IAMCCS V2V Bus To WanAnimate

WanAnimate is the animation backend that takes a reference character and drives it with a pose video, a face video, and optionally a background - and it's famously picky about getting all of those channels right. V2V Bus To WanAnimate is the adapter that unpacks the IAMCCS media and control buses into WanAnimate's expected inputs, so the bus-driven V2V graph can switch to WanAnimate without re-plumbing.

This one has the richest output set of the BusTo family, because WanAnimate wants more channels than the others: face_video, pose_video, and background_video are separate optional inputs, plus a character_mask (a real MASK, not an image). The node routes the media bus's source into the right channel - driver motion goes to pose_video, reference to reference_image - and lets you override or add the face/background/mask channels as needed.

Inputs

• media_bus, control_bus - required.
• face_video, pose_video, background_video (optional IMAGE) - override channels.
• character_mask (optional MASK) - which region of the frame the character occupies.

Outputs

• reference_image - the character identity.
• face_video, pose_video, background_video, character_mask - the WanAnimate channels, resolved from the bus and your overrides.
• positive_prompt, negative_prompt, fps, generation_width, generation_height, output_prefix, source_audio, source_video_info, report.

Install

Ships in IAMCCS-nodes:

cd ComfyUI/custom_nodes
git clone https://github.com/IAMCCS/IAMCCS-nodes.git

or via ComfyUI Manager (search "IAMCCS"), restart. The WanAnimate model itself is separate - this node only converts the bus.

Practical notes

WanAnimate's character mask and background channel are where quality is won or lost. If the bus's source video has a static background, leaving background_video unconnected means the backend derives it from the source - usually fine. But if the character moves through a changing scene, feed a background and mask the character so the model doesn't smear motion onto the background. This is also the backend the pack's original LoRA-fix story revolves around: the whole IAMCCS pack started because LoRA weights silently failed to load in native WanAnimate pipelines without the wrapper - so if you're applying character LoRAs through this chain, make sure you're on the pack's LoRA stack/apply nodes rather than vanilla Apply LoRA, or you may get ignored weights and broken consistency.