Compare commits

..

7 Commits

8 changed files with 11752 additions and 4897 deletions

View File

@ -174,7 +174,7 @@ class Ideogram4Transformer(nn.Module):
llm = self.llm_cond_proj(llm) * text_mask
h[:, :L_text] = h[:, :L_text] + llm
h = h + self.embed_image_indicator((indicator == OUTPUT_IMAGE_INDICATOR).to(torch.long), out_dtype=h.dtype)
h = h + self.embed_image_indicator((indicator == OUTPUT_IMAGE_INDICATOR).to(torch.long))
# Qwen3-VL interleaved MRoPE; position_ids (B, L, 3) -> (3, L) (same across batch).
freqs_cis = precompute_freqs_cis(
@ -235,7 +235,7 @@ class Ideogram4Transformer2DModel(Ideogram4Transformer):
def _run_conditional(self, x_chunk, context_chunk, attn_mask_chunk, t_chunk, gh, gw, transformer_options):
B = x_chunk.shape[0]
device = x_chunk.device
img_tokens = self._img_to_tokens(x_chunk)
img_tokens = self._img_to_tokens(x_chunk).to(self.dtype)
L_img = img_tokens.shape[1]
L_text = context_chunk.shape[1]
L = L_text + L_img
@ -268,7 +268,7 @@ class Ideogram4Transformer2DModel(Ideogram4Transformer):
def _run_image_only(self, x_chunk, t_chunk, gh, gw, transformer_options):
B = x_chunk.shape[0]
device = x_chunk.device
img_tokens = self._img_to_tokens(x_chunk)
img_tokens = self._img_to_tokens(x_chunk).to(self.dtype)
L_img = img_tokens.shape[1]
position_ids = self._image_position_ids(gh, gw, device).unsqueeze(0).expand(B, L_img, 3)

View File

@ -285,7 +285,7 @@ class AudioSaveHelper:
results = []
for batch_number, waveform in enumerate(audio["waveform"].cpu()):
filename_with_batch_num = filename.replace("%batch_num%", str(batch_number))
file = f"{filename_with_batch_num}_{counter:05}.{format}"
file = f"{filename_with_batch_num}_{counter:05}_.{format}"
output_path = os.path.join(full_output_folder, file)
# Use original sample rate initially

