Seedance 1.0 Pro (closed weights)
ByteDance's commercial video generation model, available in Pro, Pro Fast and Lite tiers via API.
- Up to
- 12 seconds
- Resolution
- 1080p
- Weights
- Not released
- API
- Yes
- Commercial use
- Vendor states commercial use is permitted
It supports text-to-video and image-to-video at 480p, 720p and 1080p, 24 fps, with clip durations from 2 to 12 seconds. Despite frequent listing in 'open source video model' roundups, no Seedance weights have ever been published.
There is no model license because there is no weight release; use is governed by BytePlus/Volcano Engine commercial terms of service.
Specification
- What it takes in
- text, image
- What it makes
- video
- Maximum duration
- 12 seconds
- Maximum resolution
- 1080p
- Aspect ratios
- not established
- Controls
- text prompt, reference image, duration selection (2-12s), resolution tier, aspect ratio, camera-motion prompting, multi-shot prompting
- Weights
- Not released
- API
- Yes
- Pricing
- Closed, paid API only. Priced per generated token via BytePlus ModelArk / Volcano Engine (documented at $0.0025 per 1,000 tokens at the time of checking). No self-hosting option exists because no weights are published, so there are no VRAM requirements to state.
- Released or updated
- 2025-06-11
Supported aspect ratios is not established here. That means no page we could retrieve stated it, not that the model lacks one.
Strengths
- Strong motion and multi-shot narrative quality
- Documented 2-12 second range and 1080p output
- Cheap per-second pricing relative to Western competitors
- First-party API with clear docs
Weaknesses
- No weights, no self-hosting, no fine-tuning
- No license to audit; terms can change unilaterally
- Frequently and wrongly listed as open source, which creates procurement risk
- Regional availability and content policy constraints
Best for
- Teams that want low-cost high-quality hosted generation and do not need weights; included here specifically to document that it is not open.
Where the sources disagree
Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.
- Numerous SEO blogs imply Seedance weights are downloadable. Verified against ByteDance's own Hugging Face org: no Seedance video weights exist. The 2-12 second and 480p/720p/1080p specs come from BytePlus ModelArk docs and third-party comparison pages; per-tier caps may differ between Pro, Pro Fast and Lite.
What to understand before using it
Explainers naming the mechanisms this model's own documentation mentions.
How to prompt it
Written for Seedance 1.0 Pro (closed weights). See prompt craft for the full vocabulary and cinematic language for the lens, light and mood tables.
-
Seedance 1.5 Pro
Cheap clean single-take shots without cuts; the exact model for the 2D sprite animation pipeline.
For sprites: fixed 4 s, 720p, aspect ratio equal to the key pose and passed explicitly on every call, start frame always, end frame only for loops, one action in the positive prompt plus the mandatory camera/prop/facing negative block. "Do not silently substitute a model."
MCP servers that front ByteDance
Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.
-
370.ai, AI Gateway: Video (Seedance 2.0, Wan, HappyHorse), Image, Speech + 100+ Chat Models
One key, 100+ models, chat with any LLM and generate video, images, speech. Free trial at 370.ai.
-
Adclip
Ad creative generation via MCP, copy and static images from a JSON brief. Keyless.
-
Aetherwave
Music, image, video and audio generation across top AI providers - one key, one credit pool.
-
ArkRoute, Visual AI API Gateway
Generate images and videos using 28+ visual AI models from OpenAI (GPT Image 2, DALL-E 3), Google (Imagen 4, Veo 3.1), ByteDance (Seedream, Seedance 2.0), and Kuaishou (K
-
Avocado AI
Generate AI images, videos, music, SFX & speech in any AI assistant. Results appear inline in chat.
-
BananaBanana Image & Video Generation
Generate images & video (Nano Banana, Veo, Omni) pay-as-you-go. No subscription, crypto payments.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
ByteDance Seedance 2.0
Seedance 2.0 is ByteDance Seed's unified multimodal audio-video model: a single generation pass accepts text plus mixed references (up to 9 images, 3
Video generation
Adobe Firefly Video Model
The Adobe Firefly Video Model generates video from a text prompt, optionally guided by an image used as the first or final frame. Adobe's Firefly Serv
Video generation
Allegro
A small text-to-video model comprising a 2.8B VideoDiT and a 175M VideoVAE, released under Apache-2.0 in October 2024. It generates 88-frame clips at
Video generation