Skip to content

<extend> to use audio concat #1339

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mcmonkey4eva merged 2 commits into from
Apr 7, 2026
+36 −0
Merged

<extend> to use audio concat #1339

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7e8c92b
<extend> to use audio concat
jtreminio Apr 5, 2026
e295b4a
Feedback
jtreminio Apr 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 36 additions & 0 deletions src/BuiltinExtensions/ComfyUIBackend/WorkflowGeneratorSteps.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1984,6 +1984,38 @@ void altLatent(ImageToVideoGenInfo genInfo)
#region Extend Video
AddStep(g =>
{
WGNodeData ensureAttachedAudio(WGNodeData media)
{
if (media?.AttachedAudio is null || media.AttachedAudio.DataType == WGNodeData.DT_AUDIO || g.CurrentAudioVae is null)
{
return media;
}
WGNodeData dup = media.Duplicate();
dup.AttachedAudio = media.AttachedAudio.DecodeLatents(g.CurrentAudioVae, true);
return dup;
}
WGNodeData appendAudio(WGNodeData combinedAudio, WGNodeData nextAudio)
{
if (nextAudio is null)
{
return combinedAudio;
}
if (combinedAudio is null)
{
return nextAudio;
}
if (combinedAudio.DataType != WGNodeData.DT_AUDIO || nextAudio.DataType != WGNodeData.DT_AUDIO)
{
return combinedAudio;
}
string concatNode = g.CreateNode("AudioConcat", new JObject()
{
["audio1"] = combinedAudio.Path,
["audio2"] = nextAudio.Path,
["direction"] = "after"
});
return combinedAudio.WithPath([concatNode, 0], WGNodeData.DT_AUDIO, combinedAudio.Compat ?? nextAudio.Compat);
}
string fullRawPrompt = g.UserInput.Get(T2IParamTypes.Prompt, "");
if (fullRawPrompt.Contains("<extend:"))
{
Expand All @@ -1998,6 +2030,7 @@ void altLatent(ImageToVideoGenInfo genInfo)
PromptRegion regionalizer = new(fullRawPrompt);
List<JArray> vidChunks = [g.CurrentMedia.Path];
WGNodeData conjoinedLast = g.CurrentMedia;
WGNodeData conjoinedAudio = ensureAttachedAudio(conjoinedLast)?.AttachedAudio;
string getWidthNode = g.CreateNode("SwarmImageWidth", new JObject()
{
["image"] = g.CurrentMedia.Path
Expand Down Expand Up @@ -2057,6 +2090,7 @@ void altLatent(ImageToVideoGenInfo genInfo)
};
g.CreateImageToVideo(genInfo);
g.CurrentMedia = g.CurrentMedia.AsRawImage(genInfo.Vae);
WGNodeData stageWithAudio = ensureAttachedAudio(g.CurrentMedia);
videoFps = genInfo.VideoFPS;
g.CurrentMedia.FPS = videoFps ?? g.CurrentMedia.FPS;
if (saveIntermediate)
Expand All @@ -2071,12 +2105,14 @@ void altLatent(ImageToVideoGenInfo genInfo)
});
g.CurrentMedia = g.CurrentMedia.WithPath([cutNode, 0]);
vidChunks.Add(g.CurrentMedia.Path);
conjoinedAudio = appendAudio(conjoinedAudio, stageWithAudio?.AttachedAudio);
string batchedNode = g.CreateNode("ImageBatch", new JObject()
{
["image1"] = conjoinedLast.Path,
["image2"] = g.CurrentMedia.Path
});
conjoinedLast = conjoinedLast.WithPath([batchedNode, 0]);
conjoinedLast.AttachedAudio = conjoinedAudio;
}
g.CurrentMedia = conjoinedLast;
g.CurrentMedia.FPS = videoFps ?? g.CurrentMedia.FPS;
Expand Down
Loading