[pull] master from comfyanonymous:master

comfy/k_diffusion/sampling.py

@@ -1557,10 +1557,13 @@ def default_er_sde_noise_scaler(x):
 
 
 @torch.no_grad()
-def sample_seeds_2(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None, r=0.5):
+def sample_seeds_2(model, x, sigmas, extra_args=None, callback=None, disable=None, eta=1., s_noise=1., noise_sampler=None, r=0.5, solver_type="phi_1"):
     """SEEDS-2 - Stochastic Explicit Exponential Derivative-free Solvers (VP Data Prediction) stage 2.
     arXiv: https://arxiv.org/abs/2305.14267 (NeurIPS 2023)
     """
+    if solver_type not in {"phi_1", "phi_2"}:
+        raise ValueError("solver_type must be 'phi_1' or 'phi_2'")
+
     extra_args = {} if extra_args is None else extra_args
     seed = extra_args.get("seed", None)
     noise_sampler = default_noise_sampler(x, seed=seed) if noise_sampler is None else noise_sampler
@@ -1600,8 +1603,14 @@ def sample_seeds_2(model, x, sigmas, extra_args=None, callback=None, disable=Non
         denoised_2 = model(x_2, sigma_s_1 * s_in, **extra_args)
 
         # Step 2
-        denoised_d = torch.lerp(denoised, denoised_2, fac)
-        x = sigmas[i + 1] / sigmas[i] * (-h * eta).exp() * x - alpha_t * ei_h_phi_1(-h_eta) * denoised_d
+        if solver_type == "phi_1":
+            denoised_d = torch.lerp(denoised, denoised_2, fac)
+            x = sigmas[i + 1] / sigmas[i] * (-h * eta).exp() * x - alpha_t * ei_h_phi_1(-h_eta) * denoised_d
+        elif solver_type == "phi_2":
+            b2 = ei_h_phi_2(-h_eta) / r
+            b1 = ei_h_phi_1(-h_eta) - b2
+            x = sigmas[i + 1] / sigmas[i] * (-h * eta).exp() * x - alpha_t * (b1 * denoised + b2 * denoised_2)
+
         if inject_noise:
             segment_factor = (r - 1) * h * eta
             sde_noise = sde_noise * segment_factor.exp()

comfy/utils.py

@@ -53,7 +53,7 @@ def scalar(*args, **kwargs):
     ALWAYS_SAFE_LOAD = True
     logging.info("Checkpoint files will always be loaded safely.")
 else:
-    logging.info("Warning, you are using an old pytorch version and some ckpt/pt files might be loaded unsafely. Upgrading to 2.4 or above is recommended.")
+    logging.warning("Warning, you are using an old pytorch version and some ckpt/pt files might be loaded unsafely. Upgrading to 2.4 or above is recommended as older versions of pytorch are no longer supported.")
 
 def load_torch_file(ckpt, safe_load=False, device=None, return_metadata=False):
     if device is None:

comfy_extras/nodes_custom_sampler.py

@@ -659,6 +659,31 @@ def execute(cls, model, eta, sde_start_percent, sde_end_percent, s_noise, predic
     get_sampler = execute
 
 
+class SamplerSEEDS2(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return io.Schema(
+            node_id="SamplerSEEDS2",
+            category="sampling/custom_sampling/samplers",
+            inputs=[
+                io.Combo.Input("solver_type", options=["phi_1", "phi_2"]),
+                io.Float.Input("eta", default=1.0, min=0.0, max=100.0, step=0.01, round=False, tooltip="Stochastic strength"),
+                io.Float.Input("s_noise", default=1.0, min=0.0, max=100.0, step=0.01, round=False, tooltip="SDE noise multiplier"),
+                io.Float.Input("r", default=0.5, min=0.01, max=1.0, step=0.01, round=False, tooltip="Relative step size for the intermediate stage (c2 node)"),
+            ],
+            outputs=[io.Sampler.Output()]
+        )
+
+    @classmethod
+    def execute(cls, solver_type, eta, s_noise, r) -> io.NodeOutput:
+        sampler_name = "seeds_2"
+        sampler = comfy.samplers.ksampler(
+            sampler_name,
+            {"eta": eta, "s_noise": s_noise, "r": r, "solver_type": solver_type},
+        )
+        return io.NodeOutput(sampler)
+
+
 class Noise_EmptyNoise:
     def __init__(self):
         self.seed = 0
@@ -996,6 +1021,7 @@ async def get_node_list(self) -> list[type[io.ComfyNode]]:
             SamplerDPMAdaptative,
             SamplerER_SDE,
             SamplerSASolver,
+            SamplerSEEDS2,
             SplitSigmas,
             SplitSigmasDenoise,
             FlipSigmas,