ComfyUI LC Audio_Video Nodes

ComfyUI LC Audio_Video Nodes

Custom nodes for ComfyUI by lonecatone23.

• Repo: https://github.com/lonecatone23/ComfyUI_LC_AV_nodes
• Image companion: https://github.com/lonecatone23/ComfyUI_LC123_nodes
• Civitai: lonecatone23
• Support: https://ko-fi.com/lonecatone
• Version: 0.3.13

Small tools that remove friction — frames, soundtrack, metadata, fewer extra packs.

This pack is not a fork of LC123. Do not merge the two folders. LC_PIPE stays on the image pack. This pack uses LC_AV_PIPE.

Release history lives in git tags. This page describes the pack as it is now.

---

Install

ComfyUI/custom_nodes/ComfyUI_LC_AV_nodes/__init__.py

__init__.py must sit directly in that folder — not in ComfyUI_LC_AV_nodes/ComfyUI_LC_AV_nodes/. If you unzip a pack zip inside an existing clone, move the inner files up one level.

Restart ComfyUI. Console should print [LC AV] total … nodes. Hard-refresh the browser after a web/ JS update.

Requirements: ComfyUI’s Python (torch, numpy). Save Video needs ffmpeg on PATH. Audio Separate needs torchaudio (no Numba / SoX).

Optional example graph: workflows/LC_AV Node Examples.json
(BETA — examples only. Add nodes from the node menu; do not treat the graph as a production template.)

---

What this pack is

| Title | Class | Role | | --- | --- | --- | | LC AV Pipe (in/edit) 🎬 | LCAvPipeEdit | Pack or edit LC_AV_PIPE. In: pipe, av_pipe, then video / audio / fps / … Out: av_pipe. | | LC AV Pipe Out 🎬 | LCAvPipeOut | Unpack. In: pipe + av_pipe. No LC_PIPE on the output side. | | LC Pipe → AV Pipe 🔌 | LCPipeToAvPipe | One LC_PIPE in, one LC_AV_PIPE out. Shared keys only. | | LC Create Video 🎬 | LCCreateVideo | IMAGE batch + fps (+ optional AUDIO) → LC_AV_PIPE. Does not encode a file. | | LC Save Video 💾 | LCSaveVideo | ffmpeg encode. Inputs: images, audio, av_pipe, metadata. No LC_PIPE socket. | | LC Save Video Metadata 🏷️ | LCSaveVideoMetadata | LC_SAVE_META + A1111 parameters. Works with Save Video or LC123 Save Image. | | LC Final Frame 🖼️ | LCFinalFrame | Last frame of an IMAGE batch. | | LC VAE Decode 🧩 | LCVaeDecode | Boolean wrapper: core VAEDecode or core VAEDecodeTiled. | | LC Get Latent Size 📐 | LCGetLatentSize | Pixel width / height, batch, frames. Optional VAE for compression. | | LC Load Audio 📂 | LCLoadAudio | Load from input. start_time / end_time cut, preview / pause, timeline handles. | | LC Audio Duration ⏱️ | LCAudioDuration | Seconds int + float (and minutes). | | LC Audio Crop ✂️ | LCAudioCrop | Crop AUDIO with MM:SS start / end. | | LC Audio Channel 🎚️ | LCAudioChannel | Stereo → L / R. | | LC Audio Separate 🎼 | LCAudioSeparate | Demucs stems: Bass, Drums, Other, Vocals. | | LC Audio EQ 3-Band 🎛️ | LCAudioEqualizer3Band | Low shelf, mid peak, high shelf. | | LC Audio Volume 🔊 | LCAudioVolume | Gain 0–4, soft clip. |

---

LC_AV_PIPE 🎬

Type string: LC_AV_PIPE.

Edit node sockets, top → bottom:

• pipe (LC_PIPE)
• av_pipe (LC_AV_PIPE)
• video, audio, frame_rate, duration, sample_rate, width, height, frame_count
• positive / negative, seed, total_steps, sampler_name, models

Wired slots override; empty slots pass through.

Do not put video into LC_PIPE. Convert shared fields with LC Pipe → AV Pipe.

No civitai_air on the pipe — paste AIR on Save Video Metadata.

---

Save Video 💾

VHS-style options: frame_rate, loop_count, filename_prefix, format, pix_fmt, crf, pingpong, save_output, prune_outputs.

prune_outputs keeps intermediate frame PNGs off disk.

save_metadata writes sidecar JSON + container comment. Civitai reads PNG chunks, not mp4 comment — keep civitai_still on and upload the first-frame PNG (fill models + civitai_air on the metadata node).

Frames stream into ffmpeg one at a time with a progress bar, so long clips don't fill your RAM, and Cancel stops it (no half-written file is left).

On-node preview after encode. Resize the node; the player follows aspect.

Wire IMAGE from VAE Decode (or Create Video images) into images. Metadata is optional. av_pipe can carry frames if they were packed there.

---

LC VAE Decode 🧩

tiled off = nodes.VAEDecode.
tiled on = nodes.VAEDecodeTiled (tile_size, overlap, temporal_size, temporal_overlap).

