T2IAdapter Custom Weights 🛂🅐🅒🅝

Documentation

Class name: CustomT2IAdapterWeights
Category: Adv-ControlNet 🛂🅐🅒🅝/weights/T2IAdapter
Output node: False

This node is designed to load and configure weights for a custom Text-to-Image (T2I) Adapter within the Advanced ControlNet framework. It allows for the dynamic adjustment of weight parameters to fine-tune the control over the image generation process, incorporating options to flip weights for varied effects.

Input types

Required

weight_i
- unknown
- Comfy dtype: FLOAT
- Python dtype: unknown
flip_weights
- A boolean parameter that, when enabled, reverses the order of weights, potentially altering the image generation outcome for creative variations.
- Comfy dtype: BOOLEAN
- Python dtype: bool

Output types

CN_WEIGHTS
- Comfy dtype: CONTROL_NET_WEIGHTS
- Outputs the configured weights as a set, ready for application within the T2I Adapter for controlling image generation.
- Python dtype: list[float]
TK_SHORTCUT
- Comfy dtype: TIMESTEP_KEYFRAME
- Generates a keyframe group based on the configured weights, facilitating precise control over the image generation timeline.
- Python dtype: TimestepKeyframeGroup

Usage tips

Infra type: CPU
Common nodes: unknown

Source code

class CustomT2IAdapterWeights:
    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "weight_00": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.001}, ),
                "weight_01": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.001}, ),
                "weight_02": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.001}, ),
                "weight_03": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.001}, ),
                "flip_weights": ("BOOLEAN", {"default": False}),
            },
        }
    
    RETURN_TYPES = ("CONTROL_NET_WEIGHTS", "TIMESTEP_KEYFRAME",)
    RETURN_NAMES = WEIGHTS_RETURN_NAMES
    FUNCTION = "load_weights"

    CATEGORY = "Adv-ControlNet 🛂🅐🅒🅝/weights/T2IAdapter"

    def load_weights(self, weight_00, weight_01, weight_02, weight_03, flip_weights):
        weights = [weight_00, weight_01, weight_02, weight_03]
        weights = get_properly_arranged_t2i_weights(weights)
        weights = ControlWeights.t2iadapter(weights, flip_weights=flip_weights)
        return (weights, TimestepKeyframeGroup.default(TimestepKeyframe(control_weights=weights)))

2.6 KiB Raw Permalink Blame History