ComfyUIĀ Ā >Ā Ā NodesĀ Ā >Ā Ā AnimateDiff Evolved >Ā Ā FreeInit Iteration Options šŸŽ­šŸ…šŸ…“

ComfyUI Node: FreeInit Iteration Options šŸŽ­šŸ…šŸ…“

Class Name

ADE_IterationOptsFreeInit

Category
Animate Diff šŸŽ­šŸ…šŸ…“/iteration opts
Author
Kosinkadink (Account age: 3712 days)
Extension
AnimateDiff Evolved
Latest Updated
6/17/2024
Github Stars
2.2K

How to Install AnimateDiff Evolved

Install this extension via the ComfyUI Manager by searching for Ā AnimateDiff Evolved
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter AnimateDiff Evolved in the search bar
After installation, click the Ā Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • High-speed GPU machines
  • 200+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 50+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

FreeInit Iteration Options šŸŽ­šŸ…šŸ…“ Description

Customizable iteration options for AnimateDiff framework, fine-tuning parameters for precise animation diffusion results.

FreeInit Iteration Options šŸŽ­šŸ…šŸ…“:

The ADE_IterationOptsFreeInit node is designed to provide flexible and customizable iteration options for the AnimateDiff framework. This node allows you to fine-tune the iteration process by specifying various parameters that control the behavior of iterations, including the number of iterations, batch offsets, seed offsets, and initialization types. By leveraging these options, you can achieve more precise and tailored results in your animation diffusion tasks. The node is particularly useful for artists looking to experiment with different iteration settings to optimize their creative outputs.

FreeInit Iteration Options šŸŽ­šŸ…šŸ…“ Input Parameters:

iterations

This parameter specifies the number of iterations to be performed. It determines how many times the iteration process will be executed, directly impacting the refinement and quality of the output. The minimum value is 1, and the default value is set to 2.

filter

This parameter allows you to choose the type of filter to be applied during the iteration process. The available options are FreeInitFilter.LIST, which includes gaussian, butterworth, ideal, and box. Each filter type affects the noise and frequency characteristics of the iterations differently.

d_s

This parameter controls the spatial decay factor, influencing how quickly the effect of the filter diminishes over space. It ranges from 0.0 to 1.0, with a default value of 0.25. Adjusting this value can help you fine-tune the spatial characteristics of the iterations.

d_t

This parameter controls the temporal decay factor, affecting how quickly the effect of the filter diminishes over time. It ranges from 0.0 to 1.0, with a default value of 0.25. This parameter is useful for managing the temporal consistency of the iterations.

n_butterworth

This parameter sets the order of the Butterworth filter, which is used to control the frequency response of the iterations. The value ranges from 1 to 100, with a default value of 4. Higher values result in a sharper cutoff in the frequency domain.

sigma_step

This parameter defines the step size for the sigma value used in the iteration process. It ranges from 1 to 999, with a default value of 999. This parameter is crucial for controlling the noise level and smoothness of the iterations.

apply_to_1st_iter

This boolean parameter determines whether the specified settings should be applied to the first iteration. The default value is False. Enabling this option can help you achieve a consistent starting point for the iterations.

init_type

This parameter allows you to select the initialization type for the iterations. The available options are defined in FreeInitOptions.LIST. The choice of initialization type can significantly impact the behavior and outcome of the iterations.

iter_batch_offset

This optional parameter specifies the batch offset for the iterations. It ranges from 0 to BIGMAX, with a default value of 0. Adjusting this value can help you manage the batch processing of iterations.

iter_seed_offset

This optional parameter sets the seed offset for the iterations. It ranges from BIGMIN to BIGMAX, with a default value of 1. This parameter is useful for controlling the randomness and reproducibility of the iterations.

FreeInit Iteration Options šŸŽ­šŸ…šŸ…“ Output Parameters:

ITERATION_OPTS

This output parameter returns the configured iteration options as an IterationOptions object. This object encapsulates all the specified settings and can be used to control the iteration process in subsequent nodes. The output is essential for ensuring that the desired iteration behavior is applied consistently throughout the animation diffusion workflow.

FreeInit Iteration Options šŸŽ­šŸ…šŸ…“ Usage Tips:

  • Experiment with different filter types (gaussian, butterworth, ideal, box) to see how they affect the noise and frequency characteristics of your iterations.
  • Adjust the d_s and d_t parameters to fine-tune the spatial and temporal decay factors, respectively, for more precise control over the iteration effects.
  • Use the n_butterworth parameter to control the sharpness of the Butterworth filter's frequency response, which can help you achieve the desired level of detail in your iterations.
  • Set the apply_to_1st_iter parameter to True if you want to ensure a consistent starting point for your iterations, especially when experimenting with different settings.

FreeInit Iteration Options šŸŽ­šŸ…šŸ…“ Common Errors and Solutions:

Invalid value for iterations

  • Explanation: The value provided for the iterations parameter is outside the allowed range.
  • Solution: Ensure that the iterations value is at least 1.

Invalid filter type

  • Explanation: The specified filter type is not recognized.
  • Solution: Choose a valid filter type from FreeInitFilter.LIST, such as gaussian, butterworth, ideal, or box.

Out of range value for d_s or d_t

  • Explanation: The values for d_s or d_t are outside the allowed range of 0.0 to 1.0.
  • Solution: Adjust the d_s and d_t values to be within the range of 0.0 to 1.0.

Out of range value for n_butterworth

  • Explanation: The value for n_butterworth is outside the allowed range of 1 to 100.
  • Solution: Set the n_butterworth value to be within the range of 1 to 100.

Out of range value for sigma_step

  • Explanation: The value for sigma_step is outside the allowed range of 1 to 999. - Solution: Ensure that the sigma_step value is within the range of 1 to 999.

Invalid value for iter_batch_offset or iter_seed_offset

  • Explanation: The values for iter_batch_offset or iter_seed_offset are outside the allowed range.
  • Solution: Adjust the iter_batch_offset and iter_seed_offset values to be within their respective allowed ranges.

FreeInit Iteration Options šŸŽ­šŸ…šŸ…“ Related Nodes

Go back to the extension to check out more related nodes.
AnimateDiff Evolved
RunComfy

Ā© Copyright 2024 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals.