We’re excited to announce that Wan2.7 — Alibaba’s latest video generation model — is now available in ComfyUI via Partner Nodes!

Wan2.7 is a comprehensive upgrade over version 2.6, with significant improvements across image quality, audio, motion dynamics, stylization, and consistency. It also expands the creative workflow toolkit considerably — supporting up to 5 real-person image inputs, a vocal timbre reference, and 3×3 grid-based image generation.

This release brings a fully upgraded multimodal video pipeline directly into your node graph, supporting text, image, audio, and video inputs across four task types:

Image-to-Video: first-frame, first+last-frame, and audio-driven generation
Text-to-Video: pure text prompts with optional audio input and multi-shot narration
Video Continuation: extend an existing clip with new content guided by a text prompt
Reference-to-Video: reference both a subject’s visual appearance and vocal timbre; supports up to 5 real-person inputs and multi-character interactions
Video Edit: edit or replicate videos via text prompts, reference image, or style transfer

Examples

Image to Video

The flock of flamingos in yellow sunglasses stands in the bright daylight as in the image. The camera frame slowly tilts to a Dutch angle. Funky bass groove begins. One flamingo — slightly taller than the others — notices the tilt, looks directly at the lens, then deliberately tilts its own head to match. Flamingo: "Better. Now we're both weird."

Starting from the front view, the camera slowly orbits behind the TV-headed figure, settling over its shoulder and looking out across the dim, blurred office into the darkness beyond. A deep ambient bass tone hums. The figure doesn’t move, but the screen’s glow casts a faint rectangle of light forward into the dark room. TV Head (quietly): “Something’s out there.” The screen flickers once. “It’s been watching us back.”

Download Wan2.7 Image to Video Workflow

Text to Video

Warm amber candlelight, low angle wide shot. A vast library where bookshelves extend infinitely upward into darkness, books drifting open in mid-air, pages glowing softly. A young scholar walks the central aisle, candlelight in hand. A deep disembodied voice resonates from above: "Have you found what you came for?"

Rain-streaked glass, night, interior car — dashboard light only. Two people sit in a parked car outside a lit house, neither moving. Woman (staring ahead): "I don't know how to go in there and pretend everything's fine."

Download Wan2.7 Text to Video Workflow

Reference to Video

Wan2.7 Reference to Video Workflow

Video Edit

before:

after:

Download Wan2.7 Video Edit Workflow

Get Started in ComfyUI

Update ComfyUI to the 0.18.5, (ComfyUI Desktop and Comfy Cloud will be ready soon.)
Go to Template Library → Video and search for Wan2.7
Choose the workflow that matches your task and run!

As always, enjoy creating!

ComfyUI Newsletter

Wan2.7 Is Now Available in ComfyUI via…