Ksampler - ComfyUI 原生节点文档

Ksampler 节点是 ComfyUI 中常用的采样节点。

KSampler 节点用于对潜在图像（latent image）进行多步去噪采样。它结合正向和负向条件（prompt），通过指定的采样算法和调度器，生成高质量的潜在图像。常用于文生图、图生图等 AI 图像生成流程中。

​

参数说明

​

输入参数

参数名	类型	是否必填	默认值	说明
model	MODEL	是	无	用于去噪的模型（如 Stable Diffusion 模型）
seed	INT	是	0	随机种子，保证生成结果可复现
steps	INT	是	20	去噪步数，步数越多图像越精细，速度越慢
cfg	FLOAT	是	8.0	Classifier-Free Guidance 系数，数值越高越贴合提示词，过高会影响质量
sampler_name	枚举	是	无	采样算法名称，影响生成速度、风格和质量
scheduler	枚举	是	无	调度器，控制噪声去除的过程
positive	CONDITIONING	是	无	正向条件，描述希望图像包含的内容
negative	CONDITIONING	是	无	负向条件，描述希望图像排除的内容
latent_image	LATENT	是	无	待去噪的潜在图像，通常为噪声或上一步输出
denoise	FLOAT	是	1.0	去噪强度，1.0为完全去噪，数值越低越保留原始结构，适合图生图

​

输出参数

输出名	类型	说明
samples	LATENT	去噪后的潜在图像，可用于后续解码为最终图像

​

使用示例

Stable diffusion 1.5 文生图工作流示例

Stable diffusion 1.5 文生图工作流示例

Stable diffusion 1.5 图生图工作流示例

Stable diffusion 1.5 图生图工作流示例

​

源码

[更新于2025年5月15日]

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)