Repository navigation
Fix Low VRAM Audio VAE loader returning an unusable model - #562
Open
Henry Kroll III (themanyone) wants to merge 2 commits into
Open
Henry Kroll III (themanyone) wants to merge 2 commits into
Henry Kroll III (themanyone) wants to merge 2 commits into
Conversation
The node instantiated the internal AudioVAE module directly with the state dict, which raised a TypeError (the constructor only accepts metadata) and, even when given metadata alone, produced a bare model with no weights instead of a VAE. Loading now goes through the public VAE wrapper like the core audio VAE loader, so the node returns a working VAE that downstream audio encode/decode nodes can use. 💘 Generated with Crush Assisted-by: Crush:deepseek-v4-flash
Author
|
There was another err2.txt which started happening after an update a while back. Working around it by inserting Cheers! |
Bring in tiled fusion sampler and workflow updates from upstream, resolving any overlapping changes in favor of upstream.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When running ComfyUI with
--lowvramafter updatelow_vram_loaders.pyfails withTypeError: AudioVAE.__init__() takes 2 positional arguments but 3 were givenerr.txt
The fix
The node instantiated the internal AudioVAE module directly with the state dict, which raised a TypeError (the constructor only accepts metadata) and, even when given metadata alone, produced a bare model with no weights instead of a VAE. Loading now goes through the public VAE wrapper like the core audio VAE loader, so the node returns a working VAE that downstream audio encode/decode nodes can use.
💘 Generated with Crush
Assisted-by: Crush:deepseek-v4-flash
Tested by: themanyone with heavy LTX 3.5 ia2v workflow in ComfyUI --lowvram
[INFO] Prompt executed in 588.98 seconds
CPU: 8-core AMD Ryzen 9 5900HX with Radeon Graphics (-MT MCP-)
speed/min/max: 1100/423/4683 MHz Kernel: 7.2.5-100.fc43.x86_64 x86_64
Up: 12h 24m Mem: 9.21/31.23 GiB (29.5%) Storage: 1.84 TiB (48.7% used)
Procs: 474 Shell: Bash inxi: 3.3.41
Graphics:
Device-1: NVIDIA GA104M [GeForce RTX 3070 Mobile / Max-Q] driver: nvidia
v: 615.71.09