Seedance 2.0 Mini · Text to Video

ABOUT THE WORKFLOW

Generate a Video from Text
Write a prompt describing the scene, action, camera movement, and sound. Seedance 2.0 Mini generates a 5-second video with native audio in a single pass. Seedance 2.0 Mini is the lightweight, lower-cost variant of ByteDance's top-ranked video model, built for fast iteration and high-volume generation.

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 Mini by ByteDance (SEED Lab). The lightweight variant of the #1-ranked video model on the Artificial Analysis Video Arena. Generates synchronized audio and video in one pass, supports 16:9, 9:16, and 1:1 aspect ratios, and runs at lower cost than the full Seedance 2.0 model.

HOW IT WORKS

Step 1. Write your prompt
Describe the full scene: subject, action, camera movement, lighting, mood, and sound. "A golden retriever runs through a sunlit meadow toward the camera, wildflowers swaying, bees buzzing, warm afternoon light, shallow depth of field" gives the model clear direction.
Works great with: cinematic scenes · nature footage · character action · product reveals · social content

Step 2. Set duration and aspect ratio
Duration defaults to 5 seconds. Aspect ratio defaults to 16:9 widescreen. Switch to 9:16 for vertical or 1:1 for square.

Step 3. Hit run and download
Seedance 2.0 Mini generates the video with synchronized audio and returns an MP4 at 30fps.
Ready for: Premiere · DaVinci Resolve · After Effects · TikTok · Instagram · YouTube

First time? Write a detailed prompt and hit run. Leave duration, aspect ratio, and audio settings as-is.

RECOMMENDED SETTINGS

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

• Standard video from text — 720p, 5 seconds, 16:9, audio on. Write your prompt and run.

• Vertical for social media — Switch aspect ratio to 9:16. Native portrait output for TikTok, Reels, and Shorts.

• Square for social — Switch aspect ratio to 1:1 for Instagram feed posts and multi-platform content.

• Turn audio off — Set generate_audio to False if you want a silent video or plan to add your own audio in post.

• Reproduce a result — Set the seed to a fixed number. Keep it locked to get the same video. Change it for a different interpretation of the same prompt.

• More cinematic output — Use camera terms in the prompt: "slow dolly push-in," "tracking shot at shoulder height," "low-angle crane rising." The model follows cinematic direction.

• Audio not matching the scene — Add explicit sound descriptions in the prompt. "Waves crashing, seagulls calling, wind in the grass" steers the generated audio toward the right environment.

Prompt: Structure it as subject, action, camera, lighting, then sound. "A lone hiker crests a mountain ridge at golden hour, camera slowly pulls back to reveal the full valley below, wind sound, distant eagle cry" is specific and sequenced. "Person on a mountain" gives the model nothing to work with.

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

⚡ Rapid Video Iteration
Test prompt ideas, visual directions, and scene concepts quickly at lower cost before running the full Seedance 2.0 model for final output.

📱 Social Media Video Content
Produce scroll-stopping vertical or widescreen clips with native audio for TikTok, Reels, and Shorts from a single prompt.

🎬 Concept and Storyboard Videos
Generate moving scene concepts and animatics with synchronized sound to test pacing and camera work before production.

📺 Ad and Marketing Drafts
Draft video concepts for campaigns, product reveals, and explainer content without filming or stock footage.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Detailed prompts with subject, action, camera, lighting, and sound

• Cinematic camera terms (dolly, tracking, pan, crane, orbit)

• Sound descriptions written directly in the prompt

• Moderate action with clear subjects and defined environments

⚠️ May produce softer results

• Very short prompts with no camera or motion direction

• Extremely complex multi-character choreography

• Prompts with no sound or atmosphere description

• Expecting the same output quality as the full Seedance 2.0 model (Mini trades peak quality for cost)

FAQ

What is Seedance 2.0 Mini?
Seedance 2.0 Mini is the lightweight, lower-cost variant of ByteDance's Seedance 2.0 video model. It shares the same multimodal audio-visual architecture as the full model and generates synchronized video and audio in a single pass. It is built for rapid iteration, high-volume generation, and use cases where cost matters more than maximum quality.

How does Seedance 2.0 Mini compare to full Seedance 2.0?
The full Seedance 2.0 model produces higher-quality output with stronger character consistency, more detailed motion, and better audio sync. Seedance 2.0 Mini trades some of that quality for significantly lower generation cost. Use Mini for rapid exploration and high-volume workflows. Use full Seedance 2.0 for final production output.

Does Seedance 2.0 Mini generate audio?
Yes. Audio is generated natively alongside the video. The model produces ambient sound, sound effects, and music synchronized to the on-screen action. Describe the sounds you want in the prompt and they generate in the same pass as the video. Set generate_audio to False to produce a silent clip.

What resolution and duration does this workflow support?
720p at 5 seconds with 16:9, 9:16, or 1:1 aspect ratio. Duration is fixed at 5 seconds for the Mini variant.

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

Is Seedance 2.0 Mini licensed for commercial use?
Seedance 2.0 Mini is a proprietary ByteDance model. Commercial use is governed by ByteDance's terms of service. Review the current terms for your specific use case.

How to run Seedance 2.0 Mini text to video online?
You can run Seedance 2.0 Mini text to video online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, write your 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 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?
Write your scene description and hit run.

→ Launch Workflow, Free

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