AI Influencer Ad Generator · Image to Video

ABOUT THE WORKFLOW

Create a Product Ad Video
Upload two images: a person and a product. Step 1 composites them into a single high-resolution image of the person holding the product in a styled scene. Step 2 takes that image and animates it into a 10-second 1080p video where the presenter speaks to camera with lip-synced dialogue, natural body language, and ambient audio. Run Step 1 first, check the result, then enable and run Step 2.

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

• Seedream 5.0 Lite by ByteDance. Used in Step 1 to composite the person and product into one styled scene at up to 2560px resolution, with accurate face, clothing, and product label preservation across up to 14 reference images.

• Wan 2.6 by Alibaba. A 14-billion-parameter video model with native audio generation, used in Step 2 to animate the composited image into a talking ad with dialogue, lip-sync, and realistic motion at 1080p.

HOW IT WORKS

Step 1. Upload your model image
A photo of the person who will present the product. Front-facing, well-lit, with visible face and upper body.
Works great with: influencer portraits · fashion photos · AI-generated characters

Step 2. Upload your product image
A clear photo of the product on a clean background showing the label, logo, or packaging design.
Works great with: perfume · beauty products · fashion accessories · gadgets · packaged goods

Step 3. Run Step 1 to generate the composite image
Seedream 5.0 Lite composites the person holding the product in the scene described in the prompt. Preview the result. Check that the product label is readable, the hand placement is natural, and the lighting works.

Step 4. Load the generated image into Step 2
Upload the output from Step 1 into the "Add your final image" input. Enable Step 2 in the workflow.

Step 5. Edit the dialogue and run Step 2
Write the presenter's spoken lines and body language in the video prompt. Wan 2.6 animates the image into a 10-second 1080p video with lip-sync, breathing, weight shifts, and ambient audio.
Ready for: TikTok · Instagram Reels · YouTube Shorts · Meta Ads · Amazon listings

First time? Run Step 1 first. Check the image. Then enable Step 2 and run again. Edit only the prompts to match your product.

RECOMMENDED SETTINGS

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

• Standard product ad video — Step 1: 9:16 at 1440x2560, single image, JPEG. Step 2: 1080P, 10 seconds, audio on, single shot. Edit the prompts to match your product and scene.

• Different setting or location — Edit the Step 1 prompt. Replace "stylish bedroom near an open closet" with "marble bathroom counter," "rooftop terrace at golden hour," or "cafe table with soft background blur."

• Different dialogue or presenter tone — Rewrite the spoken lines in the Step 2 prompt. Keep lines casual and short. "I cannot go anywhere without this scent" reads like real influencer content. "This fragrance has excellent sillage and longevity" does not.

• Multiple product variations — Keep the same model image and swap the product image across runs. Each run composites the person with a different product in the same scene.

• Product label not visible in the composite — Edit the Step 1 prompt to be more specific: "holding the perfume bottle near her collarbone, bottle facing the camera, label and cap fully visible."

• Body movement looks stiff in the video — Add more micro-actions to the Step 2 prompt. "She shifts her weight, brushes hair back with her free hand, adjusts her grip on the bottle, tilts her head mid-sentence" gives the model specific physical actions to animate between dialogue lines.

Prompt: Step 1 describes the scene and pose. Step 2 describes the motion and dialogue. "She gently shifts her weight, makes small wrist adjustments around the bottle, briefly brushes her hair back" is specific enough for natural animation. "She moves around while talking" is not.

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

🌸 Fragrance and Luxury Product Ads
Composite a model holding a perfume or luxury item in a lifestyle setting and generate a 10-second talking ad with elegant body language and spoken recommendation.

🛍️ E-commerce Product Listings
Create vertical product demo videos for marketplace listings by swapping product images across runs with the same presenter and scene.

📱 Social Media Ad Creatives
Produce scroll-stopping vertical ads for TikTok, Reels, and Shorts with native audio, lip-sync, and unscripted-feeling body language.

🔄 A/B Testing Ad Variations
Generate multiple ad versions with different presenters, products, scenes, or dialogue scripts to test which combination drives the highest engagement before committing to production spend.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Clear, front-facing model photos with visible face and hands

• Product photos on clean backgrounds with readable labels and branding

• Short, casual dialogue lines under 12 words each

• Fixed camera prompts that keep the product visible throughout the clip

⚠️ May produce softer results

• Model photos with heavy occlusion, sunglasses, or extreme angles

• Product photos with busy backgrounds or multiple items in frame

• Long monologue scripts with no physical motion described between lines

• Requesting fast camera moves or complex multi-step product demonstrations

FAQ

What is Seedream 5.0 Lite?
Seedream 5.0 Lite is ByteDance's image generation model, part of the Seed family announced alongside Seedance 2.5 at the Volcano Engine 2026 conference. It supports multi-reference input with up to 14 images in a single generation, making it strong at compositing a person with a product while preserving face, clothing, and product label accuracy.

How does this workflow differ from the Nano Banana Pro version?
This version uses Seedream 5.0 Lite (ByteDance) for image compositing instead of Nano Banana Pro (Google). Seedream 5.0 Lite outputs at higher resolution (1440x2560 vs 1K) and supports up to 14 reference images instead of 3. Both versions use the same two-step pipeline and produce similar output.

Does the video include spoken dialogue with lip-sync?
Yes. Write the spoken lines in the video prompt and Wan 2.6 generates the voice, matches mouth movement to the speech, and adds ambient audio in a single pass. Keep lines short and conversational for the cleanest sync.

Can I use any person and any product with this workflow?
Yes. Upload any front-facing portrait as the model image and any product photo as the product image. The workflow composites whoever you upload with the product you provide. Make sure the product photo has a clear label and the person photo shows visible hands for a natural holding pose.

Why does the workflow run in two steps instead of one?
Step 1 generates a static image where the person is holding the product in the right pose and scene. You preview and approve this image before Step 2 animates it into video. This gives you control over product placement, hand position, and composition before committing to the longer video generation.

Can I use these videos for paid advertising?
Seedream 5.0 Lite is a proprietary ByteDance model and Wan 2.6 is a proprietary Alibaba model. Commercial use is governed by each platform's terms of service. Review the current terms for both before running paid campaigns. Make sure you have the rights to any person or product images you upload.

How to run AI influencer ad generation online?
You can run AI influencer ad generation 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 model photo and a product photo, write the ad script, and run both steps.

→ Launch Workflow, Free

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