Go to OpenArt main site
Upload workflow

[v2.0] ControlNet Passes Extractor with Custom Save Folders [Part 1]

5.0

0 reviews
75
16.2K
3.7K
8
Description

New Update v2.1 !!! Available Here :  https://www.patreon.com/posts/update-v2-1-lcm-95056616

.

.

This workflow is part 1 of this main animation workflow : https://youtu.be/HbfDjAMFi6w

This is a Control Net Passes Exporter with custom save directory


What this workflow does

It Exports ControlNet Passes  - Canny, Depth, Hed, DwOpenPose, LineArt, Normal and Image Source Frames which are First hand, base dough for the main Animation Workflow

This Workflow firsthand make these passes and saves them in an organized way which can be used in any animation workflow

This workflow saves 10% - 20% time and ram, used up in extracting the passes during the main render. This also enables to test and experiment Animations faster.

Documented Examples :

1) https://www.patreon.com/posts/ai-animatediff-93266466  and

Loras Experiment: https://www.patreon.com/posts/93438322

2) https://www.patreon.com/posts/ai-animatediff-91407120


How to use this workflow

1) You just need to copy the path of your video, and enter an output folder, it will handle the rest including making folders.

2) Enable Passes you want to extract - Lineart, Hed, Depth, Canny, DwOP, Normal

3) Upscale or Downscale If needed

Hit Queue.

Documented Tutorial Can be found here :  https://www.patreon.com/posts/update-passes-v2-92938805


CONS

  • To avoid "No input error" while running it saves a black image in the passes folder which are not being enabled.
  • If you want to re-use the same video for another pass, export it in a different folder or else you can have 2x images in the passes accidently. Also It will generated a black image again in the passes folder which are not enabled.




My Discord Server : https://discord.gg/z9rgJyfPWJ

Discussion

(No comments yet)

Loading...

Author

27
98.4K
2.1K
2.3M

No reviews yet

  • - latest (7 months ago)

Primitive Nodes (3)

Note (1)

Reroute (2)

Custom Nodes (52)

ComfyUI

  • - EmptyImage (1)

  • - ImageScaleBy (1)

  • - ImageScale (1)

ComfyUI Nodes for Inference.Core

  • - MiDaS-DepthMapPreprocessor (1)

  • - LineArtPreprocessor (1)

  • - DWPreprocessor (1)

  • - HEDPreprocessor (1)

  • - CannyEdgePreprocessor (1)

  • - BAE-NormalMapPreprocessor (1)

  • - If ANY execute A else B (9)

  • - VHS_LoadVideoPath (1)

  • - GetImageSize (1)

  • - Image Save (7)

  • - Text Concatenate (7)

  • - Logic Boolean (8)

  • - Constant Number (2)

  • - String to Text (1)

  • - Text String (7)

Checkpoints (0)

LoRAs (0)