V3: AceStepAudio nodes

comfy_api/v3/io.py

@@ -390,19 +390,19 @@ class String(ComfyTypeIO):
     class Input(WidgetInputV3):
         '''String input.'''
         def __init__(self, id: str, display_name: str=None, optional=False, tooltip: str=None, lazy: bool=None,
-                    multiline=False, placeholder: str=None, default: str=None, dynamicPrompts: bool=None,
+                    multiline=False, placeholder: str=None, default: str=None, dynamic_prompts: bool=None,
                     socketless: bool=None, force_input: bool=None):
             super().__init__(id, display_name, optional, tooltip, lazy, default, socketless, None, force_input)
             self.multiline = multiline
             self.placeholder = placeholder
-            self.dynamicPrompts = dynamicPrompts
+            self.dynamic_prompts = dynamic_prompts
             self.default: str
 
         def as_dict_V1(self):
             return super().as_dict_V1() | prune_dict({
                 "multiline": self.multiline,
                 "placeholder": self.placeholder,
-                "dynamicPrompts": self.dynamicPrompts,
+                "dynamicPrompts": self.dynamic_prompts,
             })
 
 @comfytype(io_type="COMBO")

comfy_extras/v3/nodes_ace.py

@@ -0,0 +1,57 @@
+from __future__ import annotations
+
+import torch
+
+import comfy.model_management
+import node_helpers
+from comfy_api.v3 import io
+
+
+class TextEncodeAceStepAudio(io.ComfyNodeV3):
+    @classmethod
+    def define_schema(cls):
+        return io.SchemaV3(
+            node_id="TextEncodeAceStepAudio_V3",
+            category="conditioning",
+            inputs=[
+                io.Clip.Input("clip"),
+                io.String.Input("tags", multiline=True, dynamic_prompts=True),
+                io.String.Input("lyrics", multiline=True, dynamic_prompts=True),
+                io.Float.Input("lyrics_strength", default=1.0, min=0.0, max=10.0, step=0.01),
+            ],
+            outputs=[io.Conditioning.Output()],
+        )
+
+    @classmethod
+    def execute(cls, clip, tags, lyrics, lyrics_strength) -> io.NodeOutput:
+        conditioning = clip.encode_from_tokens_scheduled(clip.tokenize(tags, lyrics=lyrics))
+        conditioning = node_helpers.conditioning_set_values(conditioning, {"lyrics_strength": lyrics_strength})
+        return io.NodeOutput(conditioning)
+
+
+class EmptyAceStepLatentAudio(io.ComfyNodeV3):
+    @classmethod
+    def define_schema(cls):
+        return io.SchemaV3(
+            node_id="EmptyAceStepLatentAudio_V3",
+            category="latent/audio",
+            inputs=[
+                io.Float.Input("seconds", default=120.0, min=1.0, max=1000.0, step=0.1),
+                io.Int.Input(
+                    "batch_size", default=1, min=1, max=4096, tooltip="The number of latent images in the batch."
+                ),
+            ],
+            outputs=[io.Latent.Output()],
+        )
+
+    @classmethod
+    def execute(cls, seconds, batch_size) -> io.NodeOutput:
+        length = int(seconds * 44100 / 512 / 8)
+        latent = torch.zeros([batch_size, 8, 16, length], device=comfy.model_management.intermediate_device())
+        return io.NodeOutput({"samples": latent, "type": "audio"})
+
+
+NODES_LIST: list[type[io.ComfyNodeV3]] = [
+    TextEncodeAceStepAudio,
+    EmptyAceStepLatentAudio,
+]

nodes.py

@@ -2299,14 +2299,15 @@ def init_builtin_extra_nodes():
         "nodes_tcfg.py",
         "nodes_v3_test.py",
         "nodes_v1_test.py",
+        "v3/nodes_ace.py",
         "v3/nodes_audio.py",
         "v3/nodes_controlnet.py",
         "v3/nodes_images.py",
         "v3/nodes_mask.py",
         "v3/nodes_preview_any.py",
         "v3/nodes_primitive.py",
-        "v3/nodes_webcam.py",
         "v3/nodes_stable_cascade.py",
+        "v3/nodes_webcam.py",
     ]
 
     import_failed = []