Skip to content
Node packVerifiedExternal
Open source

ControlAltAI-Nodes

Quality of Life ComfyUI nodes from ControlAltAI.

Maintainer@gsethBgrade

Package profile

Status
Verified
Publisher
@gseth
Source
GitHub
Stars
211

README

ComfyUI ControlAltAI Nodes

This repository contains custom nodes designed for the ComfyUI framework, focusing on quality-of-life improvements. These nodes aim to make tasks easier and more efficient. Two Flux nodes are available to enhance functionality and streamline workflows within ComfyUI.

Nodes

List of Nodes:

  • Flux
    • Flux Resolution Calculator (Updated, May 2025)
    • Flux Sampler
    • Flux Union ControlNet Apply
  • Logic
    • Boolean Basic
    • Boolean Reverse
    • Integer Settings
    • Integer Settings Advanced (New, June 2025)
    • Switch Two Way (New, June 2025)
    • Switch Three Way (New, June 2025)
    • Choose Upscale Model
  • Image
    • Get Image Size & Ratio
    • Perturbation Texture (New, June 2025)
    • Noise Plus Blend
  • Flux Region
    • Region Mask Generator
    • Region Mask Processor
    • Region Mask Validator
    • Region Mask Conditioning
    • Flux Attention Control
    • Region Overlay Visualizer
    • Flux Attention Cleanup
  • HiDream
    • HiDream Resolution (New, June 2025)
  • Utility
    • Text Bridge (New, June 2025)

Flux Resolution Calculator

The Flux Resolution Calculator is designed to determine the optimal image resolution for outputs generated using the Flux model, which is notably more oriented towards megapixels. Unlike traditional methods that rely on standard SDXL resolutions, this calculator operates based on user-specified megapixel inputs. Users can select their desired megapixel count, ranging from 0.1 to 2.0 megapixels, and aspect ratio. The calculator then provides the exact image dimensions necessary for optimal performance with the Flux model. This approach ensures that the generated images meet specific quality and size requirements tailored to the user's needs. Additionally, while the official limit is 2.0 megapixels, during testing, I have successfully generated images at higher resolutions, indicating the model's flexibility in accommodating various image dimensions without compromising quality.

  • Supported Megapixels: 0.1 MP - 2.5 MP (change stepping to 0.1 for fine-tuned selection)
  • Note: Generations above 1 MP may appear slightly blurry, but resolutions of 3k+ have been successfully tested on the Flux1.Dev model.
  • Custom Ratio: Custom Ratio is now supported. Enable or disable the Custom Ratio and input any ratio. (Example: 4:9).
  • Preview: The preview node is just a visual representation of the ratio.
  • Divisible By: You can now choose the divisibility by 8/16/32/64. By default, it is 64. To get fine-tuned results, choose divisibility by 8. Divisibility by 32/64 is recommended for Flux Dev 1.

Flux Sampler

The Flux Sampler node combines the functionality of the CustomSamplerAdvance node and input nodes into a single, streamlined node.

  • CFG Setting: The CFG is fixed at 1.
  • Conditioning Input: Only positive conditioning is supported.
  • Compatibility: Only the samplers and schedulers compatible with the Flux model are included.
  • Latent Compatibility: Use SD3 Empty Latent Image only. The normal empty latent image node is not compatible.

ComfyUI Screenshot ComfyUI Screenshot ComfyUI Screenshot

Flux Union ControlNet Apply

The Flux Union ControlNet Apply node is an all-in-one node compatible with InstanX Union Pro ControlNet. It has been tested extensively with the union controlnet type and works as intended. You can combine two ControlNet Union units and get good results. Not recommended to combine more than two. The ControlNet is tested only on the Flux 1.Dev Model.

ComfyUI Screenshot

Recommended Settings: strength: 0.15-0.65. end percentage: 0.200 - 0.900.

