This should make it possible to do higher res images/longer videos by
further offloading weights to CPU memory.
Please report an issue if this slows down things on your system.
The 10 step minimum for the AYS scheduler is pointless, it works well at lower steps, like 8 steps, or even 4 steps.
For example with LCM or DMD2.
Example here: https://i.ibb.co/56CSPMj/image.png
Python Linting / Run Ruff (push) Successful in 1m50s
Test server launches without errors / test (push) Failing after 1m5s
Unit Tests / test (ubuntu-latest) (push) Failing after 1h23m5s
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Has been cancelled
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Has been cancelled
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Has been cancelled
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.9, [self-hosted Linux], stable) (push) Has been cancelled
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.10, [self-hosted macOS], stable) (push) Has been cancelled
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.11, [self-hosted macOS], stable) (push) Has been cancelled
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.12, [self-hosted macOS], stable) (push) Has been cancelled
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.9, [self-hosted macOS], stable) (push) Has been cancelled
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Has been cancelled
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, --use-pytorch-cross-attention, macos, 3.11, [self-hosted macOS], nightly) (push) Has been cancelled
Unit Tests / test (macos-latest) (push) Has been cancelled
Unit Tests / test (windows-latest) (push) Has been cancelled
The downscale_ratio formula for the temporal had issues with some frame
numbers.
* fix attention OOM in xformers
* allow passing attention mask in flux attention
* allow an attn_mask in flux
* attn masks can be done using replace patches instead of a separate dict
* fix return types
* fix return order
* enumerate
* patch the right keys
* arg names
* fix a silly bug
* fix xformers masks
* replace match with if, elif, else
* mask with image_ref_size
* remove unused import
* remove unused import 2
* fix pytorch/xformers attention
This corrects a weird inconsistency with skip_reshape.
It also allows masks of various shapes to be passed, which will be
automtically expanded (in a memory-efficient way) to a size that is
compatible with xformers or pytorch sdpa respectively.
* fix mask shapes
The last ROCM 6.2 build was November 22nd, after that date new builds use ROCM 6.2.4.
The builds from the new URL have been tested and work without problems.
* fix: The custom nodes installed in the paths specified in `extra_model_paths.yaml` encounter a bug where the prestartup script is not imported.
* Ensure custom paths are used during startup
https://github.com/comfyanonymous/ComfyUI/pull/5794
