A
ANT GROUP / inclusionAI/invoker-render-1.0

Invoker-Render 1.0

Causal renderer for Code World Model 2.0 with 33.12 billion parameters. Its weights were published on November 16. It converts structural proxies, an appearance reference and text into video, while another engine maintains world state.

01 / SUMMARY

The essential

ORIENTATIONProxy-controlled video rendering

Primary use stated or inferred cautiously from official documentation.

CONTEXT1344 × 768 RGB image, 24 fps proxy video and text

Maximum input capacity when published by the source.

EXITStreaming video; file inference with 17 × N + 5 frames, minimum 39

Documented maximum generation limit.

ACCESSHugging Face · downloadable checkpoint

Verified availability channels.

MODEL TYPEVideo

Primary functional family and verified specialties.

LICENSEApache-2.0 + CC BY-NC 4.0 · non-commercial

Declared terms for API access, model weights, or self-hosting.

02 / TECHNICAL SHEET

Limits and integration

API IDinclusionAI/invoker-render-1.0
Model typeVideo
Access modelDownloadable weights
LicenseApache-2.0 + CC BY-NC 4.0 · non-commercial
DeploymentSelf-hosted
Release16 NOV 2026
Knowledge cutoffNot published
EntranceText · Image · Video
ExitVideo
Context window1344 × 768 RGB image, 24 fps proxy video and text
maximum outputStreaming video; file inference with 17 × N + 5 frames, minimum 39
ReasoningNot published
Published tools
Structured OutingsNot published
Batch processingNot published
Prompt cacheNot published
Fine-tuningNot published
Verified platformsHugging Face
BEST SUITED FOR

Research generation controlled by camera, geometry and motion. The model maintains a visual reference and a bounded history window. The project includes a WebSocket service and file and browser clients.

WORTH MONITORING

Use is subject to non-commercial terms. The 24 fps describe the timeline, not inference speed. The production profile uses eight NVIDIA GPUs; the main FP32 weights occupy about 132.5 GB. The world engine and proxies are external components.

03 / CAPABILITIES

What it can do

01

Orientation

Research generation controlled by camera, geometry and motion. The model maintains a visual reference and a bounded history window. The project includes a WebSocket service and file and browser clients.

02

Context

1344 × 768 RGB image, 24 fps proxy video and text · Streaming video; file inference with 17 × N + 5 frames, minimum 39

03

Tools and integration

Not published

04

Access

Hugging Face · downloadable checkpoint

Input modalities
TextImageVideo
04 / PRICES

Documented cost

ConceptWorthUnit/condition
Standard inputNo published official API rateStandard API rate
Cached inputNot publishedReading reused prefixes
Cache write or storageNot publishedThe condition varies by provider
Standard outputSelf-hosted infrastructure costMay include reasoning tokens
Batch inputNot publishedAsynchronous processing
Batch outputNot publishedAsynchronous processing

The card states Apache-2.0 together with CC BY-NC 4.0; retain the non-commercial restriction. No official API tariff is verified. Self-hosting costs include GPUs, memory, proxy generation and storage.

i Prices change and may depend on level, region or context length. Check the source before making a decision.

05 / EVALUATIONS

How to read the results

“

The card describes the input contract and four-step causal streaming. No comparable numeric benchmark is verified for this checkpoint. Session continuity does not prove real-time speed or unlimited stability.

i We have not found published benchmarks for this model.

Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.

06 / VERSIONS

Chronology

inclusionAI/invoker-render-1.0

Weights published on the 16th; contract and license verified in the November 18 revision.

07 / SOURCES

Traceability