ELYUMCREATE. EDIT. MOVE.ModelsPricingFAQSign inStart creating

Seedance 2.0AI video generator

Strong realism, 9 images and 3 clips — also edits clips. Pay only for the takes you keep — kill the rest for a full refund.

Text to videoImage to videoReference to videoVideo editingNative audio
Only on Elyum · Keep what you love. Unique keep/kill system with a full refund on kills.
Try Seedance 2.0 freeSee pricing150 free credits · no card required
Real Seedance 2.0 output, rendered on Elyum — untouched. Prompt: “Aerial drone shot: a turquoise ocean wave curls and breaks over black volcanic sand, white foam drawing swirling patterns, bright daylight.”
Developed by ByteDance
Max resolution1080P
Clip length4–15 seconds
Aspect ratios4 options
Best forcharacter-locked product films with audio

Seedance 2.0 is ByteDance's video model, launched February 12, 2026. It is known for strong realism, native audio generated with the picture, and mixed references — up to nine images and three clips in one generate. Clips run 4 to 15 seconds. On Elyum you use it as text to video, image to video, reference to video, and video editing.

Use it for product films, character-locked scenes, lip-synced ads, and edits of existing footage. One credit balance across 50+ models, from a Free plan with 150 starter credits up to Ultra, plus top-ups. Also runs from Claude, ChatGPT, and Cursor through Elyum's MCP server and REST API.

Seedance 2.0 pricing on Elyum

ResolutionCredits / second5s clip15s clip
480p86.420% off32 credits · $0.3296 credits · $0.96
720p201620% off80 credits · $0.80240 credits · $2.40
1080p302420% off120 credits · $1.20360 credits · $3.60

1 credit = $0.01. The struck-through number is the pre-cut rate — the discount is already in the live price. You only pay for takes you keep; previews and killed takes cost nothing. Full plan details on the pricing page.

Why Seedance 2.0 is good

Strong realism

Seedance 2.0 is known for photoreal motion and physical accuracy. Complex multi-subject action and camera moves hold for a full 4–15 second take, which is why it shows up in product and narrative work.

Nine images, three clips

Attach up to nine stills and three video clips as references in one generate. Lock a face, a product, a camera move, and existing footage, then describe how they combine.

Native audio

Sound and dialogue generate with the video, not as a second pass. ByteDance built a joint audio-video model, so speech, room tone, and effects land in the same take.

Text, image, reference, and edit

On Elyum the four routes are text to video, image to video, reference to video, and video editing. Four aspect ratios. Start from a prompt, a still, reference media, or an existing clip.

Character-locked references

Reference images keep facial features, clothing, and style through the generated clip. That is the usual path when a character or product has to look the same across takes.

Preview free, pay for keeps

Credits charge only when you keep a take. Kill the rest and they refund in full. Kept downloads are clean, full quality, and watermark-free.

Why generate with Elyum?

  • Pay only for what you keep — full refund on kills.
  • Every top video model in one place, one balance.
  • Rates ~20% under comparable platforms.
  • Kept files download clean and full quality — no watermark, commercial use included.
  • Works from the studio, or from Claude, ChatGPT and Cursor via MCP.
  • Free plan with 150 credits — no card required.

How it works

  1. Sign up free on Elyum. Previews cost nothing; the Free plan includes 150 starter credits.
  2. Open the video studio.
  3. Pick Seedance 2.0 from the model list.
  4. Write a prompt or attach images and clips (up to nine images and three clips). Set duration between 4 and 15 seconds.
  5. Generate a free preview, then keep the takes you want or kill the rest.

What people make with it

  • Product films and lifestyle shots with matching ambient sound
  • Lip-synced dialogue scenes and talking ads
  • Image-to-video from a product still, portrait, or key art
  • Edits of an existing clip: new action, new look, or a continuation
  • Reference-locked character or brand continuity across takes
  • Short multi-shot social and ad cuts with native sound

Frequently asked questions

Is Seedance 2.0 free to try?
Previews are free. The Free plan has 150 starter credits, and you only pay for the takes you keep. Kill the rest and those credits refund in full.
How much does Seedance 2.0 cost on Elyum?
Seedance 2.0 on Elyum is 6.4 credits per second at 480p (5s ≈ 32 credits / $0.32, 15s ≈ 96 credits / $0.96), 16 credits per second at 720p (5s ≈ 80 credits / $0.80, 15s ≈ 240 credits / $2.40), and 24 credits per second at 1080p (5s ≈ 120 credits / $1.20, 15s ≈ 360 credits / $3.60). 1 credit = $0.01. Credits are charged only when you keep a take.
Does Seedance 2.0 generate audio?
Yes. Seedance 2.0 generates native audio — sound and dialogue — with the video. Audio and picture are produced together, so speech and effects land in the same take.
What can I make with Seedance 2.0 on Elyum?
On Elyum, Seedance 2.0 is text to video, image to video, reference to video, and video editing, 4–15 seconds, with native audio. You can attach up to nine images and three clips as references. Four aspect ratios, at 480p, 720p, or 1080p.
Can I use Seedance 2.0 videos commercially?
Yes. Kept takes download clean and full quality, with no watermark and commercial use included. You only pay for the takes you keep.
Can Seedance 2.0 edit an existing video?
Yes. Video editing is one of the four routes on Elyum. Attach a clip, describe the change in plain language, and you get a 4–15 second take with native audio. Optional image or video refs can lock identity. Preview is free; credits charge only if you keep it.

More models to try

Seedance 2.5Sharpest realism, native audio, up to 30 references — also edits clipsfrom 40 creditsSeedance 2.0 FastQuick, cheap drafts of the Seedance look — also edits clipsfrom 24 creditsSeedance 2.0 MiniThe smallest Seedance: fastest and cheapest — also edits clipsfrom 24 creditsMiniMax H3Frontier realism from text or a starting imagefrom 26 creditsWan 3.0One take up to 30 s at 1080p, 10 images and 5 clips — also edits clipsfrom 13 creditsGemini Omni 1.1Omni's newer generation — up to 1080p, keeps faces and voices from referencesfrom 22 credits

Create everything. Keep the best.

Seedance 2.0 and 50+ other top models on one balance. Every render is a free preview — pay nothing for the rest.

Start creating free