← All models
DeepMind
New
3.5
800 cr
Google DeepMindimage → videoNEW

Veo 3.1 · Reference

Photo as reference — native, 1080p + audio

Google DeepMind Veo 3.1 reference-to-video. Up to 3 reference images guide identity/style, 1080p with synchronized audio. Fixed 8-second clip, 16:9 or 9:16.

Price
800 cr
Avg latency
~200s
Tier
premium
fal.ai model id
fal-ai/veo3.1/reference-to-video

What Veo 3.1 · Reference is built for

Veo 3.1 · Reference by Google DeepMind is a premium-tier image to video model used to animate a still image into motion.

Inside Lumineer AI, Veo 3.1 · Reference runs on the same unified credit balance as every other model — no per-vendor billing, no API keys to manage. One generation costs 800 credits and completes in roughly 200 seconds.

Teams pick Veo 3.1 · Reference for product motion, portrait animation, still-to-reel and similar use cases where Google DeepMind's aesthetic bar is non-negotiable. Failed generations are refunded automatically, and every output is stored in your private Library.

Sample output

Official Veo 3 demo · video

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

Veo 3
video

Specs

Technical characteristics of Veo 3.1 · Reference as it runs inside Lumineer.

VendorGoogle DeepMind
Categoryimage → video
Tierpremium
Price per run800 credits (~$6.40)
Typical latency~200s
Aspect ratios16:9 · 9:16
Resolutions720p · 1080p
Referencesmulti
Seed controlNo
Negative promptNo
API accessREST via Lumineer (no fal.ai key required)

Related models