---
title: "Krea Realtime Video 14B"
description: "Krea Realtime Video 14B from Krea AI: realtime-video-generation and text-to-video; Runner parity pending."
modelId: "krea-realtime-video"
pageSource: generated
---

Krea Realtime Video 14B is Krea AI's open realtime/streaming video generation model. Unlike the batch T2V models in this catalog, it targets low-latency streaming generation: text-to-video and video-to-video in a streaming regime. The in-tree runtime lives under synthesis/visual_generation/krea_realtime, and the route exposes num_blocks, resolution, fps, and seed controls. Alias krea-rt-14b resolves here.

<ModelPaperFigures modelId="krea-realtime-video" locale="en" />

Project page: [krea.ai](https://www.krea.ai/). Code: [krea-ai/realtime-video](https://github.com/krea-ai/realtime-video).

<ModelCommandBuilder modelId="krea-realtime-video" locale="en" />

## What it is for

Use `krea-realtime-video` for catalog text-to-video inference. The recipe exists so you can launch a recorded T2V profile without assembling an upstream demo.

Upstream describes it as a 14B autoregressive/streaming video model distilled for realtime block-wise generation (weights at krea/krea-realtime-video, apache-2.0). This repository records the block-based generation controls (num_blocks) and the prompt/video input contract; deeper internals are not recorded here.

Catalog tasks include realtime-video-generation, text-to-video, video-to-video, and streaming-video. Catalog aliases include `krea-rt-14b`. Documented modalities: text and video in, video out.

Recorded evaluation entry points include [VBench](/docs/evaluation/benchmark-hub/vbench) (Baseline quality check for streaming T2V output).

## Runtime contract

Optional `prompt`, `negative_prompt`, `frames`, `fps`, and `height`; artifacts `krea-realtime-video.mp4`.

CLI task profiles: `interactive-video`. WorldFoundry binds `KreaRealtimeVideoPipeline`.

Family status: **Runner parity pending**.

Recorded `interactive-video` defaults: fps=16, height=480, width=832, seed=42.

Realtime throughput expectations depend heavily on your GPU — the 14B scale wants datacenter-class hardware for true realtime rates.

## Running in WorldFoundry

The catalog launch is `worldfoundry-eval run krea-realtime-video --pipeline.task-profile interactive-video`. The command builder above switches `--pipeline.task-profile` among recorded tasks and still emits `worldfoundry-eval run`.

It runs in the unified environment `worldfoundry-unified-cu128` (Python 3.11, CUDA 12.8).

Recorded weight repositories include `krea/krea-realtime-video`. Prepare the environment and check local assets with `bash scripts/inference/prepare_model_infer.sh krea-realtime-video`. Add `--download` to fetch missing public checkpoints.

Recorded licenses include apache-2.0; status: **Runner parity pending**.

<ModelRelatedRecipes modelId="krea-realtime-video" locale="en" />