← All models
ByteDance
Top pick
4.8
378 cr
ByteDanceimage → videoNEW

Seedance 2.0 · Reference

Photo as reference — native

ByteDance Seedance 2.0 reference-to-video. Your uploaded photos are treated as visual REFERENCES (face, subject, style) — the video does NOT start on them. Upload up to 9 images and describe any scene; the model keeps your subject consistent throughout. Generates native audio with the picture — dialogue, ambience and synced effects.

Price
378 cr
Avg latency
~150s
Tier
premium
fal.ai model id
bytedance/seedance-2.0/reference-to-video

What Seedance 2.0 · Reference is built for

Seedance 2.0 · Reference by ByteDance is a premium-tier image to video model used to animate a still image into motion.

Inside Lumineer AI, Seedance 2.0 · Reference runs on the same unified credit balance as every other model — no per-vendor billing, no API keys to manage. One generation costs 378 credits and completes in roughly 150 seconds.

Teams pick Seedance 2.0 · Reference for product motion, portrait animation, still-to-reel and similar use cases where ByteDance's aesthetic bar is non-negotiable. Failed generations are refunded automatically, and every output is stored in your private Library.

Sample output

Official Seedance Reference demo · video

Reference rendering shipped by ByteDance — same endpoint you'll run inside Lumineer.

Seedance Reference
video

Specs

Technical characteristics of Seedance 2.0 · Reference as it runs inside Lumineer.

VendorByteDance
Categoryimage → video
Tierpremium
Price per run378 credits (~$3.02)
Typical latency~150s
Aspect ratios16:9 · 9:16 · 1:1
Resolutions1080p · 720p · 480p · 4k
Durations5s · 8s · 10s · 15s
Referencesmulti
Seed controlNo
Negative promptNo
API accessREST via Lumineer (no fal.ai key required)

Related models