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.pyindex 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.htmlimport numpy as npimport 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 = stepsif 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()