Reference

Video models

The video models behind Crust's video nodes.

Video models offer some of these modes: Generate (a clip from a prompt, with or without start and end frames), Reference (images, clips or sound steer the result), Edit (change a clip) and Extend (continue one). Each card lists the modes a model offers, whether it makes sound, and how many references it takes. Durations and resolutions are on each model's page.

Video model families

veo-3.1-generate-001 / fastGoogle / Veo node

Generate and reference modes. Start/end frames, up to three references, and optional generated audio. Extend is retired.

Seedance familyByteDance / fal / Seedance node

Text, image, and reference video generation with large image/video/audio reference banks and optional generated audio.

standard / proKling / fal / Kling node

Generate mode with start/end frames and optional generated audio.

wan3.0-video / primeAlibaba / Wan node

Generate, reference, edit, and extend with image, video, and audio references.

grok-imagine-video / 1.5xAI / Grok video node

Generate, reference, edit, and extend. Supports a start image, source video, and several image references.

h3-maxMiniMax / H3 Max node

Multimodal generation from prompt plus image, video, and audio references.

ray-3.2Luma / Luma Ray node

Text-to-video, image-to-video, video edit, start/end frames, and keyframe direction.

auto / v1.1Alibaba / Happy Horse node

Text, image, reference, and video-edit modes with dialogue-focused output.

Wan VACE / Luma Ray 3.2fal / Luma / Video reframe

Generates or rebuilds a clip for a target aspect rather than only cropping it.

Sync V2 Pro / HeyGen Speed / Precisionfal / HeyGen / Lip sync

Drives mouth motion in a source video from the connected audio track.

ltx-2.5-proLightricks / fal / LTX 2.5 node, Audio to video

Text-to-video or image-to-video with start and end frames, 6, 8, or 10 seconds, camera motion presets, and generated audio. Also Audio to video's Auto choice for 2–10 seconds of audio.

ltx-2.3-qualityLTX / fal / Audio to video node

Audio to video for longer audio, up to 60 seconds: a clip timed to the connected track.

omnihuman-v2ByteDance / fal / Audio to video (menu variant or Model)

A lip-synced talking person from one portrait and 4 seconds to 5 minutes of speech. Prompt optional.

sam-3-video-rlefal / Video segmentation node

Prompted video masks; returns a mask track for the described subject.

proteus / artemis / nyx / gaia / starlightTopaz / fal / Upscale video node

Video upscaling with a choice of enhancement models; Auto picks by source.

meshy-7.1Meshy / fal / 3D generate node

Text, image or multi-image to a GLB model.

Guide version 2026.10.21-3 · October 21, 2026