This repository has been archived by the owner on Jan 9, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 165
Refactor and Optimize Codebase for latest ComfyUI #237
Open
toxicwind
wants to merge
158
commits into
LucianoCirino:main
Choose a base branch
from
toxicwind:main
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Conversation
This file contains 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
Basic info on Comfy Efficiency Nodes.
readme
funding options
all node images updated
changes to how advanced encode work .. possibly resolves the token issues
3 lines -4118,4119, 4121 changed
many small codes in the l is tokenized is modified
Add Github Action for Publishing to Comfy Registry
Add pyproject.toml for Custom Node Registry
"both" was missing
Load settings fix
Show latent upscaler when "both" is selected
omfy.sampler's 'convert cond' has been removed so line 127 changes
changes in line 131 check same
module 'comfy.sample' has no attribute 'get_additional_models'
…LucianoCirino#203) This fixes cases where the widget is not a plain object, but a class instance with `value` getters/setters.
* bugfix: in case of XY_Capsule, prompt needs to be encoded by the analysed LoRA's clip * bugfix: when processing LoRAs you need to reload the LoRA every index on the y scale (not only the first one) to maintain the LoRA-patched clip. * add align your step schedulers via monkey patching --------- Co-authored-by: larsupb <[email protected]>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
This pull request aims to enhance the codebase by improving code organization, readability, and maintainability. The changes made are as follows:
Code Organization and Style:
Refactored Functions:
adjust_tensor_shape
,expand
, andbounded_modulo
for improved efficiency and readability.calc_cond
Function:catenate_conds
andsubscript_cond
Functions:pad_cond
Function:F.pad
for efficient tensor padding.CFGDenoiser
Class:prepare_inputs
,prepare_cond
,apply_model
, andpost_process
for modularity and readability.CFGNoisePredictor
Class:apply_model
method for readability and modularity.txt2img_image_conditioning
method static for better organization.SDKSampler
Class:set_model_wrap
method to set themodel_wrap
attribute for improved organization.set_model_wrap
method.These changes aim to improve code quality and make it more readable and maintainable while preserving the original functionality of the code. The code remains functionally intact, but the enhancements result in a cleaner, more organized, and better-documented codebase.