Skip to content
Node packVerifiedExternal
Open source

ComfyUI-Impact-Subpack

This extension serves as a complement to the Impact Pack, offering features that are not deemed suitable for inclusion by default in the ComfyUI Impact Pack

Maintainer@ltdrdataBgrade

Package profile

Status
Verified
Publisher
@ltdrdata
Source
GitHub
Stars
385

README

ComfyUI-Impact-Subpack

This node pack provides nodes that complement the ComfyUI Impact Pack, such as the UltralyticsDetectorProvider.

Nodes

  • UltralyticsDetectorProvider - Loads the Ultralystics model to provide SEGM_DETECTOR, BBOX_DETECTOR.
  • Unlike MMDetDetectorProvider, for segm models, BBOX_DETECTOR is also provided.
  • The various models available in UltralyticsDetectorProvider can be downloaded through ComfyUI-Manager.

Ultralytics models

  • When using ultralytics models, save them separately in models/ultralytics/bbox and models/ultralytics/segm depending on the type of model. Many models can be downloaded by searching for ultralytics in the Model Manager of ComfyUI-Manager.
  • huggingface.co/Bingsu/adetailer - You can download face, people detection models, and clothing detection models.
  • ultralytics/assets - You can download various types of detection models other than faces or people.
  • civitai/adetailer - You can download various types detection models....Many models are associated with NSFW content.

Paths

  • In extra_model_paths.yaml, you can add the following entries:
  • ultralytics_bbox - Specifies the paths for bbox YOLO models.
  • ultralytics_segm - Specifies the paths for segm YOLO models.
  • ultralytics - Allows the presence of bbox/ and segm/ subdirectories.

Model loading configuration related to weights_only

  • Loading model files can involve executing code, so if malicious code is embedded in a model, it can pose a security risk. For this reason, PyTorch 2.6 and later have introduced features for safer model loading. The issue is that older model files, which were created without such safe loading (weights_only) restrictions, may occasionally fail to load properly.
  • By listing the paths of models deemed safe in <user_directory>/default/ComfyUI-Impact-Subpack/model-whitelist.txt, those specific models will have weights_only disabled, allowing them to be loaded without restriction.
    • <user_directory>: typically located at ComfyUI/user.

How To Install?

Install via ComfyUI-Manager (Recommended)

  • Search ComfyUI Impact Subpack in ComfyUI-Manager and click Install button.

Manual Install (Not Recommended)

  1. cd custom_nodes
  2. git clone https://github.com/ltdrdata/ComfyUI-Impact-Subpack
  3. cd ComfyUI-Impact-Subpack
  4. pip install -r requirements.txt
    • IMPORTANT:
      • You must install it within the Python environment where ComfyUI is running.
      • For the portable version, use <installed path>\python_embeded\python.exe -m pip instead of pip. For a venv, activate the venv first and then use pip.
  5. Restart ComfyUI

Credits

ComfyUI/ComfyUI - A powerful and modular stable diffusion GUI.

Bing-su/adetailer - This repository provides an object detection model and features based on Ultralystics.

huggingface/Bingsu/adetailer - This repository offers various models based on Ultralystics.

  • You can download other models supported by the UltralyticsDetectorProvider from here.

