Seedance 2.0
ByteDance's default AutorunX video engine for Short Film, Movie Maker, and Ad Remake — identity-preserving reference-to-video at up to 4K.
What Seedance 2.0 does
Seedance 2.0 produces 12-15 second video clips from a prompt, an image, an existing video, or a reference subject, and is ByteDance's most capable video model in the family for holding a specific look, subject, or identity consistent across a generation. It's the workhorse model behind most of AutorunX's default video generation, chosen as the default specifically because it balances quality, control, and cost across a wide range of shot types.
Beyond generating new clips from scratch, it can also edit or extend existing video through its V2V mode, and preserve a specific subject's identity across reference-driven generations — useful whenever a shot needs to feature a particular person, character, or product consistently.
Capabilities
Key features
- Identity-preserving reference-to-video
- The 2.0 Identity variant conditions generation on a reference subject and keeps that subject's face and distinguishing features consistent in the output, rather than using the reference only as loose stylistic guidance.
- Multiple quality/speed tiers
- The Fast variants (1.0 Fast, 2.0 Fast) trade some fidelity for speed and lower cost, while 1.5 Pro and 2.0 target maximum quality — letting a workflow use fast passes for iteration and the higher tier for the final render.
- Video-to-video editing
- Seedance 2.0 can take an existing video clip as input and modify it, rather than only generating from a blank prompt — useful for adjusting a shot you've already produced.
- Subject-to-video (S2V)
- The 2.0 reference mode drives generation from a subject reference, keeping that subject's appearance consistent through the output — a distinct mode from general image-to-video.
- 4K-capable output
- Resolution scales from 480p up to 4K depending on the request, covering both quick draft passes and final, display-ready renders from the same model family.
How Seedance 2.0 works
Seedance 2.0 is ByteDance's professional-tier video generation model, built to take multimodal inputs — text, a reference image, an existing video clip, or a reference subject — and produce a coherent 12-15 second clip from them. The 2.0 Identity variant is tuned specifically for reference-to-video generation that preserves a subject's identity (face, build, distinguishing features) across the output, rather than treating the reference as loose stylistic guidance.
The model family spans several variants tuned for different trade-offs: 1.0 Fast and 2.0 Fast prioritize speed and lower cost per clip, 1.5 Pro and 2.0 target higher fidelity and stronger prompt adherence, and 2.0 Identity adds the identity-preservation behavior for reference-to-video and subject-to-video (S2V) work. This lets a single family cover both quick iteration passes and final, production-quality renders.
Resolution scales from 480p up to 4K depending on the request and variant, and beyond straight text-to-video and image-to-video, Seedance 2.0 supports video-to-video (V2V) editing of an existing clip and subject-to-video generation, where a reference subject drives the appearance of the generated output.
What people use Seedance 2.0 for
Default engine for Short Film and Movie Maker
Generate narrative shots and scenes end to end, using Seedance 2.0 as the default model for both single-shot Short Film generations and multi-scene Movie Maker projects.
Ad Remake with identity-preserving reference
Recreate or restyle an ad concept while keeping the featured person or product recognizable, using the 2.0 Identity variant's reference-to-video mode.
Editing existing footage
Use V2V mode to modify a clip that's already been generated or captured, rather than starting a fresh generation from a prompt.
Fast iteration before a final render
Use a Fast variant to block out a shot quickly, then switch to 1.5 Pro or 2.0 for the final, higher-fidelity pass.
How to use Seedance 2.0 on AutorunX
Seedance 2.0 is the default model for Short Film, in the Video module.
- 01
Open Short Film, Movie Maker, or Ad Remake in Video
From the AutorunX dashboard, go to Video and open Short Film, AI Movie Maker, or Ad Remake — Seedance 2.0 is the default model in all three.
- 02
Set up your input
Write your prompt, attach a reference image or subject, or upload an existing clip if you're using video-to-video editing.
- 03
Confirm Seedance 2.0 in the model picker
Seedance 2.0 (or the Fast/Identity variant appropriate to your service) is pre-selected by default. Open the model picker to confirm, or switch variants for a speed/quality trade-off.
- 04
Generate and review
Hit generate to render a 12-15 second clip. Chain shots together in Movie Maker, or iterate on the same reference for a consistent Ad Remake sequence.
- Billed per second of generated video from your shared AutorunX credit wallet.
- 162 credits / sec (Fast, Short Film/Movie Maker default) · 200 credits / sec (2.0/Identity, Ad Remake/Sync Motion default)
Tips for better results
- Use Identity mode when a specific subject must recur
- Reach for the 2.0 Identity variant whenever a shot needs to feature the same recognizable person or character rather than a generic figure matching the prompt.
- Iterate on Fast, finalize on Pro or 2.0
- Block out composition and timing on a Fast variant first, then re-run the finished prompt on 1.5 Pro or 2.0 for the version you'll actually publish.
- Feed V2V a clean source clip
- Video-to-video edits work best starting from a clip with stable framing and lighting — heavy artifacts or motion blur in the source carry through to the edit.
- Match resolution to the shot's purpose
- Request lower resolution for quick drafts and reserve the 4K tier for hero shots or footage headed to a large display, since higher resolution costs more per clip.
Seedance 2.0 — frequently asked
Related models
OmniHuman 1.5
ByteDanceByteDance's audio-driven human video model that animates a photo to speak and move in sync with a given audio track.
Kling 3.0
Kuaishou TechnologyKuaishou's flagship video model with native multi-lingual audio, in-video editing, and clips up to native 4K.
Wan
AutorunX ownedAlibaba's open Wan model family, run two ways on AutorunX: self-hosted Wan 2.2 for cost-efficient generation, and cloud Wan 3.0 for up to 30-second clips.
Ready to create with Seedance 2.0?
Open Short Film and generate your first video in a couple of minutes.
Free plan, no card required.