Video-Generierung

Bernini

von ByteDance

ByteDance's open‑source model for instruction‑based video edits, identity held.

Bernini

Hauptfunktionen

Add a snowman beside the dog and keep the rest of the clip unchangedTry now

Technische Spezifikationen

Planner + DiT

Qwen2.5-VL planner, 14B Wan2.2 renderer

Edit, Generate, R2V

Editing, generation, subject-to-video

480p / 16fps

Default render setting

Apache 2.0

Open weights, self-hostable

Anwendungsfälle

Augment real footage

Add or remove props, fix a detail, or restyle an element in a clip without re-shooting. The consistency lock keeps the rest of the shot identical, so edits read as native.

Recurring characters and avatars

Keep the same face across episodes, ads, or an avatar series. Subject-to-video holds a person's identity from a few reference images as they move through new scenes.

Virtual try-on and product placement

Swap clothing onto a moving model from a reference, or drop a product or on-screen video into a shot, for fashion and ad work that needs the source clip kept intact.

Re-block an action

Change what someone is doing in a take, a stand becomes a crouch, without re-filming. Motion editing alters the action while identity, framing, and lighting stay fixed.

Prompt-Beispiele

Consistency edit

Add a snowman beside the dog on the snowy path, and keep the dog, the road, and the trees unchanged

Edit prompt

Identity-locked subject

Place this person on a neon city rooftop at night, gently turning to camera, keeping their face and jacket

Edit prompt

Reference swap

Replace the outer shirt with the one in the reference image, keep the pose, lighting, and motion exactly

Edit prompt

Einfache Preise

Starten Sie noch heute kostenlos, mit der Option, jederzeit zu upgraden oder zu kündigen.

Basic

$0/ Monat
abgerechnet als $0 pro Jahr

900 monatliche Credits

1 Nutzer

Alle Modelle

Workflows

Standard

$0/ Monat
abgerechnet als $0 pro Jahr

3200 monatliche Credits

1 Nutzer

Alle Modelle

Workflows

Pro

$0/ Monat
abgerechnet als $0 pro Jahr

6200 gemeinsame monatliche Credits

1 Nutzer

+ bis zu 4 weitere gegen Aufpreis

Alle Modelle

Workflows

Pro Max

$0/ Monat
abgerechnet als $0 pro Jahr

24000 gemeinsame monatliche Credits

1 Nutzer

+ bis zu 9 weitere gegen Aufpreis

Alle Modelle

Workflows

Enterprise

Für höhere Limits

Individuell

Preis- und Abrechnungsbedingungen

Unbegrenzte Credits
Individuelle Platzlimits
Alle Modelle
Workflows
Pricing Gradient

Free

Zum Ausprobieren

$0

dauerhaft kostenlos

Bis zu 20 Credits
Nur 1 Nutzer
Eingeschränkte Modelle
Workflows
Tarifdetails vergleichen

Häufig gestellte Fragen

What is Bernini?
Bernini is ByteDance's open-source unified framework for video generation and editing. It pairs an MLLM-based semantic planner with a DiT-based renderer built on Wan2.2, and was released under Apache 2.0 in June 2026.
What can Bernini do?
It handles text-to-image, image editing, text-to-video, instruction-based video editing, reference-guided editing such as garment swaps and video insertion, and subject-to-video that places a person or character into a new scene.
How is Bernini different from a standard video model?
Most video models generate from scratch. Bernini splits the work: an MLLM planner decides the semantics, then the renderer paints pixels. That design gives it strong consistency on edits, untouched parts of a clip stay frozen, and strong identity preservation in subject-to-video.
Is Bernini open source?
Yes. The inference code and the renderer weights are public under Apache 2.0, on GitHub and Hugging Face. You can run it on your own hardware; a Hopper-class GPU is recommended, with multiple GPUs for video.
How well does Bernini preserve a subject's identity?
Identity preservation is its standout result. In ByteDance's subject-to-video evaluations it leads comparable systems on face similarity, holding a recognizable face as the subject moves, which makes it a fit for avatars, character work, and serialized content where the same face has to recur.
What resolution does Bernini output?
The default render setting is 480p at 16fps. The release prioritizes editing fidelity and consistency over maximum resolution, and higher settings are possible at greater compute cost.

Weitere Modelle

Entdecken Sie den Rest des Morphic-Modellkatalogs.

Alle Modelle ansehen →

Kling 4.0

Kling

Kuaishou's next Kling flagship, expected soon. Longer clips and sharper detail are on the way.

Seedream 5.0 Pro

ByteDance

Grounded editing and multi-layer separation. Dense infographics and native text in 14 languages.

Nano Banana 2 Lite

Google DeepMind

Google DeepMind's fastest Nano Banana model. 1K images in about four seconds, with consistent characters.

Seed Audio 1.0

ByteDance

ByteDance's all-in-one audio model. Voice, music, and sound effects in one generation.