Nodes in this pack

1 node
  • UltralyticsDetectorProvider

Related resources

40 connections
Used byL_wf — v2.5Used byAnima adetailer face workflow — v1.0Used byWan Vace 2.1 Flow Archive — simpleUsed byLTX2.3 | Z-Image + Ollama T2I to I2V | 12GB Friendly — v1.0Used byANIMA Pro Grade SFW/NSFW W/ Controlnet, Regional Prompt, & Realism enhancer — V4.0 Enhancer versionUsed byWhite 5 Ultra Depth Control Text Generation Image — v1.0Used bySimple Text2Image Workflow for Beginners — v1.1Used byGladas' Workflow for Krea 2 Turbo — v1 — v8Used byGladas' Workflow for Anima — v2 — v3Used byMoody Simple Flux 2 Klein 9B Edit Workflow — v2.0Used byKrea2千问完美洗图流+SD高清工作流合集(Krea2 + QWEN Comprehensive Perfect Image Refining Workflow + SD High-Definition Workflow Compilation) — v2.0Used byIllustrious/ Pony/ SDXL Pro Grade Workflow (Low or High VRAM) — V8.1 Region Prompt UltraUsed byCharacters generator | Generation of detailed сharacter for full body — v1.2Used byDual-Checkpoint TIPO-Enhanced SDXL Image Generation — v1.0Used byKrea 2 Pro Grade w/ Image Edit, Style Transfer, Controlnet, Multi-reference, SAM3 Detailers, & Low VRAM options — v1.1 added rebalanceUsed byMoody Anime to Real Workflow — v1.0 ZITUsed byComfyUI Multi-Subject Workflows — Latent Couple Pose v1.1Used byFlux2 Klein 9b/4b simple workflow (TXT2IMG, IMG2IMG, Edit, Inpaint, Outpaint, metadata export for Civitai, SeedVR2) — v1.9Used byZ-Image Base & Turbo Pro Grade Workflow I2I/T2I (Low or High VRAM) — V8.0 upgrades + Qwen advUsed byZ-image turbo TXT2IMG, IMG2IMG, inpaint, outpaint, onlymasked inpaint, controlnet, lora manager, caption, adetailer, SeedVR2. — v1.3Used byt2i-ill (Hires. Fix + Face Detailer) with spectrum nodes workflows — v1.0Used byAll-in-One. Z-Image, Ernie, Klein, t2i, i2i, controlNet, inpaint, outpaint, LLM, WAN, Qwen image, SDXL, Chroma — v7.3Used byLonecat's Illustrious/Pony/SDXL WIldcard Workflow — v2.0 Professional GradeUsed byCharacters generator | Generation of detailed сharacter for full body — v1.1Used byUltra photo-realistic workflow | refiner, upscaling, FaceDetailer (+index elements), inpainting, controlnet, Civitai Metadata (NOOBAI-XL/ILLUSTRIOUS/SDXL) ComfyUi — v5.5Used byEazy Illustrious - Workflow for ComfyUI — v0.2Used byZ-Image Base & Turbo Pro Grade Workflow I2I/T2I (Low or High VRAM) — V2.0Used byFisherKing-ZiT-[EyeDetailer]-I2I-ReferenceWorkflow-v1.0 [Low VRAM]Used byMoody ZIB (Zimage Base) + ZIT (Zimage Turbo) Simple Workflow — v6.0 ZIB+ZITUsed byConsistent face 3x3 generator (discontinued) — v1.2Used byIllustrious/ Pony/ SDXL SFW & NSFW Pro Grade Workflow (Low and high VRAM) — V8.1 upgradesUsed byPornMaster [Flux2 Klein 9b kv] t2i Workflow — V1Used byMoody Simple Zimage Turbo/Distilled Workflow — v3.0Used by简单易懂的Illustrious工作流/text2img:Simple Workflow for Illustrious(lora、fix、FaceDetailer) — v2.0Used byGonzaLomo SDXL Workflows — v3.0Used byZ-image turbo TXT2IMG, IMG2IMG, inpaint, outpaint, onlymasked inpaint, controlnet, lora manager, caption, adetailer, SeedVR2. — v2.2Used byComfyUI Image Workflows — V16Used byQwen-Image refiner — v1.0Used byComfyUI Image Workflows — V17Used byComfyUI Image Workflows — V9.0

Sources

3 sources
GitHubSourceVersion 50c7b71a6a224734cc9b21963c6d1926816a97f1
github.com/ltdrdata/ComfyUI-Impact-Subpack

Verified Oct 8

Source excerpts

1 excerpt

Source context: Repo ltdrdata/ComfyUI-Impact-Subpack