Wan 2.5: Image to Video with Audio

HOW IT WORKS

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

Step 2. Describe the motion Write a short prompt for what should move and how, like "the cat leans toward the flowers, petals sway in the breeze." You can describe the sound and mood too, and Wan 2.5 will score it.

Step 3. Hit run and download You get back a 5-second 720P MP4 at 24fps, with audio generated in the same 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 · 24fps · 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 clip (most people) ★ Start here — 720P · 5 seconds · default negative prompt. The right starting point for almost everyone.

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

• Want a longer clip — Set the duration to 10 seconds for more room for the motion to play out.

• Motion is too wild or too still — Name the action and its pace in the prompt. "A slow push-in as she turns her head" gives steadier results than "make it move."

• Want sound or a voice — Describe the audio in your prompt. Wan 2.5 generates synchronized sound, from ambience and effects to voice, in the same pass as the video.

• Reproduce a clip you liked — Lock the seed to the number that produced it. Same image, same prompt, same seed gives you the same clip again.

• Cleaner result — The default negative prompt filters common issues like low quality, deformed shapes, and bad proportions. Leave it on for a first run.

Prompt: Describe what moves, how it moves, and the mood. Keep it concrete. Naming the camera move and the pace ("slow push-in," "gentle sway") reads better than a vague instruction. You can add sound cues in the same prompt.

USE CASES

🎬 Social & Short-form Turn a single image into a scroll-stopping clip for Reels, Shorts, or TikTok, with sound baked in from the start.

🛍️ Product & Marketing Animate a product shot into a short promo with motion and a soundtrack, no shoot and no separate audio pass.

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

🎞️ Previs & Mood Test how a still reads in motion and sound before committing to a full shoot or animation build.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• A clear subject with room to move

• A clean, well-lit source image

• A prompt that names the motion

• Simple, describable action

⚠️ May produce softer results

• Cluttered frames with no clear subject

• Fast or extreme motion in a short clip

• 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 2.5? Wan 2.5 is a video generation model from Alibaba's Wan team. It turns a still image or a text prompt into a short, cinematic clip, and its standout feature is native audio: it generates synchronized sound in the same pass as the video. It supports 480p, 720p, and 1080p output at 24fps.

Does Wan 2.5 generate audio along with the video? Yes, and this is what sets it apart. Wan 2.5 produces synchronized audio in one pass, covering ambience, sound effects, music, and voice with lip-sync, all driven by your prompt. There is no separate recording or manual alignment step. Describe the sound you want alongside the motion and the model scores the clip to match.

What resolution and length does this workflow produce? It defaults to 720P at 5 seconds, rendered as a 24fps MP4. You can move up to 1080P for a sharper clip, or set the duration to 10 seconds for a longer one. Higher resolution and longer duration take a little more time to generate.

How is Wan 2.5 different from other image-to-video models? The main difference is built-in audio. Many image-to-video models output silent clips that you have to score separately, while Wan 2.5 generates the picture and a matched soundtrack together. It also offers multiple resolutions and aspect ratios, which makes it flexible for both vertical social clips and widescreen content.

Can I use a vertical or square image? Yes. Wan 2.5 supports several aspect ratios, so a vertical or square source works as well as a widescreen one. Match the output framing to your source image for the most natural result, especially for vertical social formats.

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 images you upload.

How to run Wan 2.5 online? You can run Wan 2.5 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 prompt and the settings are already set.

→ Launch Workflow, Free

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