efficiency-nodes-ED

Context To BasicPipe

Converts a context into a BASIC_PIPE tuple containing its model, CLIP, VAE, positive conditioning, and negative conditioning.

Context To DetailerPipe

Converts a context and detailer-related inputs into a DETAILER_PIPE tuple containing the context model components, wildcard, detector, and optional segmentation detector, SAM model, and detailer hook.

Detailer (SEGS) 💬ED

It enhances details by inpainting each region within the detected area bundle (SEGS) after enlarging them based on the guide size.

Efficient Loader 💬ED

Loads model, CLIP, and VAE components from configured inputs and handles prompt encoding, with outputs for context, model, conditioning, latent, image, CLIP, and dependencies.

Embedding Stacker 💬ED

Collects enabled positive and negative embeddings with their weights, combines them with an optional LoRA stack, and returns the combined stack.

Ext Model Input 💬ED

Packages a model, CLIP, and optional LoRA stack, reference image, and reference mask into a context.

FaceDetailer 💬ED

This node enhances details by automatically detecting specific objects in the input image using detection models (bbox, segm, sam) and regenerating the image by enlarging the detected area based on the guide size. Although this node is specialized to simplify the commonly used facial detail enhancement workflow, it can also be used for various automatic inpainting purposes depending on the detection model.

Get Booru Tag 💬ED

Returns a text string assembled from optional text inputs after stripping comments and trimming separators; the shown method does not use its URL input.

Int Holder 💬ED

Returns the output integer, replacing it with a truthy optional integer input and sending node feedback for the displayed value.

KSampler (Efficient) 💬ED

Samples a context's model and latent using seed, step, CFG, sampler, and scheduler settings; the implementation also supports mask-detailer and refiner-script paths and declares context, image, and step outputs.

KSampler Text 💬ED

Accepts positive and negative text with sampling settings and a context, encodes both text inputs, calls the Efficient KSampler path, and declares context and image outputs.

Load Image 💬ED

Loads an image and its mask, extracts prompt text from the image, and can optionally upscale or resize the image and mask using the selected sizing and proportion settings.

LoRA Stacker 💬ED

Builds a LoRA stack from enabled selections using simple shared or advanced model and CLIP strengths, and can extend an optional incoming stack.

MaskDetailer 💬ED

Uses an image and mask from context with detailer and sampling settings to invoke Impact Pack's MaskDetailerPipe for masked image refinement; the node declares context and refined-image outputs.

Refiner Script 💬ED

Creates a SCRIPT value containing refiner settings such as noise, seed, sampling parameters, step range, batch handling, optional refiner model components, and an optional LoRA stack.

Regional Processor 💬ED

Applies regional control-net processing to a model and base positive conditioning using a region script, prompt weight, dimensions, and seed, then returns the processed model and conditioning.

Regional Script 💬ED

Description compacte indisponible pour ce nœud.

Regional Stacker 💬ED

Description compacte indisponible pour ce nœud.

Save Image 🔔ED

Description compacte indisponible pour ce nœud.

Simple Text 💬ED

Description compacte indisponible pour ce nœud.

SUPIR Model Loader 💬ED

Description compacte indisponible pour ce nœud.

SUPIR Sampler 💬ED

Description compacte indisponible pour ce nœud.

TIPO Script 💬ED

Description compacte indisponible pour ce nœud.

Ultimate SD Upscale 💬ED

Description compacte indisponible pour ce nœud.

Wildcard Encode 💬ED

Description compacte indisponible pour ce nœud.