.ai

les meilleurs modèles d'IA open source

Rechercher

Nœud WAS Node Suite dans ComfyUI

WAS Node Suite is a 200-node toolbox for text (concatenate, find/replace, random prompt), images (blend, filters, resize, crop, save as JPEG/WebP), masks, numbers and file handling, filling gaps the core node set leaves open.

Pack de nœuds : was-node-suite-comfyui

Catégorie : Packs de nœuds personnalisés populaires

Cette page n'est pas encore traduite ; elle est affichée en anglais.

Ce que fait WAS Node Suite

WAS (WASasquatch) Node Suite is one of the oldest and largest packs. Popular nodes include Text Concatenate and Text Multiline for prompt building, Text Find and Replace, Random Prompt / Prompt Styles, Image Save (JPEG, WebP, quality settings, custom paths), Image Blend / Image Blend by Mask, Image Resize and Image Crop, Image Filter Adjustments (brightness, contrast, sharpness), Image Load Batch for folders, Number and Math nodes, Constant Number, Logic Boolean, and Mask Crop Region / Mask Dilate / Mask Gaussian Region for mask work.

Because the suite is so large, it brings heavy dependencies (OpenCV, scikit-image, some optional NLP packages for the text nodes) and occasionally conflicts with other packs. Many workflows depend on only one or two of its nodes, so it is often installed just for Image Save or Text Concatenate.

Entrées

Nom	Type	Rôle
(varies)	-	Each node has its own inputs; the most used are IMAGE, MASK and STRING.

Sorties

Nom	Type	Rôle
(varies)	-	IMAGE, MASK, STRING, NUMBER depending on the node.

Oubliez l'installation : des workflows ComfyUI préinstallés sur le cloud

BitVector exécute des workflows ComfyUI prêts à l'emploi sur ses propres GPU. Rien à installer, aucun nœud manquant, aucune case rouge. Ouvrez-le sur votre téléphone ou votre portable et générez en une minute.

Essayer BitVector

Comment utiliser WAS Node Suite

Install was-node-suite-comfyui from Manager and restart (first import downloads nothing by default).
Use Text Multiline -> Text Concatenate -> CLIP Text Encode (with text input converted to an input) to build prompts from pieces.
Use Image Save with extension webp and quality 90 to export smaller files.
Use Image Load Batch to process a folder of pictures one per queue.
Use Mask Gaussian Region to blur masks before compositing.

Réglages et conseils

Convert the text widget of CLIP Text Encode to an input (right-click > convert widget to input) to feed WAS text nodes.
Image Save has embed_workflow for PNG; JPEG and WebP drop the metadata.
Disable the BLIP/CLIPSeg nodes in was_suite_config.json if their dependencies cause import errors.
Check the node search with the prefix "WAS" to see everything the suite adds.

Dépannage de WAS Node Suite

IMPORT FAILED: No module named cv2 / skimage / numba

Pourquoi cela arrive

Dependencies did not install into the ComfyUI Python environment.

Comment le corriger

Manager > Try Fix on WAS Node Suite, or pip install -r requirements.txt with the ComfyUI Python (python_embeded on portable).

Startup takes a long time after installing WAS

Pourquoi cela arrive

The suite checks and downloads optional models for BLIP and CLIPSeg on first run when enabled.

Comment le corriger

Leave it to finish once, or disable those nodes in was_suite_config.json.

Image Save writes nowhere I can find

Pourquoi cela arrive

output_path is relative to the ComfyUI output folder, or an absolute path was set.

Comment le corriger

Set output_path to [time(%Y-%m-%d)] or a plain folder name; check the console for the written path.

Lancez ce workflow depuis votre téléphone

Chaque workflow de cette page est préinstallé sur BitVector, modèles et nœuds personnalisés déjà en place. Choisissez-en un, tapez un prompt, c'est fait. Zéro configuration, rien à télécharger.

Essayer BitVector

Questions sur WAS Node Suite

Do I need WAS if I have Impact and rgthree?

Not necessarily. Many of its functions exist in core now (Image Blend, Image Crop, text concatenation via core String nodes). Install it when a workflow asks for it.

Is it maintained?

Updates are infrequent but it generally still imports on current ComfyUI; check Manager for the latest commit.

Nœuds liés

Save Image

ComfyUI core

Save Image writes the IMAGE tensor to ComfyUI/output as a PNG, with the whole workflow embedded in the file metadata so the picture can be dragged back into ComfyUI to restore the graph.

Load Image

ComfyUI core

Load Image reads a picture from the ComfyUI input folder (or an upload) and outputs an IMAGE tensor plus a MASK taken from the alpha channel, the starting point for img2img, inpainting, ControlNet and IP-Adapter graphs.

CLIP Text Encode (Prompt)

ComfyUI core

CLIP Text Encode turns a text prompt into CONDITIONING using the model text encoder. One node holds the positive prompt, a second one the negative prompt.

Grow Mask, Feather Mask and Invert Mask

ComfyUI core

The core mask tools expand (Grow Mask), soften (Feather Mask) and flip (Invert Mask) a MASK so inpainted regions blend into the surrounding picture without visible seams.

ComfyUI Manager

ComfyUI-Manager

ComfyUI Manager is the extension that installs, updates and fixes custom node packs and models from inside the interface, resolves missing nodes in imported workflows and snapshots your setup.

Marre de réparer des nœuds ? Laissez faire le cloud

BitVector garde des centaines de workflows ComfyUI installés, à jour et testés sur des GPU cloud rapides. Pas de Python, pas d'erreurs CUDA, pas de limite de VRAM. Depuis n'importe quel navigateur.

Essayer BitVector