Wan 2.6 · Multi-Shot Image to Video

ABOUT THE WORKFLOW

Build a Multi-Shot Clip From One Image Upload a picture and describe the scene. Wan 2.6 plans its own camera angles and cuts, builds the picture and the sound together in one pass, and returns a clip with multiple shots and synchronized audio. No editing or stitching needed.

Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.

Model

• Wan 2.6 by Tongyi Lab at Alibaba. Released December 2025. A closed video model that generates 720p or 1080p video up to 15 seconds with native audio in one pass. Its multi-shot mode plans camera angles and transitions automatically from a single prompt, holding characters and lighting consistent across cuts.

HOW IT WORKS

Step 1. Upload your image The opening frame. It sets the subject, the scene, and the look. Works great with: character art · group scenes · product setups · location photos

Step 2. Describe the scene Write the story arc, not a shot list. The model decides where to cut, which angles to use, and how to time them. "Group of men wearing Santa attire sing while holding their instruments."

Step 3. Hit run and download The model builds several camera angles, cuts between them, writes sound effects and ambient audio, and returns one finished clip saved under wan2.6. Ready for: Premiere · DaVinci Resolve · CapCut · After Effects

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

RECOMMENDED SETTINGS

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

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

• Want a single continuous shot instead — Switch shot type from multi to single. The model holds one camera angle through the whole clip rather than planning cuts.

• Need higher resolution — Switch to 1080P. Resolution and duration together drive cost, so raise one at a time.

• Need a longer clip — Raise the duration. The model handles up to 15 seconds per run. More time gives it room for more shots and transitions.

• Sound is not matching the scene — Describe the sound separately in the prompt. Name the voices, the instruments, and the room tone alongside the visual action.

• Your prompt is already detailed — Turn prompt extend off. Left on, the model rewrites your prompt for richer detail before generating.

• Repeat a take you liked — Set a fixed seed number instead of leaving it on random. The same image, prompt, and seed give you the same clip back.

• The negative prompt — The default lists common quality issues. Add anything you keep seeing, like "shaky camera" or "discontinuous cuts."

Prompt: Write a story, not a shot list. "A jazz quartet plays in a dim club, the camera drifts from the pianist to the saxophonist, crowd murmurs and glasses clink" gives you more than "show each musician." The multi-shot mode decides its own coverage, so describe the scene and the mood, not the individual angles.

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

USE CASES

🎬 Social Clips and Trailers Turn one still into a multi-angle clip with cuts and sound for Reels, TikTok, or Shorts, with no editing step.

📢 Product and Brand Films Animate a product setup into a short with several camera angles, ambient audio, and transitions in one run.

🎵 Music and Performance Give the model a band or performer and a description of the performance. It returns coverage from multiple angles with the instruments and voices on the track.

🎨 Previz and Storyboarding Test how a scene plays across several shots before committing to a production schedule.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Scene descriptions with a story arc rather than a shot list

• One or two clear subjects with a consistent setting

• Prompts that name the sound alongside the action

• Clips of 5 to 10 seconds to start

⚠️ May produce softer results

• Shot-by-shot instructions that fight the model's own coverage plan

• Scenes with many unrelated subjects

• Duration pushed to 15 seconds on a first test

• Prompts that describe the image instead of what happens

FAQ

What is Wan 2.6 multi-shot mode? Wan 2.6 multi-shot mode generates a video with multiple camera angles and automatic transitions from a single prompt. The model plans its own coverage, deciding when to cut and which angle to use, while keeping characters, lighting, and environment consistent across shots. Sound effects, dialogue, and ambient audio are synchronized in the same pass.

How does the model decide where to cut? The model reads your prompt as a story arc and chooses camera angles and cut points that follow the action. You describe the scene and the mood, and it handles the editorial decisions. If you want to control every cut yourself, switch shot type to single and run separate clips.

Does Wan 2.6 generate audio with the video? Yes. Sound is generated in the same pass as the picture, including ambient sound, effects, dialogue, and lip sync. Describe the sound in your prompt and it goes onto the track. Turn audio off if you want a silent clip.

What is the difference between multi and single shot type? Multi lets the model plan multiple camera angles and transitions within one clip. Single holds one continuous camera angle from start to finish. Use multi for scene-level clips and single when you want full control over the camera.

Is Wan 2.6 open source? No. Wan 2.6 is API-only with no published weights. Open weights in the Wan family stop at Wan 2.2, which is released under Apache 2.0. Pick Wan 2.2 for open weights and local control, and Wan 2.6 for multi-shot storytelling and native audio through the API.

What is the difference between Wan 2.6 and Wan 2.7? Wan 2.6 introduced multi-shot mode and native audio in December 2025. Wan 2.7 arrived in April 2026 and added a thinking mode that plans composition before rendering, plus first-to-last-frame interpolation and clips up to 15 seconds. Both are API-only. Pick 2.6 for multi-angle coverage from a single prompt, and 2.7 for compositional planning and longer clips.

How to run Wan 2.6 multi-shot online? You can run Wan 2.6 multi-shot online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, upload an image, describe the scene, 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 designer runs an edit 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 an image, describe the scene, and run it. The model plans the shots for you.

→ Launch Workflow, Free

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