View File

@ -158,7 +158,7 @@ class SaveAudio(IO.ComfyNode):
return IO.Schema(
node_id="SaveAudio",
search_aliases=["export flac"],
display_name="Save Audio (FLAC) (Deprecated)",
display_name="Save Audio (FLAC)",
category="audio",
essentials_category="Audio",
inputs=[
@ -167,7 +167,6 @@ class SaveAudio(IO.ComfyNode):
],
hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo],
is_output_node=True,
is_deprecated=True,
)
@classmethod
@ -187,7 +186,7 @@ class SaveAudioMP3(IO.ComfyNode):
return IO.Schema(
node_id="SaveAudioMP3",
search_aliases=["export mp3"],
display_name="Save Audio (MP3) (Deprecated)",
display_name="Save Audio (MP3)",
category="audio",
essentials_category="Audio",
inputs=[
@ -197,7 +196,6 @@ class SaveAudioMP3(IO.ComfyNode):
],
hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo],
is_output_node=True,
is_deprecated=True,
)
@classmethod
@ -219,7 +217,7 @@ class SaveAudioOpus(IO.ComfyNode):
return IO.Schema(
node_id="SaveAudioOpus",
search_aliases=["export opus"],
display_name="Save Audio (Opus) (Deprecated)",
display_name="Save Audio (Opus)",
category="audio",
inputs=[
IO.Audio.Input("audio"),
@ -228,7 +226,6 @@ class SaveAudioOpus(IO.ComfyNode):
],
hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo],
is_output_node=True,
is_deprecated=True,
)
@classmethod
@ -244,54 +241,6 @@ class SaveAudioOpus(IO.ComfyNode):
save_opus = execute # TODO: remove
class SaveAudioAdvanced(IO.ComfyNode):
@classmethod
def define_schema(cls):
return IO.Schema(
node_id="SaveAudioAdvanced",
search_aliases=["save audio", "export audio", "output audio", "write audio", "flac", "mp3", "opus"],
display_name="Save Audio (Advanced)",
description="Saves the input audio to your ComfyUI output directory.",
category="audio",
inputs=[
IO.Audio.Input("audio", tooltip="The audio to save."),
IO.String.Input(
"filename_prefix",
default="audio/ComfyUI",
tooltip=(
"The prefix for the file to save. May include formatting tokens "
"such as %date:yyyy-MM-dd%."
),
),
IO.DynamicCombo.Input(
"format",
options=[
IO.DynamicCombo.Option("flac", []),
IO.DynamicCombo.Option("mp3", [
IO.Combo.Input("quality", options=["V0", "128k", "320k"], default="V0"),
]),
IO.DynamicCombo.Option("opus", [
IO.Combo.Input("quality", options=["64k", "96k", "128k", "192k", "320k"], default="128k"),
]),
],
tooltip="The file format in which to save the audio.",
),
],
hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo],
is_output_node=True,
)
@classmethod
def execute(cls, audio, filename_prefix: str, format: dict) -> IO.NodeOutput:
file_format = format.get("format", None)
quality = format.get("quality", None)
if quality:
ui=UI.AudioSaveHelper.get_save_audio_ui(audio, filename_prefix=filename_prefix, cls=cls, format=file_format, quality=quality)
else:
ui=UI.AudioSaveHelper.get_save_audio_ui(audio, filename_prefix=filename_prefix, cls=cls, format=file_format)
return IO.NodeOutput(ui=ui)
class PreviewAudio(IO.ComfyNode):
@classmethod
def define_schema(cls):
@ -873,7 +822,6 @@ class AudioExtension(ComfyExtension):
SaveAudio,
SaveAudioMP3,
SaveAudioOpus,
SaveAudioAdvanced,
LoadAudio,
PreviewAudio,
ConditioningStableAudio,

View File

@ -411,21 +411,6 @@ class ImageProcessingNode(io.ComfyNode):
return has_group
@classmethod
def _ensure_image_list(cls, images):
"""Normalize to a flat list of [1, H, W, C] tensors."""
if isinstance(images, torch.Tensor):
if images.ndim != 4:
raise ValueError(f"Expected 4D image tensor, got shape {tuple(images.shape)}")
return [images[i:i+1] for i in range(images.shape[0])]
flat = []
for item in images:
if not isinstance(item, torch.Tensor) or item.ndim != 4:
raise ValueError(f"Expected 4D image tensor, got {type(item).__name__} shape {getattr(item, 'shape', None)}")
flat.extend([item[i:i+1] for i in range(item.shape[0])])
return flat
@classmethod
def define_schema(cls):
if cls.node_id is None:
@ -473,9 +458,6 @@ class ImageProcessingNode(io.ComfyNode):
"""Execute the node. Routes to _process or _group_process based on mode."""
is_group = cls._detect_processing_mode()
if is_group:
images = cls._ensure_image_list(images)
# Extract scalar values from lists for parameters
params = {}
for k, v in kwargs.items():

View File

@ -1,3 +1,3 @@
# This file is automatically generated by the build process when version is
# updated in pyproject.toml.
__version__ = "0.24.0"
__version__ = "0.24.1"

16559
openapi.yaml

File diff suppressed because it is too large Load Diff

View File

@ -1,6 +1,6 @@
[project]
name = "ComfyUI"
version = "0.24.0"
version = "0.24.1"
readme = "README.md"
license = { file = "LICENSE" }
requires-python = ">=3.10"

View File

@ -1,4 +1,4 @@
comfyui-frontend-package==1.45.15
comfyui-frontend-package==1.44.19
comfyui-workflow-templates==0.9.98
comfyui-embedded-docs==0.5.2
torch