Recommended PreProcessors: Canny: Canny Edge (ControlNet Aux). Tile: Tile (ControlNet Aux). Depth: Depth Anything V2 Relative (ControlNet Aux). Blue: Direct Input (Blurry Image) or

Nodes in this pack

23 nodes
  • BooleanBasic
  • BooleanReverse
  • ChooseUpscaleModel
  • FluxAttentionCleanup
  • FluxAttentionControl
  • FluxControlNetApply
  • FluxResolutionNode
  • FluxSampler
  • FluxUnionControlNetApply
  • GetImageSizeRatio
  • HiDreamResolutionNode
  • IntegerSettings
  • IntegerSettingsAdvanced
  • NoisePlusBlend
  • PerturbationTexture
  • RegionMaskConditioning
  • RegionMaskGenerator
  • RegionMaskProcessor
  • RegionMaskValidator
  • RegionOverlayVisualizer
  • TextBridge
  • ThreeWaySwitch
  • TwoWaySwitch

Related resources

30 connections
Used byLTX2.3 | Z-Image + Ollama T2I to I2V | 12GB Friendly — v1.0Used byChroma-ZIT-Upscaler-Detailer — v1.0Used byFLUX XY — v1.0Used byLonecat's Illustrious/Pony/SDXL WIldcard Workflow — v2.0 Professional GradeUsed byFlux 2 Klein Workflow - t2i / i2i — v1.0Used byZ-Image Turbo Text-to-Image powered by Ollama 🦙 — Z-Image Turbo WorkflowUsed byNunchaku Render & Edit — v7.4Used byJibMixWan T2I effective workflow — v1.2Used byHunyuan 3D Flux Character Sheet To 3D — v1.0Used byMy Simple NSFW WAN2.2 I2V Workflow + Upscale + Upframe — v1.0Used byCombined workflow (ComfyUI txt2img, Wildcards, LLMs/Ollama, Pony, SDXL, Illustrious, Flux, Qwen, Z-Image, Anima, Flux 2 Klein, Krea 2 Turbo) — v2Used byZ-Image-Turbo Simple Variance Workflow — v1.0Used byZimage TURBO llm upscale_2_pass seedVR2 workflow — v1.0Used byEasy Character Creator — v3.0 (Randomizer)Used byZ-Image Base & Turbo Pro Grade Workflow I2I/T2I (Low or High VRAM) — v1.0Used byCyberRealistic Z-Image Turbo - ComfyUI Workflow — v5.0Used byCyberRealistic Z-Image Turbo - ComfyUI Workflow — v2.5Used byCombined workflow (ComfyUI txt2img, Wildcards, LLMs/Ollama, Pony, SDXL, Illustrious, Flux, Qwen, Z-Image, Anima, Flux 2 Klein, Krea 2 Turbo) — 20251214Used byIllustrious Workflow — v1.0Used byAnima Prompt Structure and Wildcard Workflow — v2.0 (compact)Used byFlux.2 Klein Mix Workflow. Consistency, Enhanced, Image Size control, I2I, T2I, In & outpaint, ControlNets. — v3.0Used byCyberRealistic Z-Image Turbo - ComfyUI Workflow — v4.0Used byEasy Character Creator — v2.0Used byMPI Random Prompt Gen — v3.1Used by(Video Tutorial Resources) Real Flux Skin Textures, PulID V2, Redux and Depth Blur FX — v1.0Used byZ-Image Turbo | Detailer(s) | Dual Sampling | Upscaling — BasicUsed byBerts Eyebrow's Workflow (Z-image) — v1.0Used byEasy Character Creator — v1.0Used byCyberRealistic Z-Image Turbo - ComfyUI Workflow — v1.0Used byCombined workflow (ComfyUI txt2img, Wildcards, LLMs/Ollama, Pony, SDXL, Illustrious, Flux, Qwen, Z-Image, Anima, Flux 2 Klein, Krea 2 Turbo) — v1

Sources

3 sources
GitHubSource
github.com/gseth/ControlAltAI-Nodes

Verified Oct 16

GitHubSourceVersion 721492b66c9cede8ae23ae10615462ad80cfd061
github.com/gseth/ControlAltAI-Nodes

Verified Oct 20

Source excerpts

1 excerpt

Source context: Repo gseth/ControlAltAI-Nodes