KSampler & KSampler (Advanced)
The heart of every ComfyUI graph: iteratively denoises a latent tensor using your chosen solver, scheduler curve, and classifier-free guidance scale. Package: Built-in Core.
Updated Oct 17, 2026 · 1 min read
- Node / Pack
- KSampler & KSampler (Advanced)
- Category
- sampling
- Inputs
- model, positive, negative, latent_image, seed, steps, cfg, sampler_name, scheduler, denoise
- Outputs
- LATENT
- Source Pack
- Built-in Core
What KSampler & KSampler (Advanced) does in a ComfyUI graph
The heart of every ComfyUI graph: iteratively denoises a latent tensor using your chosen solver, scheduler curve, and classifier-free guidance scale.
On the canvas, this node accepts `model, positive, negative, latent_image, seed, steps, cfg, sampler_name, scheduler, denoise` and emits `LATENT`. Every pin is color-coded by data type so you cannot accidentally wire a pixel `IMAGE` tensor into a `LATENT` pin without an intermediate encode step.
Installation and missing-node recovery on Windows
KSampler & KSampler (Advanced) ships inside the default ComfyUI core on Windows. Double-click anywhere on the empty Studio canvas and type its name to drop it into your graph.
Download the full Windows desktop or portable package at /download to get started with a clean Python 3.12 environment.
FAQs
How do I fix "KSampler & KSampler (Advanced)" showing up as a red box in ComfyUI?
Update your ComfyUI installation to the latest build from /download so all recent core nodes are registered.
What are the main inputs and outputs of KSampler & KSampler (Advanced)?
Inputs: model, positive, negative, latent_image, seed, steps, cfg, sampler_name, scheduler, denoise. Outputs: LATENT.
Run on your hardware. Free forever.
The full ComfyUI engine: open source, fast, extensible, and yours to run however you want. Download the desktop app and open this workflow on your own machine.
