Turn a Photo Into a Video Ad · Image to Video

ABOUT THE WORKFLOW

Generate a Video Ad From a Photo
Upload a photo of a person and describe the ad you want. The workflow writes a script, generates an opening frame, and produces a short video with spoken dialogue and ambient sound. Add an optional product photo to feature in the scene.

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

• Nano Banana 2. Generates the opening frame from your person photo and prompt, preserving identity and appearance.

• Seedance 2.5 by ByteDance. Turns the opening frame and script into a finished video with synced speech and audio in a single pass.

HOW IT WORKS

Step 1. Upload a person photo
The person who will appear in the ad. Face, hair, skin tone, and clothing carry into the video.
Works great with: headshots · half-body shots · lifestyle photos

Step 2. Upload a product photo (optional)
The product you want featured. Mention "IMAGE 2" in your prompt to include it. If you leave it out of the prompt, it is ignored.

Step 3. Write your prompt
Describe the ad: product name, duration, mood, tagline, and what happens. Example: "15-second Brewline cold brew ad. Morning routine, upbeat. Tagline: 'Brewline. Your morning, on autopilot.'"

Step 4. Hit run and download
The workflow generates an opening frame, writes a video script from your prompt, and produces a finished video with spoken dialogue and sound.
Ready for: Instagram Reels · TikTok · YouTube Shorts · any editor

First time? Leave every setting as-is. The defaults (1080p · 5s · 16:9 · 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 video ad (most people) — 1080p · 5s · 16:9 · audio on · random seed. The right starting point for almost everyone.

• Want a vertical ad for Reels or TikTok — Switch the aspect ratio to 9:16. Keep everything else the same.

• Want to feature a product in the scene — Upload the product as a second image and mention "IMAGE 2" in the prompt. The workflow composites it into the opening frame.

• Want a longer clip — Increase duration. Each run makes multiple API calls, so longer clips cost more per run.

• The person does not look right — Use a clear, well-lit photo with the face fully visible. Avoid heavy filters or sunglasses.

• The dialogue sounds rushed or unclear — Shorten the spoken lines in your prompt. The model handles short, natural sentences better than long scripts.

• Want to reproduce a result you liked — Lock the seed to the number from your previous run. Change one thing at a time in the prompt.

Prompt: Describe the ad like a brief to a director: product name, duration, mood, what happens, and the tagline. "15-second Brewline cold brew ad, morning kitchen scene, upbeat, tagline: Brewline, your morning on autopilot" works better than "make a cool ad for my drink."

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

📱 UGC-Style Product Ads
Upload a creator photo, name the product, and get a spokesperson video that looks like organic content rather than a polished commercial.

🛍️ E-Commerce Product Launches
Turn a product shot and a model photo into a short video ad without booking a shoot or hiring an editor.

🎬 Social Media Ad Testing
Generate multiple ad variations from the same person photo by changing the prompt. Test different moods, taglines, and scenarios before committing to a production run.

🏢 Small Business Marketing
Create a spokesperson video for a local business using a photo of the owner. No camera crew, no editing software, no prior video experience needed.

🎯 Pitch Decks and Mockups
Need a video ad concept to show a client before production starts? Generate a reference clip to sell the idea.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Clear, well-lit person photos with the face fully visible

• Short, specific prompts with a product name, mood, and tagline

• Single-product ads with one clear action

• Natural UGC-style scenarios (morning routines, unboxing, daily use)

⚠️ May produce softer results

• Group photos or multiple people in the person image

• Long dialogue scripts with fast or overlapping speech

• Heavily filtered or low-resolution source photos

• Vague prompts without a clear product or scenario

FAQ

What is Seedance 2.5 and what makes it good for video ads?
Seedance 2.5 is a video model by ByteDance. It generates video with synced spoken dialogue and ambient sound in a single pass, up to 1080p and 30 seconds per clip. It preserves the identity of a reference person across the video, which makes it suited for spokesperson ads where the face and voice need to stay consistent.

Does the person in the video actually speak the dialogue?
Yes. When you include a tagline or dialogue in the prompt, the person in the video speaks those words with visible lip movement and audible speech. The audio is generated in the same pass as the video. This is not a text overlay or subtitle.

Can I use a product photo without a person photo?
No. The person photo is required. The product photo is optional. If you want to feature a product, upload it as a second image and mention "IMAGE 2" in your prompt. Without a person photo, the workflow will not run.

What resolution and aspect ratio does the output support?
The default is 1080p at 16:9. You can switch the aspect ratio to 9:16 for vertical video (Reels, TikTok, Shorts) or 1:1 for square formats. Resolution stays at 1080p.

How long can the video be?
The default is 5 seconds. You can increase the duration in the settings. Each run makes multiple API calls (image generation and video generation), so longer clips cost more per run. For best dialogue clarity, keep spoken lines short relative to the clip length.

Can I use the output commercially?
Seedance 2.5 is a proprietary ByteDance model and Nano Banana 2 calls an external API. Commercial use of the outputs is generally allowed, but review the terms of the underlying model providers for your specific use case. Make sure you have the rights to any person or product photo you upload.

How to run AI video ads online?
You can run AI video ads online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, upload your inputs, 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 a person photo, describe your ad, and hit run. The settings are already set.

→ Launch Workflow, Free

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