Seedance 2.5
Seedance 2.5 generates 30-second cinematic clips with native audio and advanced reference control — built for long-form storytelling and professional workflows.
curl https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-5-image-to-video-basic",
"prompt": "Aerial drone shot over a misty mountain valley at golden hour"
}'
# Use the returned queue_id with https://api.venice.ai/api/v1/video/retrieve.
# Call /video/complete after downloading if needed.Overview
What is Seedance 2.5
Seedance 2.5 is ByteDance's next-generation AI video model that generates up to 30-second audio-video clips in a single take. It supports text-to-video, image-to-video, and reference-to-video modes, with native audio, lip sync, and strong character consistency, making it ideal for cinematic and commercial content.
Using it anonymously on Venice
On Venice, Seedance 2.5 runs with anonymized privacy — your prompts are never stored or profiled. This means you get full creative control over high-resolution, long-duration video without surveillance. Whether animating stills or building narrative scenes, your process stays private and permissionless.
Specifications
Datasheet
- Maker
- ByteDance
- Modality
- Text-to-video, image-to-video, reference-to-video
- Open weights
- No — proprietary
- License
- Proprietary
- Clip lengths
- 4s – 30s
- Resolutions
- 1080p, 720p, 480p
- Mode
- image-to-video
- Audio
- Yes
- Prompt limit
- 15,000 chars
- References
- Up to 50 assets — images, video, and audio
- Reference video
- 15 seconds total maximum
- Released
- July 31, 2026
- Privacy on Venice
- Anonymized — prompts not stored
- Available on Venice since
- Aug 2026
Assessment
Strengths and limitations
- Generates full 30-second clips in one take: no stitching, with smooth motion and strong continuity.
- Native audio generation including dialogue with accurate lip sync, music, and ambient sound.
- Supports up to 50 multimodal references (images, video, audio) for precise creative control.
- Strong character and product consistency across scenes — ideal for branding and storytelling.
- Available in multiple input modes: text-to-video, image-to-video, and reference-to-video.
- Not open source: cannot be self-hosted or fine-tuned due to proprietary licensing.
- Max resolution capped at 1080p on Venice, despite 4K capability in other deployments.
- No TEE or end-to-end encryption on Venice: privacy is anonymized but not sovereign-grade.
Use cases
What it is good for
- 01Creating 30-second ad spots with consistent branding and lip-synced voiceovers.
- 02Animating still product images into dynamic showcase videos.
- 03Developing narrative scenes using reference characters and environments.
- 04Producing social-first video content with native audio and motion.
- 05Prototyping cinematic sequences with precise camera and performance control.
Prompting
Getting better results
Use clear scene transitions in your prompt to guide continuity across 30 seconds.
Include dialogue in quotes to trigger accurate lip sync and voice generation.
Upload reference images of characters or products to maintain consistency.
For image-to-video, describe the desired motion explicitly (e.g., 'camera pans left').
Use multiple short reference videos to guide complex motion sequences.
Leverage white-model or greenscreen references for professional post-production workflows.
Samples
Sample outputs
Generated on Venice with our standard prompt suite — the same prompts we run through every model of this type, so you can judge it like-for-like.
Slow aerial drone shot gliding over a misty mountain valley at golden hour, sunlight piercing clouds onto a winding river, ancient pine forests on either side, ultra-smooth motion, professional color grading, atmospheric haze, 4K
Calm ocean waves rolling onto a black-sand beach at sunrise, golden light on wet sand, foam dissolving into the shore, a single silhouetted figure at the waterline, smooth continuous forward push, serene cinematic atmosphere
A slow tracking shot through a rain-soaked Tokyo street at night, neon reflecting in puddles, steam rising from a food cart, a person with a translucent umbrella, shallow depth of field, teal-and-orange grade, smooth steady camera
Alternatives
How it compares
| Model | Best for | Max duration | Max resolution | Native audio |
|---|---|---|---|---|
| Seedance 2.5 | 30s storytelling, reference control | 30s | 1080p | Yes |
| Grok Imagine 1.5 | Fast ideation, social clips | 15s | 1080p | Yes |
| Wan 2.7 Enhanced | Open weights, cost efficiency | 15s | 1080p | Yes |
| Vidu Q3 | High motion clarity | 16s | 1080p | Yes |
Choose Seedance 2.5 when you need full 30-second scenes with native audio, lip sync, and reference-based consistency — unmatched for cinematic storytelling and professional video production on Venice.
API
Call it from your code
Venice exposes this model through the REST API. Queue a generation with the model id.
curl https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-5-image-to-video-basic",
"prompt": "Aerial drone shot over a misty mountain valley at golden hour"
}'
# Use the returned queue_id with https://api.venice.ai/api/v1/video/retrieve.
# Call /video/complete after downloading if needed.Pricing
What it costs on Venice
Pay per clip on Venice — price scales with resolution and duration (4s–30s), from $0.51.
New Venice accounts include a free daily allowance and 500 welcome credits — no credit card required.
FAQ
Frequently asked questions
Seedance 2.5 is ByteDance's advanced AI video model that generates up to 30-second audio-video clips in a single take. It supports text-to-video, image-to-video, and reference-to-video modes, with native audio, lip sync, and strong character consistency for cinematic and commercial use.
On Venice, pricing starts at $0.51 per clip for 480p at 4 seconds, scaling with resolution and duration. A 1080p 4-second clip costs $2.05. You pay per generation with no subscription required.
No. Seedance 2.5 is a proprietary model developed by ByteDance. It is not open source, so it cannot be self-hosted or fine-tuned. Access is via API or platform integration, including on Venice.
No. Seedance 2.5 does not support external tool use or live web search. It generates video based solely on the input prompt and provided reference materials.
Seedance 2.5 supports 1080p, 720p, and 480p resolutions on Venice. While higher resolutions like 4K are possible in other deployments, Venice currently caps output at 1080p.
Yes. The variant 'seedance-2-5-image-to-video-basic' allows you to animate a still image into motion, with durations from 4 to 30 seconds and support for native audio generation.
Seedance 2.5 is better for long-form storytelling with 30-second clips, reference control, and lip sync. Grok Imagine 1.5 is faster for short social clips but limited to 15 seconds and lacks advanced referencing.
Use Seedance 2.5 anonymously
Venice does not store your prompts. Chat history stays in your browser.