Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Meta / Emu

Emu Video

Factorized text-to-video system that first generates an image, then conditions temporal diffusion on that image and text.

restrictedClosed weightsVideo generation
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
8 of 19 specification fields collected
Output resolution512 × 512See specification notes below
Clip durationAbout 4 seconds at 16 fpsSee specification notes below
Input billingNot collectedMeta · research reference
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2023-11-16Source for Release date (opens in a new tab)

Research disclosure date, not general API or weight availability.

Parameters
4.3B U-Net total reported in appendix; components rounded to 2.7B frozen spatial and 1.7B trainable temporalSource for Parameters (opens in a new tab)

Reported rounded components do not sum exactly. The count is not the entire multi-model pipeline plus all encoders.

Architecture
Image-conditioned diffusion with frozen spatial weights, learned temporal layers and a frame-interpolation modelSource for Architecture (opens in a new tab)
Languages
Not collected
Context caching
Not collected

No model-specific inference service or discounted prompt-cache contract is established for these research weights.

Video duration
About 4 seconds at 16 fpsSource for Video duration (opens in a new tab)
interpolation
16 generated frames become 65 interpolated frames, approximately 4.06 secondsSource for interpolation (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Meta · research reference

Provider source (opens in a new tab)
API model ID
Not collected

Descriptive catalog identity, not a verified selectable API ID.

Access
Paper and examples available. No original public checkpoint or callable inference contract verified.
Regions
Research deployment only; public availability and residency are not established

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

The cited research release does not supply a current production processing/retention agreement. Research access or an expired demonstration is not a production API entitlement.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Meta · research reference

Not verified

No published service cache policy for this research record.

How it works
Not collected

No published service cache policy for this research record.

Minimum reusable input
Not collected

No published service cache policy for this research record.

Lifetime & refresh
Not collected

No published service cache policy for this research record.

How to enable it
Not collected

No published service cache policy for this research record.

Usage fields
Not collected

No published service cache policy for this research record.

Billing rules
Not collected

No published service cache policy for this research record.

Limits & data boundaries
Not collected

No published service cache policy for this research record.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Original Meta research weights are not supplied by the reviewed release. The paper documents this named model or explicitly identified trained variant, while public artifacts provide research descriptions, examples or evaluation data rather than an original downloadable checkpoint. This record covers those unreleased research weights, not independently trained reimplementations or openly available base components.

Classification evidence (opens in a new tab)

Lifecycle dates

Research model disclosed16 Nov 2023Source (opens in a new tab)

Sources reviewed