) Waiting to run
Details
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Details
Unit Tests / test (windows-2022) (push) Waiting to run
Details

Browse Source
This commit is contained in:
comfyanonymous 2026-02-08 18:16:40 -08:00 committed by GitHub
parent f350a84261
commit a0302cc6a8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
comfy_extras/nodes_latent.py
View File

@ -391,8 +391,9 @@ class LatentOperationTonemapReinhard(io.ComfyNode):
latent_vector_magnitude = (torch.linalg.vector_norm(latent, dim=(1)) + 0.0000000001)[:,None] latent_vector_magnitude = (torch.linalg.vector_norm(latent, dim=(1)) + 0.0000000001)[:,None]
normalized_latent = latent / latent_vector_magnitude normalized_latent = latent / latent_vector_magnitude
mean = torch.mean(latent_vector_magnitude, dim=(1,2,3), keepdim=True) dims = list(range(1, latent_vector_magnitude.ndim))
std = torch.std(latent_vector_magnitude, dim=(1,2,3), keepdim=True) mean = torch.mean(latent_vector_magnitude, dim=dims, keepdim=True)
std = torch.std(latent_vector_magnitude, dim=dims, keepdim=True)
top = (std * 5 + mean) * multiplier top = (std * 5 + mean) * multiplier