Wan 2.2 14B: Image to Video + End Frame

HOW IT WORKS

Step 1. Upload a start frame The image your clip begins on. A clear subject with room to move gives the cleanest motion. Works great with: photos · illustrations · product shots · character art

Step 2. Add an end frame (optional) Upload a second image to set where the clip lands. The model animates the motion from the start frame to the end frame. Leave it out to let the motion run free from the start image.

Step 3. Write a short motion prompt Describe what should move and how, like "the camera pushes in slowly as she turns toward the light." Keep it concrete.

Step 4. Hit run and download You get back a smooth 480p MP4. The workflow interpolates extra frames so the motion plays back cleanly. Ready for: Premiere · CapCut · DaVinci Resolve · any editor

First time? Leave every setting as-is. The defaults (480p · 6 steps · fixed 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 clip (most people) Start here — Start frame, short motion prompt, defaults at 480p. The right starting point for almost everyone.

• Control where the clip ends — Add an end frame. The model animates from the start image to the end image, so you set both ends of the shot. This is the way to build a transition or a clean loop.

• Motion is too wild or too still — Name the action and its pace in the prompt. Wan 2.2 sets the motion early in the process, so a clear description steers it better than a vague one.

• Reproduce a clip you liked — The seed is fixed by default. Keep it fixed and the same frames and prompt give you the same clip again.

• Running longer or larger — Bigger frame counts and higher resolution take more time, and start-and-end-frame clips are heavier than single-frame ones. Raise them gradually.

Prompt: Describe what moves, how it moves, and the mood. Lead with the subject and camera, then the motion. The default negative prompt filters common video artifacts like blur, flicker, and bad hands, so leave it on for a first run.

USE CASES

🎬 Social & Short-form Animate a single image into a clip for Reels, Shorts, or TikTok, with the motion you describe.

🎞️ Transitions & Loops Set a start and an end frame to build a controlled transition between two images, or a clip that loops back to where it began.

🎨 Artists & Illustrators Bring character art or a painting to life with subtle, controlled motion while the style holds.

🛍️ Product & Marketing Turn a product still into a short motion piece for a landing page or a social post.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• A clear subject with room to move

• A start and end frame that share a subject, for end-frame mode

• A prompt that names the motion

• Clean, well-lit source images

⚠️ May produce softer results

• Start and end frames that are too different

• Fast or extreme motion in a short clip

• Cluttered frames with no clear subject

• 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 2.2 14B? Wan 2.2 14B is an open-weight video generation model from Alibaba's Wan team, released in July 2025 under the Apache 2.0 license. It was the first video diffusion model to use a Mixture-of-Experts design, pairing a high-noise expert that sets the overall motion and layout with a low-noise expert that refines the detail. This workflow runs the image-to-video version at 480p.

What does the optional end frame do? The end frame sets the last image of the clip. When you provide one, Wan 2.2 animates the motion from your start frame to your end frame, so you control both ends of the shot. That makes it the tool for building a transition between two images or a clip that lands back where it started. Leave it out and the model animates freely from the start frame alone.

How is Wan 2.2 different from Wan 2.5? Wan 2.2 is the open-weight model: the actual graph runs here, it is Apache 2.0 licensed, and it outputs silent video. Wan 2.5 is a newer API model whose headline feature is native synchronized audio. If you need the model weights and full control, Wan 2.2 is the one. If you want a clip with sound generated in the same pass, that is Wan 2.5.

Why does this workflow only need 6 steps? It uses a step-distillation speed LoRA built for Wan 2.2. That LoRA compresses the long sampling schedule down to about 6 steps, which is what keeps generation fast. The model's two-expert design splits those steps between the high-noise and low-noise experts.

Does Wan 2.2 generate audio? No. The open-weight Wan 2.2 outputs silent video, so add music or sound in your editor afterward. If you want audio generated together with the video, use the Wan 2.5 workflow instead, which scores the clip in the same pass.

Can I use the results commercially? Yes. Wan 2.2 is released under the Apache 2.0 license, which permits commercial use, and videos you generate on Floyo carry full commercial rights. You are responsible for having the right to use the images you upload as frames.

How to run Wan 2.2 online? You can run Wan 2.2 online through Floyo. No installation, no setup, no GPU to rent. Open the workflow in your browser, upload a start frame, 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 a start frame and run it. Add an end frame and a prompt to steer it.

→ Launch Workflow, Free

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