Home Projects Bernini
Bernini
Python

Bernini

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

by bytedance · GitHub
Stars
Forks
License
Created
Last commit
Language
image-editingimage-generationvideo-editingApache-2.0Python
View on GitHub
In plain words

Generate and edit videos using a framework that plans and renders content intelligently.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
Bernini — GitHub preview card
📈 Star history
1 1301 129
2026-07-202026-08-31
📈 Track Bernini

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

Bernini has 1.1k stars on GitHub. It has been forked 84 times. Bernini is written mainly in Python. It has been in active development since 2026. Bernini is available under the Apache-2.0 license. Its main topics are image-editing, image-generation, video-editing, video-generation.

Compare with the paid tools it replaces
A free alternative to RunwayKling
Frequently asked questions

What is Bernini?

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

Is Bernini open source?

Bernini is an open-source project. It is released under the Apache-2.0 license.

Is Bernini free?

Yes. Bernini is free and open source — you can use, modify and self-host it.

What license does Bernini use?

Bernini is available under the Apache-2.0 license.

What language is Bernini written in?

Bernini is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — Bernini

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=bytedance-bernini)](https://olud.ai/project/bytedance-bernini.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
ChronoEdit
[ICLR 2026] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
697 · aigc
sharesimage-editingvideo-generation
FateZero
[ICCV 2023 Oral] "FateZero: Fusing Attentions for Zero-shot Text-based Video Editing"
1.2k · image-editing
sharesvideo-editingimage-editing
DreamOmni2
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editin…
2k · image-editing
sharesimage-editingimage-generation
MagicDance
[ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions R…
776 · behavior-generation
sharesvideo-editingimage-editing
DiffMorpher
Official Code for DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing…
504 · diffusion-models
sharesimage-editingvideo-generation
gpt_image_playground
基于 OpenAI gpt-image-2 API 的图片生成与编辑工具
3.1k · gpt-image
sharesimage-editingimage-generation
Voost
[SIGGRAPH Asia 25] Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtua…
340 · diffusion-models
sharesimage-editingimage-generation
MagicBrush
[NeurIPS'23] "MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing".
411 · diffusion-models
sharesimage-editingimage-generation
NOVA
[ICLR 2025] Autoregressive Video Generation without Vector Quantization
655 · autoregressive-models
sharesvideo-generationimage-generation
LLMGA
This project is the official implementation of 'LLMGA: Multimodal Large Language Model based Ge…
396 · aigc
sharesimage-editingimage-generation

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.