Integrate Feature-Reactivity With FlexExpressionEditor Node#65
Open
ryanontheinside wants to merge 57 commits intoPowerHouseMan:mainfrom
Open
Integrate Feature-Reactivity With FlexExpressionEditor Node#65ryanontheinside wants to merge 57 commits intoPowerHouseMan:mainfrom
ryanontheinside wants to merge 57 commits intoPowerHouseMan:mainfrom
Conversation
Add pyproject.toml for Custom Node Registry
Add Github Action for Publishing to Comfy Registry
…nd cpu, depending on the available device.
Add support for Mac Users
Changed to allow partial reference to sample image
features include audio, MIDI, motion, proximity, time, depth, etc.
Author
|
Hello @PowerHouseMan, just following up to see if you had a chance to take a look. |
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 introduces a feature-reactivity system for expressions in ComfyUI-AdvancedLivePortrait, allowing expressions to be modulated dynamically by various feature sources. The feature sources supported include audio, MIDI, motion, proximity, time, depth, color, brightness, pitch, and more.
Main Contribution:
To implement this system, I have added a new node called the FlexExpressionEditor. This node functions similarly to the existing expression editor but is enhanced to accept feature inputs, enabling expressions to be modulated over time by external sources such as audio. Key features of the FlexExpressionEditor include:
Feature Targets: any of the expression parameters can be modulated by the feature input
Interchangeable Feature Sources: Any supported feature source can be applied interchangeably
Chaining Capability: Multiple FlexExpressionEditor nodes can be chained, enabling complex and layered expression control.
Benefits:
The FlexExpressionEditor adds a powerful dimension to the expression capabilities within this project, providing users with fine-grain control over expressions through external inputs. This enhancement offers substantial new functionality with no impact on the existing features or workflows.
Additional Information:
Thank you for considering this addition. I am open to any feedback or suggestions for further refinement.
Using drums to rotate_pitch, synth for pupil_x, and manual feature for rotate_roll:
https://github.com/user-attachments/assets/72f95c90-9fa9-4e3e-a492-739566c188c9
Using time feature to modulate aaa and the motion of the driving video to modulate yaw:
https://github.com/user-attachments/assets/cc43b439-e089-43c0-8a3e-d9b16467d983
Using proximity to control aaa:
https://github.com/user-attachments/assets/828039ef-5d9b-4f93-a818-ae1c1ce31cc9
Using area to control blink:
https://github.com/user-attachments/assets/cd383ba7-984a-4c56-a927-ff9fd608e5f8