Add LCM Sampling Methods to Sampling Method list, maybe this will be useful

[Reizer88]

WARNING : Always backup your file before you make change

You need two step to make small edits using a text editor. Follow these steps:

1. First Step,
   Edit the file with the name "sampling.py" you can found at : "[Your Installation folder]\stable-diffusion-webui-directml\repositories\k-diffusion\k_diffusion\sampling.py"

Copy and paste the code below at the end of the line and save :

@torch.no_grad()
def sample_lcm(model, x, sigmas, extra_args=None, callback=None, disable=None, noise_sampler=None):
    extra_args = {} if extra_args is None else extra_args
    noise_sampler = default_noise_sampler(x) if noise_sampler is None else noise_sampler
    s_in = x.new_ones([x.shape[0]])
    for i in trange(len(sigmas) - 1, disable=disable):
        denoised = model(x, sigmas[i] * s_in, **extra_args)
        if callback is not None:
            callback({'x': x, 'i': i, 'sigma': sigmas[i], 'sigma_hat': sigmas[i], 'denoised': denoised})

        x = denoised
        if sigmas[i + 1] > 0:
            x += sigmas[i + 1] * noise_sampler(sigmas[i], sigmas[i + 1])
    return x

3. The second step is edit the file with the name "sd_samplers_kdiffusion.py" found here: "[Your Installation folder]\stable-diffusion-webui-directml\modules\sd_samplers_kdiffusion.py"
   On line 39 add code below to (before the "]") and save the file:

('LCM Sampler', 'sample_lcm', ['lcm'], {}),

Fist Step Images :

Second Step Images :

Result Images :

Images generated with LCM :

Sampling Method : LCM Sampler
Sampling Steps : 6
CFG Scale : 1.5
W/H : 512x712, 512x512, 600x800
Model : Realistic_LCM_BY_Stable_Yogi
IMG2IMG Upscaler : SD Upscale 4X R-ESRGAN4+

My System :
Windows 10
XFX Radeon RX 6600 8GB
RAM 32GB

@lshqqytiger Can you check the code, optimized the code and make available for the next update? Thank you