---
title: "Bernini-R 14B"
description: "Bernini-R 14B from ByteDance: text-to-image and image-to-image; Runner parity pending; dedicated `worldfoundry-bernini-cu124`."
modelId: "bernini-r-14b"
pageSource: authored
---

Bernini-R 14B is the renderer-only release of ByteDance's Bernini family: the 14B rendering model packaged without the 7B semantic planner. It keeps the same six-task surface (text-to-image, image editing, text/video/reference-to-video) but takes your inputs directly instead of planning first. WorldFoundry vendors the official renderer inference in-tree and loads ByteDance/Bernini-R-Diffusers.

<ModelPaperFigures modelId="bernini-r-14b" locale="en" />

The recorded paper is [Bernini: Latent Semantic Planning for Video Diffusion](https://arxiv.org/abs/2605.22344) (2026).

Project page: [bernini-ai.github.io](https://bernini-ai.github.io/). Code: [bytedance/Bernini](https://github.com/bytedance/Bernini).

This is **not** planner+renderer [Bernini](/docs/guides/supported-models/bernini) and **not** the single-GPU [Bernini-R 1.3B](/docs/guides/supported-models/bernini-r-1.3b).

Same paper: [Bernini: Latent Semantic Planning for Video Diffusion](https://arxiv.org/abs/2605.22344). Weights: `ByteDance/Bernini-R-Diffusers` (**apache-2.0**). Image recipes are recorded as **one-GPU**; video recipes can turn on explicit Ulysses sequence parallelism. GPU artifact parity is **pending**. Status: **Runner parity pending**.

<ModelCommandBuilder modelId="bernini-r-14b" locale="en" />

## What it is for

Pick `bernini-r-14b` when you want this family's text-to-video line in WorldFoundry: a prompt in, a generated clip out. Use it as the catalog T2V start rather than an editor or a world-model stepper.

A single 14B rendering network from the Bernini two-stage design, run standalone. The manifest records that image recipes fit on one GPU while video recipes can use explicit Ulysses sequence parallelism for speed.

Catalog tasks include text-to-image, image-to-image, text-to-video, and video-to-video. Catalog aliases include `bernini-r` and `bernini-r-diffusers`. Documented modalities: text, image, and video in, image and video out.

Recorded evaluation entry points include [VBench](/docs/evaluation/benchmark-hub/vbench) (Checks the renderer's raw T2V quality).

## Runtime contract

Optional `prompt`, `task_type`, `neg_prompt`, `num_frames`, and `height`; artifacts `generated_image`, `generated_video`, and `bernini-r-14b.mp4`.

CLI task profiles: `t2v`, `t2i`, `i2i`, `v2v`, `r2v`, and `rv2v`. WorldFoundry binds `BerniniWorldFoundryPipeline`.

Family status: **Runner parity pending**.

Runner parity is pending_gpu_validation. Use task_type to select the task; stage the Bernini-R-Diffusers checkpoint (apache-2.0) locally first. For quick experiments prefer the 1.3B sibling; for the planner+renderer pipeline use the flagship bernini entry.

Official renderer inference is vendored in-tree; no external Bernini checkout is used.

## Running in WorldFoundry

Launch `worldfoundry-eval run bernini-r-14b --pipeline.task-profile t2v` to sample the clip. The command builder above switches `--pipeline.task-profile` among recorded tasks and still emits `worldfoundry-eval run`.

It runs in the dedicated environment `worldfoundry-bernini-cu124` (Python 3.11, CUDA 12.4, torch==2.5.1+cu124).

Recorded weight repositories include `ByteDance/Bernini-R-Diffusers` and `ByteDance/Bernini-R-Diffusers`. Prepare the environment and check local assets with `bash scripts/inference/prepare_model_infer.sh bernini-r-14b`. Add `--download` to fetch missing public checkpoints.

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

<ModelRelatedRecipes modelId="bernini-r-14b" locale="en" />