Wan 2.6: Multi-Shot Image to Video

HOW IT WORKS

Step 1. Upload your image The still your video starts from. A clear subject with room to move gives the cleanest motion. Works great with: photos · illustrations · product shots · character art

Step 2. Describe the scene Write a short prompt for the action and motion. In multi-shot mode you can lay out a small sequence, and the model splits it into separate shots while keeping the subject consistent. You can describe the sound too.

Step 3. Hit run and download You get back a 720P clip with synced audio, generated in one pass. Preview it in the workflow, then download. Ready for: Premiere · CapCut · DaVinci Resolve · any editor

First time? Leave every setting as-is. The defaults (720P · 5 seconds · multi-shot · audio on) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard clip (most people) Start here — 720P · 5 seconds · multi-shot · audio on. The right starting point for almost everyone.

• Want one continuous shot — Switch the shot type to single. The clip plays as one take instead of cutting between shots.

• Tell a small story — Keep multi-shot on and describe a short sequence in order. The model splits it into several shots and holds the subject consistent across them.

• Want a longer clip — Raise the duration to 10 or 15 seconds for more room for the story to play out.

• Higher quality — Step up to 1080P. The clip comes out sharper and takes a little longer.

• Use your own soundtrack — Paste an audio URL to drive the clip with your own track, or leave it blank to let the model generate the sound.

• Let the model polish your prompt — Prompt expansion is on by default and rewrites a short prompt into a fuller one. Turn it off when you want your exact wording.

• Reproduce a clip you liked — Lock the seed to the number that produced it.

Prompt: Describe the action, the camera, and the mood. For multi-shot, lay out the beats in the order you want them. The default negative prompt filters common artifacts like blur and bad proportions, so leave it on for a first run.

USE CASES

🎬 Short-form Story Turn one image into a multi-shot mini-scene for Reels, Shorts, or TikTok, with cuts and sound built in.

🛍️ Product & Marketing Animate a product shot into a short spot with a couple of angles and a soundtrack, no shoot required.

🎞️ Previs & Storyboards Block out a sequence of shots from a single key frame to test how a scene cuts together.

🎨 Artists & Illustrators Bring a key frame or concept to life across a few coherent shots while the character holds.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• A clear subject with room to move

• A prompt that lays out the shots in order, for multi-shot

• A clean, well-lit source image

• A described motion and mood

⚠️ May produce softer results

• Cluttered frames with no clear subject

• Too many shots packed into a short duration

• Low-resolution or blurry source images

• Vague prompts with no motion described

NEW TO COMFYUI?

Start with the free ComfyUI for Beginners Course on Floyo. Sixteen short videos take you from zero to running your own AI workflows. No setup headaches, no jargon, clear hands-on lessons. Watch the course, then run any workflow here in your browser.

👉 Watch the free ComfyUI for Beginners Course →

FAQ

What is Wan 2.6? Wan 2.6 is Alibaba's video generation model, released in December 2025. It turns an image or a text prompt into a short cinematic clip and is built for multi-shot storytelling, native audio, and character consistency across longer sequences. It outputs up to 1080p at 24fps and clips up to 15 seconds. This workflow runs the image-to-video mode.

What is multi-shot mode? Multi-shot mode lets Wan 2.6 split your prompt into several connected shots within one clip, keeping the subject, style, and scene consistent across the cuts. It is the model's standout feature: instead of one continuous take, you get a short sequence that reads like a storyboard. Switch the shot type to single when you want one unbroken shot instead.

How is Wan 2.6 different from Wan 2.5? Both generate video with native synchronized audio. Wan 2.6 adds multi-shot storytelling, longer clips up to 15 seconds, and stronger character and scene consistency across a sequence. If you want a single animated shot with sound, Wan 2.5 covers it. If you want a short multi-shot scene that holds together, Wan 2.6 is the one.

Does Wan 2.6 generate audio along with the video? Yes. Wan 2.6 produces synchronized audio in the same pass as the video, covering sound effects, ambience, and voice with lip-sync. You can also supply your own audio by pasting a track URL, or leave it blank to let the model score the clip for you.

What resolution and length does this workflow produce? It defaults to 720P at 5 seconds, rendered at 24fps. You can move up to 1080P for a sharper clip, or raise the duration to 10 or 15 seconds for a longer one. Higher resolution and longer duration take a little more time to generate.

Can I use the results commercially? Yes. Videos you generate on Floyo carry full commercial rights, so you can use them in social posts, ads, client work, and shipped projects. You are responsible for having the right to use the source image you upload.

How to run Wan 2.6 online? You can run Wan 2.6 online through Floyo. No installation, no setup, no GPU to rent. Open the workflow in your browser, upload an image, write a prompt, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A creator runs a clip and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it? Upload your image and run it. Write a short scene prompt and the settings are already set.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.