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.

convert AlignYourStepsScheduler node to V3 schema (#9226)

Alexander Piskunf48d05a2d17f
diff --git a/comfy_extras/nodes_align_your_steps.py b/comfy_extras/nodes_align_your_steps.py
index 8d856d0e8..edd5dadd4 100644
--- a/comfy_extras/nodes_align_your_steps.py
+++ b/comfy_extras/nodes_align_your_steps.py
@@ -1,6 +1,10 @@
#from: https://research.nvidia.com/labs/toronto-ai/AlignYourSteps/howto.html
import numpy as np
import torch
+from typing_extensions import override
+
+from comfy_api.latest import ComfyExtension, io
+
def loglinear_interp(t_steps, num_steps):
"""
@@ -19,25 +23,30 @@ NOISE_LEVELS = {"SD1": [14.6146412293, 6.4745760956, 3.8636745985, 2.694615152
"SDXL":[14.6146412293, 6.3184485287, 3.7681790315, 2.1811480769, 1.3405244945, 0.8620721141, 0.5550693289, 0.3798540708, 0.2332364134, 0.1114188177, 0.0291671582],
"SVD": [700.00, 54.5, 15.886, 7.977, 4.248, 1.789, 0.981, 0.403, 0.173, 0.034, 0.002]}
-class AlignYourStepsScheduler:
+class AlignYourStepsScheduler(io.ComfyNode):
@classmethod
- def INPUT_TYPES(s):
- return {"required":
- {"model_type": (["SD1", "SDXL", "SVD"], ),
- "steps": ("INT", {"default": 10, "min": 1, "max": 10000}),
- "denoise": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.01}),
- }
- }
- RETURN_TYPES = ("SIGMAS",)
- CATEGORY = "sampling/custom_sampling/schedulers"
-
- FUNCTION = "get_sigmas"
+ def define_schema(cls) -> io.Schema:
+ return io.Schema(
+ node_id="AlignYourStepsScheduler",
+ category="sampling/custom_sampling/schedulers",
+ inputs=[
+ io.Combo.Input("model_type", options=["SD1", "SDXL", "SVD"]),
+ io.Int.Input("steps", default=10, min=1, max=10000),
+ io.Float.Input("denoise", default=1.0, min=0.0, max=1.0, step=0.01),
+ ],
+ outputs=[io.Sigmas.Output()],
+ )
def get_sigmas(self, model_type, steps, denoise):
+ # Deprecated: use the V3 schema's `execute` method instead of this.
+ return AlignYourStepsScheduler().execute(model_type, steps, denoise).result
+
+ @classmethod
+ def execute(cls, model_type, steps, denoise) -> io.NodeOutput:
total_steps = steps
if denoise < 1.0:
if denoise <= 0.0:
- return (torch.FloatTensor([]),)
+ return io.NodeOutput(torch.FloatTensor([]))
total_steps = round(steps * denoise)
sigmas = NOISE_LEVELS[model_type][:]
@@ -46,8 +55,15 @@ class AlignYourStepsScheduler:
sigmas = sigmas[-(total_steps + 1):]
sigmas[-1] = 0
- return (torch.FloatTensor(sigmas), )
+ return io.NodeOutput(torch.FloatTensor(sigmas))
+
+
+class AlignYourStepsExtension(ComfyExtension):
+ @override
+ async def get_node_list(self) -> list[type[io.ComfyNode]]:
+ return [
+ AlignYourStepsScheduler,
+ ]
-NODE_CLASS_MAPPINGS = {
- "AlignYourStepsScheduler": AlignYourStepsScheduler,
-}
+async def comfy_entrypoint() -> AlignYourStepsExtension:
+ return AlignYourStepsExtension()