ComfyUI > Nodes > ComfyUI Fooocus Nodes > Fooocus PreKSampler

ComfyUI Node: Fooocus PreKSampler

Class Name

Fooocus PreKSampler

Category
Fooocus
Author
Seedsa (Account age: 2658days)
Extension
ComfyUI Fooocus Nodes
Latest Updated
2024-08-08
Github Stars
0.05K

How to Install ComfyUI Fooocus Nodes

Install this extension via the ComfyUI Manager by searching for ComfyUI Fooocus Nodes
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI Fooocus Nodes in the search bar
After installation, click the 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

Fooocus PreKSampler Description

Specialized node enhancing AI art sampling with advanced algorithms for refined image creation control and improved quality.

Fooocus PreKSampler:

The Fooocus PreKSampler is a specialized node designed to enhance the sampling process in AI art generation. It leverages advanced algorithms to refine and optimize the initial stages of image creation, ensuring higher quality and more detailed outputs. This node is particularly beneficial for artists looking to achieve precise control over the sampling parameters, allowing for a more tailored and refined artistic output. By integrating the Fooocus PreKSampler into your workflow, you can expect improved consistency and quality in your generated images, making it an essential tool for any AI artist aiming for professional-grade results.

Fooocus PreKSampler Input Parameters:

model

This parameter specifies the model to be used for sampling. It is a required input and ensures that the correct model is applied during the sampling process.

seed

The seed parameter is an integer that initializes the random number generator, ensuring reproducibility of results. It has a default value of 0, with a minimum value of 0 and a maximum value of 0xffffffffffffffff. Using the same seed will produce the same output, which is useful for consistency.

steps

This integer parameter defines the number of steps to be taken during the sampling process. It has a default value of 20, with a minimum of 1 and a maximum of 10000. More steps generally lead to higher quality images but will take longer to process.

cfg

The cfg (classifier-free guidance) parameter is a float that controls the strength of the guidance. It has a default value of 8.0, with a range from 0.0 to 100.0, adjustable in steps of 0.1 and rounded to 0.01. Higher values can lead to more pronounced features in the generated image.

sampler_name

This parameter allows you to select the specific sampling algorithm to be used. It offers various options such as "euler", "heun", "dpm_2", and others, each providing different characteristics and results in the sampling process.

scheduler

The scheduler parameter determines the scheduling strategy for the sampling steps. Different schedulers can affect the pacing and quality of the sampling process.

positive

This conditioning parameter provides positive prompts that guide the model towards desired features in the generated image. It is essential for steering the model in the right direction.

negative

Similar to the positive parameter, this conditioning parameter provides negative prompts that help the model avoid undesired features in the generated image.

latent_image

The latent_image parameter is an optional input that allows you to provide a latent image to be used as a starting point for the sampling process. This can be useful for refining or continuing work on an existing image.

denoise

This float parameter controls the level of denoising applied during the sampling process. It has a default value of 1.0, with a range from 0.0 to 1.0, adjustable in steps of 0.01. Lower values can retain more noise, leading to more abstract results, while higher values produce cleaner images.

Fooocus PreKSampler Output Parameters:

LATENT

The output of the Fooocus PreKSampler is a latent representation of the generated image. This latent output can be further processed or decoded into a final image. It encapsulates the refined and optimized features resulting from the sampling process, providing a high-quality basis for the final artwork.

Fooocus PreKSampler Usage Tips:

  • Experiment with different seeds to explore a variety of outputs and find the most appealing results.
  • Adjust the steps parameter to balance between processing time and image quality; more steps generally yield better results.
  • Use the cfg parameter to fine-tune the strength of the guidance, which can significantly impact the final image's features.
  • Combine positive and negative prompts strategically to guide the model towards desired characteristics and away from unwanted ones.

Fooocus PreKSampler Common Errors and Solutions:

Invalid base_resolution format.

  • Explanation: This error occurs when the resolution format provided is incorrect or cannot be parsed.
  • Solution: Ensure that the resolution is specified in the correct format, such as "width x height", and that both width and height are valid integers.

To use SAMLoader, you need to install 'Impact Pack'

  • Explanation: This error indicates that the required 'Impact Pack' is not installed, which is necessary for using the SAMLoader.
  • Solution: Install the 'Impact Pack' to enable the functionality of the SAMLoader. Follow the installation instructions provided in the documentation or support resources.

KeyError: 'positive'

  • Explanation: This error occurs when the positive prompt is not provided or incorrectly referenced.
  • Solution: Ensure that the positive prompt is included in the input parameters and correctly referenced in the code.

KeyError: 'negative'

  • Explanation: This error occurs when the negative prompt is not provided or incorrectly referenced.
  • Solution: Ensure that the negative prompt is included in the input parameters and correctly referenced in the code.

Fooocus PreKSampler Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI Fooocus Nodes
RunComfy

© 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.