Seedance 2.0 Product Tutorial · Reference to Video

ABOUT THE WORKFLOW

Generate a Product Review Video
Upload two images: your product and the person presenting it. Write a timed script describing what the presenter says and does at each moment. Seedance 2.0 composites the person with the product into a single scene and generates a 15-second vertical video with spoken dialogue, lip-sync, and native audio. The output is a ready-to-post MP4 in 9:16 portrait format.

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

• Seedance 2.0 by ByteDance (SEED Lab). The #1-ranked video model on the Artificial Analysis Video Arena. Accepts multimodal references (images, video, audio) and generates synchronized audio-visual output with character consistency and lip-sync.

HOW IT WORKS

Step 1. Upload your product image
A clear photo of the product being reviewed. Well-lit, on a clean background, showing the product from its best angle.
Works great with: electronics · kitchen appliances · beauty products · fashion accessories · packaged goods

Step 2. Upload your model image
A photo of the person who will present the product. Front-facing, well-lit, with visible face and upper body.

Step 3. Write a timed review script
Structure the prompt with time codes and shot descriptions. Describe what the presenter says (in quotes), what they do with the product, and how the camera frames each moment. Example: "0-2s: He lifts the toaster toward the camera and says 'This toaster looks way too good to just sit on a counter.' 2-5s: He runs his hand along the body and rotates the dial."

Step 4. Hit run and download
Seedance 2.0 generates a 15-second vertical video at 720p with dialogue, lip-sync, and ambient audio. The output is an MP4 at 30fps.
Ready for: TikTok · Instagram Reels · YouTube Shorts · Amazon product listings · Shopify

First time? Upload your two images, edit the timed script to match your product, and hit run. Leave resolution, duration, and aspect ratio as-is.

RECOMMENDED SETTINGS

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

• Standard product review video (most people) — 720p, 15 seconds, 9:16 vertical, audio on. Edit the prompt script to match your product.

• Shorter hook clip — Reduce duration to 5 or 10 seconds. Write a tighter script covering only the opening hook and one product detail.

• Landscape format for YouTube or web — Switch aspect ratio from 9:16 to 16:9. Adjust the script to describe wider framing.

• Different presenter style — Rewrite the script tone. Swap "UGC iPhone aesthetic" for "studio lighting, professional presenter" or "casual kitchen setting, friend talking to camera."

• Multiple product angles — Upload additional product images in slots 3 through 9. Reference them in the prompt: "At 5s, show the product from the angle in image 3."

• Presenter identity drifts — Use a clearer, front-facing reference photo. Add "preserve the exact face, hair, and outfit from the reference" to the prompt.

• Dialogue sounds unnatural — Shorten each spoken line to 8 words or fewer. Real UGC uses short, punchy reactions, not full sentences.

Prompt: Structure the script with time codes and specific actions. "0-3s: She holds the serum bottle up and says 'This changed my skin in two weeks.' 3-6s: She squeezes a drop onto her fingertip and shows the texture to the camera." is specific. "Person talks about a product" 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

🛍️ E-commerce Product Listings
Generate vertical product demo videos for Amazon, Shopify, or marketplace listings from a product photo and a presenter image.

📱 TikTok and Reels Ad Creatives
Produce UGC-style review clips at scale by swapping product images and presenter photos across multiple runs with the same script structure.

📦 Unboxing and First Impressions
Script a timed unboxing sequence where the presenter reacts to the product, inspects build quality, and highlights key features.

🧴 Beauty and Skincare Demos
Generate application or swatch demos where the presenter interacts with the product and speaks directly to the camera.

🔄 A/B Testing Ad Variations
Run the same product with different presenters, or the same presenter with different scripts, to test which combination performs best.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Clean, well-lit product photos on simple backgrounds

• Front-facing presenter photos with visible face and hands

• Timed scripts with short spoken lines (under 10 words each)

• Clear action descriptions per segment ("lifts product," "taps the button," "rotates it")

⚠️ May produce softer results

• Product photos with busy backgrounds or multiple objects

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

• Long monologue scripts with no physical product interaction described

• Trying to show fine text or small labels on the product

FAQ

What is Seedance 2.0?
Seedance 2.0 is ByteDance's multimodal video generation model, released February 2026. It accepts text, images, video, and audio as references and generates synchronized video with native audio in a single pass. It holds the #1 position on the Artificial Analysis Video Arena for both text-to-video and image-to-video.

Can Seedance 2.0 generate dialogue with lip-sync?
Yes. Write the spoken lines in quotes in the prompt and the model generates the voice, mouth movement, and ambient audio together. It supports lip-sync in multiple languages including English and Mandarin.

How does the timed prompt script work?
Break the prompt into segments with time ranges: "0-3s: [action and dialogue]. 3-6s: [next action]." Seedance 2.0 reads the timing cues and maps each segment to the corresponding part of the video. Each segment should describe what the presenter does, what they say, and how the camera frames the shot.

Can I use my own product and presenter photos?
Yes. Upload any product photo as image 1 and any person photo as image 2. The model composites the person with the product based on your script. Make sure the product image is clear and the presenter photo is front-facing with a visible face.

Does the output have a watermark?
Seedance 2.0 outputs carry a C2PA provenance watermark embedded in the file metadata. It does not affect how the video looks but records that the content was AI-generated.

Is Seedance 2.0 licensed for commercial product videos?
Seedance 2.0 is a proprietary ByteDance model. Commercial use is governed by ByteDance's terms of service. Review the current terms for your specific use case, especially if the presenter reference is based on a real person.

How to run Seedance 2.0 product tutorial videos online?
You can run Seedance 2.0 product tutorial videos 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 your product photo, upload a presenter photo, write a timed review script, and hit run.

→ Launch Workflow, Free

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