Synchronize GPU state before LOW noise sampler, for new Wan22Blockswap #1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ockswap I remade the WanBlockswap node to run on Wan 2.2 and needed this little synchronizer to make the blockswap run with gguf models in the WanVideoLooper node. Without these few lines, there would be some wrong model block offloads inbetween the looped runs and comfyui needs to be restarted. I'll upload my updated Wan22Blockswap node later this day, I am just running some tests to check some stuff.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I remade the WanBlockswap node to run on Wan 2.2 and needed this little synchronizer to make the blockswap run with gguf models in the WanVideoLooper node. Without these few lines, there would be some wrong model block offloads inbetween the looped runs and comfyui needs to be restarted because the gguf model breaks in the ram and messes cuda up until comfy is restarted. Apparently is blockswapping mainly thought for safetensors and not ggufs, but it runs with ggufs anyways for me now :) I'll upload my updated Wan22Blockswap node later this day, I am just running some tests to check some stuff.
This is a generation on 720x960, which I could never ever run on my RTX 4080 with it's 16 GB. Swapped 30 blocks, and even that resolutions works ... takes forever, but is such a good quality as a compromise :)