Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

Add DDPM sampler.

comfyanonymous415abb275f8e
diff --git a/comfy/k_diffusion/sampling.py b/comfy/k_diffusion/sampling.py
index eb088d92b..937c5a388 100644
--- a/comfy/k_diffusion/sampling.py
+++ b/comfy/k_diffusion/sampling.py
@@ -706,3 +706,34 @@ def sample_dpmpp_sde_gpu(model, x, sigmas, extra_args=None, callback=None, disab
noise_sampler = BrownianTreeNoiseSampler(x, sigma_min, sigma_max, seed=extra_args.get("seed", None), cpu=False) if noise_sampler is None else noise_sampler
return sample_dpmpp_sde(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, eta=eta, s_noise=s_noise, noise_sampler=noise_sampler, r=r)
+
+def DDPMSampler_step(x, sigma, sigma_prev, noise, noise_sampler):
+ alpha_cumprod = 1 / ((sigma * sigma) + 1)
+ alpha_cumprod_prev = 1 / ((sigma_prev * sigma_prev) + 1)
+ alpha = (alpha_cumprod / alpha_cumprod_prev)
+
+ mu = (1.0 / alpha).sqrt() * (x - (1 - alpha) * noise / (1 - alpha_cumprod).sqrt())
+ if sigma_prev > 0:
+ mu += ((1 - alpha) * (1. - alpha_cumprod_prev) / (1. - alpha_cumprod)).sqrt() * noise_sampler(sigma, sigma_prev)
+ return mu
+
+
+def generic_step_sampler(model, x, sigmas, extra_args=None, callback=None, disable=None, noise_sampler=None, step_function=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 = step_function(x / torch.sqrt(1.0 + sigmas[i] ** 2.0), sigmas[i], sigmas[i + 1], (x - denoised) / sigmas[i], noise_sampler)
+ if sigmas[i + 1] != 0:
+ x *= torch.sqrt(1.0 + sigmas[i + 1] ** 2.0)
+ return x
+
+
+def sample_ddpm(model, x, sigmas, extra_args=None, callback=None, disable=None, noise_sampler=None):
+ return generic_step_sampler(model, x, sigmas, extra_args, callback, disable, noise_sampler, DDPMSampler_step)
+
diff --git a/comfy/samplers.py b/comfy/samplers.py
index c60288fd1..7f1987167 100644
--- a/comfy/samplers.py
+++ b/comfy/samplers.py
@@ -546,7 +546,7 @@ class KSampler:
SCHEDULERS = ["normal", "karras", "exponential", "sgm_uniform", "simple", "ddim_uniform"]
SAMPLERS = ["euler", "euler_ancestral", "heun", "dpm_2", "dpm_2_ancestral",
"lms", "dpm_fast", "dpm_adaptive", "dpmpp_2s_ancestral", "dpmpp_sde", "dpmpp_sde_gpu",
- "dpmpp_2m", "dpmpp_2m_sde", "dpmpp_2m_sde_gpu", "dpmpp_3m_sde", "dpmpp_3m_sde_gpu", "ddim", "uni_pc", "uni_pc_bh2"]
+ "dpmpp_2m", "dpmpp_2m_sde", "dpmpp_2m_sde_gpu", "dpmpp_3m_sde", "dpmpp_3m_sde_gpu", "ddpm", "ddim", "uni_pc", "uni_pc_bh2"]
def __init__(self, model, steps, device, sampler=None, scheduler=None, denoise=None, model_options={}):
self.model = model