nodes/Kosinkadink-ComfyUI-Advanced-ControlNet

T

Masks were returned as single image, which wouldn't work with AnimateDiff.

2023-09-24 18:29:57 +03:00

__init__.py

Added advanced ControlNet loaders, added customizable ControlNet weight nodes

2023-08-01 08:59:18 -05:00

.gitignore

Initial commit

2023-07-31 22:12:07 -05:00

control.py

Using "UNion" instead of "|" for documenting return type to be python 3.9-compatible

2023-09-22 11:41:46 -05:00

LICENSE

Initial commit

2023-07-31 22:12:07 -05:00

logger.py

Updated to support sliding window usage by other extensions, added scaffolding code to support masks in controlnet, added logger for future use

2023-09-18 11:23:01 -05:00

nodes.py

Fix mask output

2023-09-24 18:29:57 +03:00

README.md

Started to update README.md

2023-08-26 10:43:12 -05:00

requirements.txt

Added advanced ControlNet loaders, added customizable ControlNet weight nodes

2023-08-01 08:59:18 -05:00

README.md

ComfyUI-Advanced-ControlNet

These custom nodes allow for scheduling ControlNet strength across latents in the same batch (WORKING) and across timesteps (IN PROGRESS).

Custom weights can also be applied to ControlNets and T2IAdapters to mimic the "My prompt is more important" functionality in AUTOMATIC1111's ControlNet extension.

TODO:

Add combined Latent Timestep Keyframe nodes to allow faster setup for easier workflows and to use a single ControlNet for a batch of images; too inefficient and redundant right now for common workflows
Other handy nodes
Finish and update this README for other workflows

Workflows

AnimateDiff Workflows

Latent Keyframes identify which latents in a batch the ControlNet should apply to, and at what strength. They connect to a Timestep Keyframe to identify at what point in the generation to kick in (for basic use, start_percent on the Timestep Keyframe should be 0.0). Latent Keyframe nodes can be chained to apply the ControlNet to multiple keyframes at various strengths.