Wan Multitalk

WAN MultiTalk — Audio-Driven Talking Avatar

Overview

MultiTalk (MeiGen-AI) drives a still portrait's lip-sync and head motion from an audio track. It runs on WAN 2.1 14B Image-to-Video via kijai's ComfyUI-WanVideoWrapper. Wav2Vec speech embeddings condition the WAN sampler so the mouth and expression follow the speech, while the lightx2v step-distill LoRA keeps it to a few sampling steps.

Use it for talking heads, dubbing, and single-speaker avatar clips (~10s at 480p). It is distinct from wan-animate (pose/motion-driven character animation). This is audio → lip-sync, not reference-video motion transfer.

Pack: wan-multitalk (480p, ~10s). Higher-res/longer variants exist in the source bundle (720p, long-context) as VRAM/duration knobs on the same graph.

Pipeline (node graph)

Copy code
LoadImage (portrait) ─┐
LoadAudio ─ AudioSeparation ─ AudioCrop ─ DownloadAndLoadWav2VecModel ─ MultiTalkWav2VecEmbeds ─┐
                                                                                                 ▼
WanVideoModelLoader (WAN 2.1 14B I2V GGUF) ─ MultiTalkModelLoader ─ WanVideoLoraSelect (lightx2v)
   + LoadWanVideoT5TextEncoder (umt5) + WanVideoTextEncode + WanVideoClipVisionEncode (clip_vision_h)
   + WanVideoVAELoader ──────────────────────────────────────────────────────────────────────────┘
                                                     ▼
                       WanVideoImageToVideoMultiTalk ─ WanVideoSampler ─ WanVideoDecode ─ VHS_VideoCombine

Key nodes (all kijai WanVideoWrapper unless noted):

• DownloadAndLoadWav2VecModel. Auto-downloads the Wav2Vec speech model on first run (no manifest entry needed).
• MultiTalkWav2VecEmbeds. Turns the (separated, cropped) speech into the embeddings that steer the mouth and expression.
• MultiTalkModelLoader + WanVideoImageToVideoMultiTalk. The MultiTalk head on top of the WAN I2V model.
• AudioSeparation and AudioCrop (audio-separation-nodes-comfyui). Isolate the voice from music/noise before embedding and trim the segment you want to animate.
• ImageResizeKJv2 (KJNodes), VHS_VideoCombine (VideoHelperSuite). Resize and mux to mp4.

Models

Sources: kijai Kijai/WanVideo_comfy, MeiGen-AI MeiGen-AI/MeiGen-MultiTalk, GGUF city96/Wan2.1-I2V-14B-480P-gguf, and Comfy-Org's repackaged UMT5. See packs/wan-multitalk/manifest.yaml (some URLs are best-effort; verify per mirror). Wav2Vec auto-downloads. The bundled WanVideoWrapper loader rejects the scaled_fp8 UMT5 checkpoint; use the UMT5 fp16 file above, not generic t5xxl_fp16 weights.

Inputs & key parameters

• Portrait (LoadImage): front-facing, clear face, neutral-ish expression works best. Resized by ImageResizeKJv2 to the target (480p).
• Audio (LoadAudio): the speech track. AudioSeparation isolates the voice; AudioCrop selects the segment (drives clip length).
• Steps: low (the lightx2v distill LoRA is why; typically ~4 to 8). Raising steps rarely helps and costs time.
• BlockSwap (WanVideoBlockSwap): trade VRAM for speed. Increase blocks swapped to CPU on lower-VRAM cards.

VRAM tiers (from the source bundle's variants)

Pair with the VRAM launch-flags guidance (see troubleshooting): --use-sage-attention

• appropriate --*vram mode; MultiTalk benefits from --reserve-vram headroom for the Wav2Vec + VAE round-trips.

Gotchas

• Audio must be voice-isolated for good lip-sync. Skipping AudioSeparation on a music-heavy track makes the mouth chase the wrong signal.
• One speaker. This graph is single-speaker; multi-speaker MultiTalk needs the multi-embed variant (not in this pack).
• Wav2Vec first run downloads a model, so the first render is slower.
• If lips look under-driven, check the MultiTalk embeds are actually wired into WanVideoImageToVideoMultiTalk (not bypassed), and that the audio isn't silent after AudioCrop.

Sources

• Official: none found.
• Empirical: sampler values, wiring, and prompt notes from working graphs in packs/ and observed renders; not a vendor prompting guide.