Seedance v1.0 Lite Text-to-Video
Seedance v1.0 Lite Text-to-Video is a cost-optimized text-to-video (T2V) generation model that produces 720p or 1080p clips up to 12 seconds from natural language prompts. It's built for iterative creative workflows and high-throughput generation pipelines.
import { experimental_generateVideo as generateVideo } from 'ai';
const result = await generateVideo({ model: 'bytedance/seedance-v1.0-lite-t2v', prompt: 'A serene mountain lake at sunrise.'});Playground
Try out Seedance v1.0 Lite Text-to-Video by ByteDance. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
More models by ByteDance
| Model |
|---|
| — | — |  | 04/14/2026 | ||||||||||
| — | — | | 04/14/2026 | ||||||||||
| 256K | 1.2s | 146tps | $0.25/M | $2.00/M | Read: $0.05/M Write: — | — | — | | 09/01/2025 | ||||
| 256K | 1.2s | 121tps | $0.25/M | $2.00/M | Read: $0.05/M Write: — | — | — | | 09/01/2025 | ||||
| — | — | | 06/11/2025 | ||||||||||
| — | — | | 06/01/2025 |
About Seedance v1.0 Lite Text-to-Video
Seedance v1.0 Lite Text-to-Video is the text-to-video entry point in the Seedance 1.0 family. It generates video from written descriptions without a reference image. The Lite tier prioritizes generation speed and per-clip cost. It's a practical starting point for ideation, concept validation, and large-scale automated content pipelines where volume matters more than peak visual quality.
Seedance v1.0 Lite Text-to-Video shares Seedance 1.0's unified pre-training framework, which handles T2V, I2V, and text-to-image through one architecture using binary masks to differentiate task types. Prompt-following fidelity, motion stability, and multi-shot transition support are present in the Lite tier, not exclusive to Pro. The Seedance 1.0 tech report notes first-place ranking on Artificial Analysis T2V leaderboard evaluations. Output resolution options are 720p and 1080p at 24 fps, with durations from two to 12 seconds and aspect ratios spanning 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and 9:21.
See https://console.byteplus.com/ark/region:ark+ap-southeast-1/model/detail?Id=seedance-1-0-lite-t2v for methodology and benchmark context.
For creative teams, the Lite T2V tier suits storyboarding sessions where you evaluate many prompt variations quickly. For product and engineering teams, it offers a lower-cost path to integrating video generation into application workflows before you graduate to Pro-tier renders for final delivery.
What To Consider When Choosing a Provider
- Configuration: Lite-tier generation suits batch workflows, but you should still check provider rate limits and concurrent task caps before you design high-throughput pipelines. Compare rates (N/A; N/A).
- Zero Data Retention: AI Gateway does not currently support Zero Data Retention for this model. See the documentation for models that support ZDR.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Seedance v1.0 Lite Text-to-Video
Best For
- Storyboarding and concept validation: Review multiple prompt variations before committing to a final production render
- High-scale content pipelines: Social media scheduling tools or dynamic ad generation where cost per clip is a primary constraint
- Rapid prototyping: Lite provides a lower-cost development target for video-generative features within an application
- Short-form social content: 9:16 portrait orientation at 720p resolution meets platform delivery requirements
Consider Alternatives When
- Final delivery quality: Seedance 1.0 Pro T2V delivers higher motion fidelity and advanced directorial controls
- Reference-anchored prompts: Use an I2V variant when a specific reference image should anchor the video's subject
- Maximum speed with pro quality: Seedance 1.0 Pro Fast provides Pro-comparable quality at higher generation speed
Conclusion
Seedance v1.0 Lite Text-to-Video gives you a text-driven path into Seedance 1.0's video generation stack at a cost suited to high-iteration workflows. It shares an architecture with Pro-tier variants, so prompt engineering and content strategy you develop at the Lite tier transfer directly when projects need a higher-quality final render.
Frequently Asked Questions
What makes the Lite tier different from the Pro tier for text-to-video generation?
Lite optimizes for lower cost and faster generation, suited to iteration and batch workflows. Pro adds higher motion fidelity and more advanced motion controls for final-delivery assets.
Does Seedance v1.0 Lite Text-to-Video support landscape and portrait video formats?
Yes. The model supports seven aspect ratios including 16:9 (landscape), 9:16 (portrait), 1:1 (square), 4:3, 3:4, 21:9, and 9:21, covering most social media and web display contexts.
How long can generated videos be?
Clips range from two to 12 seconds at 24 fps and up to 1080p resolution.
Does the Lite T2V model support multi-shot transitions?
Yes. Seedance 1.0's unified architecture generates multi-shot transitions with wide, medium, and close-up cinematography natively. This applies across both Lite and Pro variants.
Can I use this model without any reference image?
Yes, T2V (text-to-video) means the video is generated entirely from a text prompt, with no image input required.
How does AI Gateway simplify access to Seedance v1.0 Lite Text-to-Video?
AI Gateway routes requests using an API key or OIDC token. You don't need a separate ByteDance or Volcano Engine account. AI Gateway handles authentication and provider selection on your behalf.