ComfyUI Node: Sampler Custom XY 🍌

Sampler Custom XY 🍌| Sampler Custom XY 🍌:

The SamplerCustomXY| Sampler Custom XY 🍌 node is designed to facilitate the sampling process in AI art generation by leveraging multiple models simultaneously. This node allows you to input a collection of models and apply sampling techniques to generate outputs that combine the strengths of each model. The primary function of this node is to perform sampling with added noise, configurable parameters, and conditioning inputs, making it a versatile tool for creating diverse and high-quality AI-generated art. By using this node, you can achieve more nuanced and refined results, as it integrates the outputs from various models into a cohesive final image.

Sampler Custom XY 🍌| Sampler Custom XY 🍌 Input Parameters:

model_xy

This parameter accepts a collection of models (XY_MODEL) that will be used for sampling. Each model in the collection contributes to the final output, allowing for a blend of different styles and features.

add_noise

A boolean parameter (BOOLEAN) that determines whether noise should be added during the sampling process. The default value is True. Adding noise can help in generating more varied and interesting outputs.

noise_seed

An integer parameter (INT) that sets the seed for noise generation. The default value is 0, with a minimum of 0 and a maximum of 0xffffffffffffffff. This seed ensures reproducibility of the noise added during sampling.

cfg

A float parameter (FLOAT) that controls the classifier-free guidance scale. The default value is 8.0, with a range from 0.0 to 100.0, adjustable in steps of 0.1 and rounded to 0.01. This parameter influences the strength of the guidance applied during sampling.

positive

This parameter accepts conditioning inputs (CONDITIONING) that positively influence the sampling process. These inputs guide the model towards desired features or styles.

negative

This parameter accepts conditioning inputs (CONDITIONING) that negatively influence the sampling process. These inputs help in avoiding unwanted features or styles in the final output.

sampler

A parameter (SAMPLER) that specifies the sampling method to be used. Different samplers can produce varying results, so choosing the right one is crucial for achieving the desired output.

sigmas

This parameter (SIGMAS) defines the noise levels at different stages of the sampling process. It helps in controlling the amount of noise added at each step.

latent_image

A parameter (LATENT) that provides the initial latent image to be used as a starting point for the sampling process. This latent image serves as the base upon which the models will build the final output.

Sampler Custom XY 🍌| Sampler Custom XY 🍌 Output Parameters:

samples

The output parameter (samples) contains the final generated images after the sampling process. These images are the result of combining the outputs from the different models specified in the model_xy parameter. The samples output provides a cohesive and refined image that integrates the strengths of each model used in the process.

denoised_samples

The output parameter (denoised_samples) contains the denoised versions of the generated images. These images have reduced noise levels, resulting in cleaner and more polished outputs. The denoised_samples output is particularly useful when a high-quality, noise-free image is desired.

Sampler Custom XY 🍌| Sampler Custom XY 🍌 Usage Tips:

• Experiment with different combinations of models in the model_xy parameter to achieve unique and diverse outputs.
• Adjust the cfg parameter to fine-tune the guidance strength and achieve the desired balance between creativity and adherence to the conditioning inputs.
• Use the add_noise parameter to introduce variability in the outputs, which can lead to more interesting and dynamic results.
• Set the noise_seed to a specific value to reproduce the same noise pattern in subsequent runs, ensuring consistency in the generated outputs.

Sampler Custom XY 🍌| Sampler Custom XY 🍌 Common Errors and Solutions:

"Invalid model_xy input"

• Explanation: This error occurs when the model_xy parameter does not receive a valid collection of models.
• Solution: Ensure that the model_xy parameter is populated with a valid collection of XY_MODEL instances.

"Noise seed out of range"

• Explanation: This error occurs when the noise_seed value is outside the acceptable range.
• Solution: Verify that the noise_seed value is within the range of 0 to 0xffffffffffffffff.

"CFG value out of range"

• Explanation: This error occurs when the cfg parameter is set outside the allowed range.
• Solution: Adjust the cfg value to be within the range of 0.0 to 100.0.

"Missing conditioning inputs"

• Explanation: This error occurs when the positive or negative conditioning inputs are not provided.
• Solution: Ensure that both positive and negative conditioning inputs are supplied to guide the sampling process effectively.