Ksampler - ComfyUI Built-in Node Documentation

The Ksampler node is a commonly used sampling node in ComfyUI.

The KSampler node performs multi-step denoising sampling on latent images. It combines positive and negative conditions (prompts) and uses specified sampling algorithms and schedulers to generate high-quality latent images. It is commonly used in AI image generation workflows like text-to-image and image-to-image.

Parameter Description

Input Parameters

Parameter	Type	Required	Default	Description
model	MODEL	Yes	None	Model used for denoising (e.g. Stable Diffusion model)
seed	INT	Yes	0	Random seed to ensure reproducible results
steps	INT	Yes	20	Number of denoising steps - more steps mean finer details but slower generation
cfg	FLOAT	Yes	8.0	Classifier-Free Guidance scale - higher values better match prompts but too high impacts quality
sampler_name	Enum	Yes	None	Name of sampling algorithm, affects generation speed, style and quality
scheduler	Enum	Yes	None	Scheduler that controls the noise removal process
positive	CONDITIONING	Yes	None	Positive conditions describing desired image content
negative	CONDITIONING	Yes	None	Negative conditions describing content to exclude
latent_image	LATENT	Yes	None	Latent image to denoise, usually noise or output from previous step
denoise	FLOAT	Yes	1.0	Denoising strength - 1.0 for full denoising, lower values preserve original structure, suitable for image-to-image

Output Parameters

Output	Type	Description
samples	LATENT	Denoised latent image that can be decoded to final image

Usage Examples

Stable diffusion 1.5 Text-to-Image Workflow Example

Stable diffusion 1.5 Text-to-Image Workflow Example

Stable diffusion 1.5 Image-to-Image Workflow Example

Stable diffusion 1.5 Image-to-Image Workflow Example

Source Code

[Updated on May 15, 2025]

def common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent, denoise=1.0, disable_noise=False, start_step=None, last_step=None, force_full_denoise=False):
    latent_image = latent["samples"]
    latent_image = comfy.sample.fix_empty_latent_channels(model, latent_image)

    if disable_noise:
        noise = torch.zeros(latent_image.size(), dtype=latent_image.dtype, layout=latent_image.layout, device="cpu")
    else:
        batch_inds = latent["batch_index"] if "batch_index" in latent else None
        noise = comfy.sample.prepare_noise(latent_image, seed, batch_inds)

    noise_mask = None
    if "noise_mask" in latent:
        noise_mask = latent["noise_mask"]

    callback = latent_preview.prepare_callback(model, steps)
    disable_pbar = not comfy.utils.PROGRESS_BAR_ENABLED
    samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
                                  denoise=denoise, disable_noise=disable_noise, start_step=start_step, last_step=last_step,
                                  force_full_denoise=force_full_denoise, noise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
    out = latent.copy()
    out["samples"] = samples
    return (out, )


class KSampler:
    @classmethod
    def INPUT_TYPES(s):
        return {
            "required": {
                "model": ("MODEL", {"tooltip": "The model used for denoising the input latent."}),
                "seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffffffffffff, "control_after_generate": True, "tooltip": "The random seed used for creating the noise."}),
                "steps": ("INT", {"default": 20, "min": 1, "max": 10000, "tooltip": "The number of steps used in the denoising process."}),
                "cfg": ("FLOAT", {"default": 8.0, "min": 0.0, "max": 100.0, "step":0.1, "round": 0.01, "tooltip": "The Classifier-Free Guidance scale balances creativity and adherence to the prompt. Higher values result in images more closely matching the prompt however too high values will negatively impact quality."}),
                "sampler_name": (comfy.samplers.KSampler.SAMPLERS, {"tooltip": "The algorithm used when sampling, this can affect the quality, speed, and style of the generated output."}),
                "scheduler": (comfy.samplers.KSampler.SCHEDULERS, {"tooltip": "The scheduler controls how noise is gradually removed to form the image."}),
                "positive": ("CONDITIONING", {"tooltip": "The conditioning describing the attributes you want to include in the image."}),
                "negative": ("CONDITIONING", {"tooltip": "The conditioning describing the attributes you want to exclude from the image."}),
                "latent_image": ("LATENT", {"tooltip": "The latent image to denoise."}),
                "denoise": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.01, "tooltip": "The amount of denoising applied, lower values will maintain the structure of the initial image allowing for image to image sampling."}),
            }
        }

    RETURN_TYPES = ("LATENT",)
    OUTPUT_TOOLTIPS = ("The denoised latent.",)
    FUNCTION = "sample"

    CATEGORY = "sampling"
    DESCRIPTION = "Uses the provided model, positive and negative conditioning to denoise the latent image."

    def sample(self, model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=1.0):
        return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)