Same latent + same VAE as the two core nodes. Use the MiniMax Video VAE for video latents.

Shows a progress bar per tile (also on the MiniMax Video VAE, which tiles itself), and Cancel stops it between tiles.

---

Load Audio 📂

Load audio uploads into Comfy input/ like stock Load Audio.

start_time / end_time (seconds). end_time 0 = end of file. Output duration is the cut length.

preview / pause plays only that cut. Drag the two handles on the timeline (after one preview so file length is known).

---

H3 Long Video 🎬

Minute-long MiniMax H3 videos made in short pieces, one segment per Run, on the same card that makes 5 s clips. The plan comes from LC Vision Director 🎬 (LC Vision). Example workflow: LC H3 Long Video Example.json.

LC H3 Segment 🎞️

• Builds one segment for your sampler: positive + latent out, seed passed through.
• index 0 = the next segment not saved yet. Set a number to redo that one.
• A CONTINUE segment starts from the last 1.6 s (picture and sound) of the one before, so the motion carries straight on.
• memory clip (default): about 1 s of segment 1 (her head only) goes in as a reference on a CUT your story writes, and as a gentle nudge on any CONTINUE that starts with no clear face (she walked away or turned round). memory_gap 5 s keeps the cut from opening on that clip's pose.
• color_match 0 = off. Turn it on (0.2 to 0.4) when Assemble flags a scene drifting warmer or cooler.
• 💡 960 x 544 is the low VRAM size. Keep one size for the whole project.
• prompt output: the segment's prompt, quotes and all. Wire it into LC H3 Dialogue Check to check each segment's speech.

LC H3 Segment Save 💾

• Decodes and saves the segment to output/LC_H3/<project>/: a preview mp4, the part for the final video and the ending the next segment starts from.
• Shows a face match to segment 1 (0 to 1): 0.55 and up = same person, under 0.40 = someone else, redo it with another seed. Other people in the shot and faces turned away are left out.
• Face check models: face_detection_yunet_2023mar.onnx + face_recognition_sface_2021dec.onnx in models/facerestore (OpenCV zoo). Without them it just skips the check.

LC H3 Assemble 🧩

• Joins every saved segment into <project>_full.mp4, straight from disk (never the whole video in RAM).
• blend_frames crossfades each CONTINUE join over the shared frames so it doesn't pop.
• Reports how smooth every join is, how far the color drifts inside each scene, and every face match. Wire Segment Save's info into after so it runs after the new segment is saved.

LC H3 Audio Sync (BETA) 🎤

• Makes an H3 video perform YOUR track (a song, a line of dialogue) instead of sound the model invents. Put it between the latent and the sampler.
• Your recording is locked into the sound half, so the model only decides the picture that fits it, mouth included.
• 💡 Wire the H3 positive conditioning through it too: the track is also handed to H3 as a clean guide.
• ✋ Put each line in the prompt with its time: At 0 seconds she says, "Hello there." H3 moves the mouth when the prompt says the words are spoken, not when it hears them. Without the time she talks over the silence instead. LC H3 Dialogue Check's prompt_line writes these lines for you from your recording.
• start_seconds picks where in the track the clip starts. A track shorter than the clip is filled with silence or looped.
• The audio output is the track cut to the clip's length: wire it to the save node so picture and sound end together.
• ⚠️ H3 was trained to about 15 s; longer clips get a warning in info.

LC Frame Interpolate 🎞️

• Smooth motion with RIFE 4.26: makes the in-between frames so a 24 fps clip plays at 48, 60, or any rate (not just 2x). Each new frame lands at its real moment in time.
• scene_cut holds hard cuts instead of morphing across them (a morph across a cut is a smeared ghost frame). 0 = off.
• Wire the clip's audio and the output is exactly as long as the sound, so picture and audio end together.
• model: rife426.pth (best on AI video in our tests, downloads once, 21 MB) or crossfade (no model, fast, soft on motion). Uses models/rife/ or ComfyUI-Frame-Interpolation's checkpoints if you have them.
• RIFE code from ComfyUI-Frame-Interpolation (Fannovel16) and Practical-RIFE (hzwer), both MIT.

LC H3 Dialogue Check (BETA) 🗣️

• Listens to a finished clip with Whisper and compares what was said with the dialogue in quotes in your prompt. A low match means garbled speech: redo the shot.
• cut_points lists the pauses, the clean places to cut or start the next segment.
• prompt_line gives the transcript back as timed lines: At 0 seconds they say, "...". Feed your recording through it before LC H3 Audio Sync, paste the lines into the prompt and change "they" to the character.
• Whisper downloads once to models/stt/ (small = about 460 MB) and runs on the CPU: a few seconds a clip, and the GPU stays free for H3.

💡 Vision Assistant → Movie (LC Vision) shows all of it in plain words, with one-click redo and Make all remaining.

---

Colors

web/lc_node_colors.js — AV family teal (#2a6a6a audio, #1a5a7a video). Distinct from LC123 sigma #1c6d6d. VAE Decode uses stock Comfy red.

web/lc_color.js is the launch-color helper (does not overwrite a saved color).

---

License

MIT. See LICENSE.