Seedance 2.5 UGC Fashion Video · R2V

ABOUT THE WORKFLOW

Generate a Fashion Video from Two Photos
Upload a product photo and a model photo. Write a prompt describing the scene, camera angles, and shot timing. Seedance 2.5 generates a vertical video with the product on the model and ambient audio included.

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 2.5 by ByteDance. Strong at preserving identity from reference images, natural camera movement, and multi-shot commercial storytelling. Generates synced audio in the same pass.

HOW IT WORKS

Step 1. Upload a product photo
The item to feature: a bag, shoes, jewelry, clothing, or any accessory. A clean, well-lit shot with the product clearly visible works best.
Works great with: bags · shoes · accessories · clothing

Step 2. Upload a model photo
The person who will appear in the video. Face, body, hair, and outfit carry into the generated result.

Step 3. Write your prompt
Describe the full video shot by shot. Include outfit details, setting, camera angles, and timing for each shot. Example: "0-2s: close-up of bag strap, gold clasp catches light. 2-4s: medium shot, model walks past brick wall with bag on shoulder."

Step 4. Hit run and download
Seedance 2.5 generates the video using both photos as visual anchors. The output includes generated ambient audio.
Ready for: Instagram Reels · TikTok · YouTube Shorts · any editor

First time? Leave every setting as-is. The defaults (720p · 8s · 9:16 · 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 fashion video (most people) — 720p · 8s · 9:16 · audio on · random seed. The right starting point for almost everyone.

• Want a longer video with more shots — Increase duration. Longer clips cost more per run. Scale your prompt to fill the extra time with distinct shots.

• Want a horizontal video — Switch the aspect ratio to 16:9. Adjust your prompt to describe wider framing.

• Want to reproduce a result you liked — Lock the seed to the number from your previous run. Keep the prompt identical.

• The product does not appear correctly — Use a clean product photo on a plain background. Describe the product in the prompt with specific details: color, material, shape, and where on the model it appears.

• The model does not match the reference — Use a clear, well-lit photo with the full face visible. Describe outfit and appearance details in the prompt to reinforce the reference.

Prompt: Describe each shot with timing, camera angle, and action. "0-2s: top-down shot, model adjusts bag strap, silver rings catch light" gives more control than "model shows off bag." Keep outfit and accessory details consistent across all shots.

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

👜 Fashion & Accessories Brands
Upload a product shot and a model photo to create short social videos for bags, shoes, jewelry, or clothing without booking a shoot.

📱 Social Media Content Creators
Generate vertical fashion reels from still photos. Write a shot list, hit run, and post the result to TikTok or Instagram.

🛍️ E-Commerce Product Pages
Turn flat product images into styled video content that shows the item on a person in motion, replacing static lookbook photos.

🎨 Mood Board to Motion
Use reference photos from a mood board as inputs. Describe the scene and get a video that matches the visual direction before committing to a full production.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Clean product photos with the item clearly visible

• Model photos with the full face and body visible

• Shot-by-shot prompts with timing and camera angles

• Consistent outfit and accessory details across all shots

⚠️ May produce softer results

• Busy or cluttered product photos

• Model photos with heavy filters or occlusions (sunglasses, hats covering face)

• Vague prompts without timing or camera direction

• Prompts that change the model's outfit between shots without a clear transition

FAQ

What is Seedance 2.5 and why is it good for fashion video?
Seedance 2.5 is a video model by ByteDance. It takes up to 30 reference images and generates video up to 1080p with synced audio. It preserves the identity and appearance of people and products from the reference photos, which makes it strong for fashion content where the model and product need to look consistent across multiple shots.

How does the model use both photos as references?
The product photo and the model photo are passed as separate reference images. Seedance 2.5 uses both as visual anchors when generating the video. Your prompt tells the model how to combine them: where the product appears, what the model is wearing, and how the scene plays out shot by shot.

What resolution and aspect ratio does this workflow support?
The default is 720p at 9:16 (vertical). You can change the aspect ratio to 16:9 for horizontal or 1:1 for square. Resolution options include 720p and 1080p. Vertical 9:16 is the most common format for fashion reels on TikTok and Instagram.

Can I add more than two reference images?
Seedance 2.5 supports up to 30 reference images. This workflow uses two inputs (product and model), but the underlying node accepts more. If you need additional references, such as a background photo or a second product, you can modify the workflow to connect extra image inputs.

Does the output include sound?
Yes. Audio generation is on by default. Seedance 2.5 generates ambient sound in the same pass as the video. The output file includes the audio track. You can turn audio off in the settings if you plan to add your own music or voiceover.

Can I use the output commercially?
Seedance 2.5 is a proprietary ByteDance model. Commercial use of the outputs is generally allowed, but review ByteDance's current terms for your specific use case. Make sure you have the rights to any product and model photos you upload.

How to run Seedance 2.5 fashion videos online?
You can run Seedance 2.5 fashion 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 a product photo and a model photo, describe the scene, and hit run.

→ Launch Workflow, Free

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