ComfyUI Node: Upscale Model Switch

Upscale Model Switch:

The Upscale Model Switch node is designed to enhance the resolution of images by utilizing advanced upscaling models. This node allows you to switch between different upscaling models and apply various processing techniques to achieve high-quality image enlargements. It is particularly useful for AI artists who need to upscale images without losing detail or introducing artifacts. The node supports multiple configurations, including the use of secondary models, sharpening filters, and strength scaling, providing a versatile tool for image enhancement tasks.

Upscale Model Switch Input Parameters:

secondary_model

This parameter allows you to specify a secondary model to be used during the upscaling process. The secondary model can be used to refine the results further, providing an additional layer of enhancement. The input type is MODEL.

secondary_start_cycle

This integer parameter defines the cycle at which the secondary model should start being applied. It ranges from 2 to 16, with a default value of 2. This setting helps in controlling when the secondary model's influence begins during the upscaling process.

upscale_model

This parameter specifies the primary upscaling model to be used. The input type is UPSCALE_MODEL. This model is responsible for the main upscaling operation, determining the overall quality and characteristics of the upscaled image.

processor_model

This parameter allows you to specify an additional processing model to be used in conjunction with the primary upscaling model. The input type is UPSCALE_MODEL. This model can apply further enhancements or adjustments to the image.

pos_additive

This parameter accepts conditioning data to be added positively during the upscaling process. The input type is CONDITIONING. It helps in fine-tuning the upscaling results by adding specific conditioning information.

neg_additive

This parameter accepts conditioning data to be added negatively during the upscaling process. The input type is CONDITIONING. It helps in fine-tuning the upscaling results by subtracting specific conditioning information.

pos_add_mode

This parameter allows you to choose the mode for positive additive conditioning. The options are increment and decrement. This setting controls how the positive conditioning data is applied during the upscaling process.

pos_add_strength

This float parameter defines the strength of the positive additive conditioning. It ranges from 0.01 to 1.0, with a default value of 0.25. This setting determines the intensity of the positive conditioning effect.

pos_add_strength_scaling

This parameter enables or disables the scaling of positive additive strength. The options are enable and disable. When enabled, the strength of the positive conditioning is scaled based on the upscaling process.

pos_add_strength_cutoff

This float parameter sets the cutoff value for positive additive strength. It ranges from 0.01 to 10.0, with a default value of 2.0. This setting defines the maximum strength that the positive conditioning can reach.

neg_add_mode

This parameter allows you to choose the mode for negative additive conditioning. The options are increment and decrement. This setting controls how the negative conditioning data is applied during the upscaling process.

neg_add_strength

This float parameter defines the strength of the negative additive conditioning. It ranges from 0.01 to 1.0, with a default value of 0.25. This setting determines the intensity of the negative conditioning effect.

neg_add_strength_scaling

This parameter enables or disables the scaling of negative additive strength. The options are enable and disable. When enabled, the strength of the negative conditioning is scaled based on the upscaling process.

neg_add_strength_cutoff

This float parameter sets the cutoff value for negative additive strength. It ranges from 0.01 to 10.0, with a default value of 2.0. This setting defines the maximum strength that the negative conditioning can reach.

sharpen_strength

This float parameter defines the strength of the sharpening filter applied to the upscaled image. It ranges from 0.0 to 10.0, with a default value of 0.0. This setting helps in enhancing the details of the upscaled image by applying a sharpening effect.

sharpen_radius

This integer parameter sets the radius of the sharpening filter. It ranges from 1 to 12, with a default value of 2. This setting determines the area around each pixel that is considered when applying the sharpening effect.

steps_scaling

This parameter enables or disables the scaling of steps during the upscaling process. The options are enable and disable. When enabled, the number of steps is scaled based on the upscaling process.

steps_control

This parameter allows you to choose the control mode for steps scaling. The options are decrement and increment. This setting controls how the number of steps is adjusted during the upscaling process.

Upscale Model Switch Output Parameters:

tensor_images

This output parameter provides the upscaled images as tensors. The upscaled images are processed and enhanced based on the specified models and parameters, resulting in high-quality, detailed images suitable for further use or display.

Upscale Model Switch Usage Tips:

• To achieve the best results, experiment with different combinations of primary and secondary models. This can help you find the optimal settings for your specific image enhancement needs.
• Adjust the sharpening strength and radius to enhance the details of the upscaled image without introducing artifacts. Start with lower values and gradually increase them to find the right balance.

Upscale Model Switch Common Errors and Solutions:

Out of Memory (OOM) Exception

• Explanation: This error occurs when the system runs out of memory during the upscaling process, especially with large images or high upscaling factors.
• Solution: Reduce the tile size or the upscaling factor to lower the memory requirements. Alternatively, try using a system with more available memory.

Invalid Model Error

• Explanation: This error occurs when an invalid or incompatible model is specified for the upscaling process.
• Solution: Ensure that the models specified for upscale_model and processor_model are compatible and correctly loaded. Verify the model paths and formats.

Parameter Out of Range

• Explanation: This error occurs when a parameter value is set outside its allowed range.
• Solution: Check the parameter values and ensure they are within the specified ranges. Adjust the values to fall within the acceptable limits.

Image Size Mismatch

• Explanation: This error occurs when the dimensions of the input image do not match the expected size for the upscaling process.
• Solution: Ensure that the input image dimensions are compatible with the upscaling model. Resize the image to the required dimensions before processing.