ComfyUI Node: Composite Noise (Inspire)

Composite Noise (Inspire):

CompositeNoise __Inspire is a versatile node designed to enhance your AI-generated art by adding controlled noise to your images. This node allows you to introduce noise in a highly customizable manner, enabling you to achieve a variety of artistic effects and styles. By manipulating parameters such as noise seed, steps, and conditioning, you can fine-tune the noise addition process to suit your creative vision. The node supports both GPU and CPU noise generation, providing flexibility depending on your hardware setup. Additionally, it offers advanced options like batch seed modes and variation strengths, making it a powerful tool for artists looking to experiment with different noise patterns and intensities.

Composite Noise (Inspire) Input Parameters:

model

This parameter specifies the model to be used for noise generation. It is essential for defining the underlying architecture that will process the noise.

add_noise

This boolean parameter determines whether noise should be added. The default value is True, with labels "enable" and "disable" to toggle the noise addition.

noise_seed

An integer parameter that sets the seed for noise generation. This allows for reproducibility of noise patterns. The default value is 0, with a minimum of 0 and a maximum of 0xffffffffffffffff.

steps

This integer parameter defines the number of steps for the noise generation process. More steps can result in finer noise details. The default value is 20, with a range from 1 to 10000.

cfg

A float parameter that controls the configuration of the noise generation. The default value is 8.0, with a range from 0.0 to 100.0, adjustable in steps of 0.5 and rounded to 0.01.

sampler_name

This parameter specifies the sampler to be used from the available samplers in comfy.samplers.KSampler.SAMPLERS.

scheduler

This parameter sets the scheduler to be used from the available options in common.SCHEDULERS.

positive

This parameter provides positive conditioning for the noise generation process.

negative

This parameter provides negative conditioning for the noise generation process.

latent_image

This parameter specifies the latent image to which noise will be added.

start_at_step

An integer parameter that defines the starting step for noise addition. The default value is 0, with a range from 0 to 10000.

end_at_step

An integer parameter that defines the ending step for noise addition. The default value is 10000, with a range from 0 to 10000.

noise_mode

This parameter specifies the mode of noise generation, with options "GPU(=A1111)" and "CPU".

return_with_leftover_noise

A boolean parameter that determines whether to return the image with leftover noise. The default value is False, with labels "enable" and "disable".

interval

An integer parameter that sets the interval for noise addition steps. The default value is 1, with a range from 1 to 10000.

omit_start_latent

A boolean parameter that decides whether to omit the start latent image. The default value is False, with labels "True" and "False".

prev_progress_latent_opt (optional)

This optional parameter specifies a previous progress latent image.

scheduler_func_opt (optional)

This optional parameter allows for a custom scheduler function.

Composite Noise (Inspire) Output Parameters:

samples

This output parameter provides the final image with the added noise, based on the specified input parameters and configurations.

noise

This output parameter returns the generated noise that was added to the image, allowing for further analysis or reuse.

Composite Noise (Inspire) Usage Tips:

• Experiment with different noise_seed values to achieve unique noise patterns and ensure reproducibility.
• Adjust the steps parameter to control the granularity of the noise; higher values can produce more detailed noise effects.
• Utilize the positive and negative conditioning parameters to influence the noise generation process based on specific conditions.
• Switch between GPU and CPU modes using the noise_mode parameter to optimize performance based on your hardware capabilities.

Composite Noise (Inspire) Common Errors and Solutions:

"unexpected keyword argument 'scheduler_func'"

• Explanation: This error occurs when an outdated version of the Impact Pack is used, which does not support the scheduler_func argument.
• Solution: Update the Impact Pack to the latest version or remove the scheduler_func argument from your configuration.

"ValueError: Invalid noise seed"

• Explanation: This error occurs when the noise_seed parameter is set to a value outside the valid range.
• Solution: Ensure that the noise_seed is within the range of 0 to 0xffffffffffffffff.

"TypeError: 'NoneType' object is not subscriptable"

• Explanation: This error occurs when a required parameter is not provided or is set to None.
• Solution: Verify that all required parameters are correctly specified and not set to None.