Visit ComfyUI Online for ready-to-use ComfyUI environment
Facilitates configuring image generation parameters for AI models, ensuring flexibility and customization for precise artistic control.
The Generation Parameter Input node is designed to facilitate the configuration of various parameters required for generating images using AI models. This node allows you to specify essential settings such as seed, image dimensions, number of steps, and other parameters that influence the generation process. By providing a structured way to input these parameters, the node ensures that the generation process is both flexible and customizable, catering to different artistic needs and preferences. This node is particularly useful for AI artists who want to have precise control over the generation settings, enabling them to experiment with different configurations to achieve the desired output.
The seed
parameter is an integer value that initializes the random number generator used in the image generation process. This allows for reproducibility of results; using the same seed will produce the same image. The default value is 0, with a minimum of 0 and a maximum of 0xffffffffffffffff.
The image_width
parameter specifies the width of the generated image in pixels. It allows you to set the desired width, with a default value of 512 pixels. The minimum value is 0, and the maximum value is 1024 pixels, adjustable in steps of 8 pixels.
The image_height
parameter defines the height of the generated image in pixels. Similar to image_width
, it allows you to set the desired height, with a default value of 512 pixels. The minimum value is 0, and the maximum value is 1024 pixels, adjustable in steps of 8 pixels.
The steps
parameter determines the number of steps the model will take during the generation process. More steps generally lead to higher quality images but will take longer to generate. The default value is 20 steps, with a minimum of 0 and a maximum of 200 steps.
The cfg
(Classifier-Free Guidance) parameter is a float value that controls the strength of the guidance during the generation process. Higher values can lead to more detailed images but may also introduce artifacts. The default value is 7.0, with a minimum of 0.0 and a maximum of 30.0, adjustable in steps of 0.5.
The sampler_name
parameter allows you to choose the sampling method used during the generation process. It offers various options provided by comfy.samplers.KSampler.SAMPLERS
, with the default being "dpmpp_2m".
The scheduler
parameter specifies the scheduling method used during the generation process. It offers various options provided by comfy.samplers.KSampler.SCHEDULERS
, with the default being "karras".
The denoise
parameter is a float value that controls the amount of denoising applied during the generation process. A value of 1 means full denoising, while 0 means no denoising. The default value is 1, with a minimum of 0 and a maximum of 1.
The parameters
parameter is an optional input that allows you to pass a set of predefined parameters. This can be useful for reusing configurations or for more advanced control over the generation process.
The parameters
output returns a dictionary containing all the input parameters. This allows for easy reuse and modification of the settings in subsequent nodes or processes.
seed
values to explore a variety of generated images while keeping other parameters constant.steps
parameter to find a balance between image quality and generation time.cfg
parameter to fine-tune the level of detail and avoid overfitting or artifacts.sampler_name
and scheduler
options to see how they affect the final output.© Copyright 2024 RunComfy. All Rights Reserved.