Skip to content
AIBRAINWORX / OpenSourceCoder.comLOCAL-FIRST. BUILT IN THE OPEN.

SOURCE-REVIEWED MODEL PROFILE

Invoker-Render 1.0

Causal proxy-conditioned streaming video renderer built on MiniMax-H3; requires a structural proxy, reference image and text.

inclusionAI / Code World Model 2.0

Metadata reviewed 2026-11-21 · Original creator: inclusionAI / Code World Model 2.0

PARAMETERS33.12B (publisher card)
CONTEXTBounded recent video history, not a text context specification
LICENSEApache-2.0 and CC BY-NC 4.0; non-commercial terms apply
MODALITYVideo, image and text to video

What it does

  • Four-step causal chunks
  • Structural proxy control
  • Separate inference code

Local fit

Default production profile: eight NVIDIA GPUs on one node. About132.5GB FP32 weights plus separate matching assets. Not tested on a desktop or12GB GPU.

24 FPS is the input timeline; not measured generation throughput.

Evidence and limits

Source reviewed; no installation, generation or benchmark.

Source reviewed

License and source

Card declares combined Apache-2.0 and CC BY-NC4.0 terms; original code and bundled components have separate licenses. No standalone LICENSE file found in the model repository.

Read the original model card ↗

Reviewed source revision: 2314c6b89c12eef07285fedd22ab6f1b519a5866

Pass the signal.