Skip to content
SenseNovaU1

Open source alternatives to SenseNovaU1

200 open source apps like SenseNovaU1, closest match first.

Top picks

  1. B

    Bunny

    Launch

    Bunny is a family of lightweight multimodal models from BAAI that understand both images and text. It combines interchangeable vision encoders, such as EVA-CLIP and SigLIP, with a range of language backbones including Llama-3-8B, Phi-3-mini

    Open source

  2. V

    VINO-code

    Launch

    VINO is a research model for visual generation that handles text-to-image, text-to-video, image-to-video and image and video editing in a single set of weights. It combines a vision-language model with a multi-modal diffusion transformer, s

    Open source

  3. M

    MPLUG-Owl

    Launch

    mPLUG-Owl is an open-source family of multimodal large language models from X-PLUG that can work with images as well as text. The repository covers the first mPLUG-Owl, which adds visual modules to a language model, mPLUG-Owl2, which uses m

    Open source

  4. I

    InternLM-XComposer

    Launch

    InternLM-XComposer is a family of vision-language models from the InternLM team that work with images, video and text. This GitHub repository hosts the project's models and related releases. The newest entries are InternLM-XComposer2.5-Omni

    Open source

  5. O

    OmAgent

    Launch

    [EMNLP-2024] Build multimodal language agents for fast prototype and production

    Open source

  6. I

    InternVL

    Launch

    InternVL is a family of open-source multimodal models, which can understand images and text together and hold a conversation about them. The project was a CVPR 2024 oral paper, and its README presents it as an open-source alternative to com

    Open source

More like SenseNovaU1

7
J

januspro.app

januspro.app

Launch
8
U

Unisondb

A streaming multimodal database for Edge AI, and Edge Computing

Launch
9
N

NExT-GPT

Code and models for ICML 2024 paper

Launch
10
M

Minimind V

Train a 65M-parameter VLM from scratch in just 2h!

Launch
11
M

MultiAI

A unified desktop app that brings multiple AI models together in one clean

Launch
12
U

UnifiedModel

The semantic layer that makes enterprise data understandable to AI agents

Launch
13
T

TongFlow

Modality-First GenAI Platform

Launch
14
U

Unify

Models that keep learning

Launch
15
M

Minimind O

A 0.1B Omni model trained from scratch, capable of listening, speaking

Launch
16
K

KG-MM-Survey

Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

Launch
17
A

Amadeus

Real-time multimodal desktop agent evolving toward a persistent AI OS interface

Launch
18
M

MultiGen

Multi-agent end-to-end application - General-purpose artificial intelligence…

Launch
19
S

Silo

多模型同时对话、文生图,纯前端。Multi-model simultaneous chat、text-to-image generation

Launch
20
H

HunyuanCustom

A Multimodal-Driven Architecture for Customized Video Generation

Launch
21
F

Falcon LLM

Multilingual, multimodal, scalable AI tool; open-source

Launch
22
O

OpenWorldLib

Unified Codebase for Advanced World Models

Launch
23
M

MultiModal_BigModels_Survey

[MIR-2023-Survey] A continuously updated paper list

Launch
24
K

Kimi K2.5

The Open-Source Multimodal AI Powering Next-Generation Agent Swarms

Launch
25
O

Olympus

[CVPR 2025 Highlight] Official code for "Olympus: A Universal Task Router

Launch
26
I

Ima2 Gen

Local-first visual generation runtime and studio for people and coding agents

Launch
27
T

Ten

Build real-time multimodal conversational AI agents

Launch
28
M

MGM-Omni

Scaling Omni LLMs to Personalized Long-Horizon Speech

Launch
29
U

Unbody

The Supabase of AI era

Launch
30
L

LLMUnity

Create characters in Unity with LLMs!

Launch
31
U

Unblink

Camera monitoring with VLM

Launch
32
A

Agentsmith

Universal, model-agnostic operating harness for AI agents

Launch
33
N

Nautilo

AI goes multiplayer. A self-hosted workspace for people and machine people

Launch
34
T

Tutti

Where people and agents build in tune

Launch
35
U

Unigit Ecosystem

UNIGIT public brand and ecosystem hub — AI should work for everyone

Launch
36
F

Factor Fields

[SIGGRAPH 2023] We provide a unified formula for neural fields

Launch
37
V

Video-LLaVA

PG-Video-LLaVA: Pixel Grounding in Large Multimodal Video Models

Launch
38
L

Local-Multimodal-AI-Chat

Self-hostable multimodal chat with local LLMs

Launch
39
U

UFO

UFO³: Weaving the Digital Agent Galaxy

Launch
40
U

Unsloth

Local UI to run and train LLMs and diffusion models

Launch
41
C

ComfyUI-fal-API

Production-ready ComfyUI custom nodes for 1,400+ fal.ai models

Launch
42
V

Vui

Vui Nano — a small, context-aware text-to-speech model trained on real

Launch
43
X

X-AnyLabeling

A lightweight, efficient

Launch
44
N

nexus-ui

Open-source component library of composable

Launch
45
A

Anuma AI

Anuma brings all your AI in one place. One memory. Every model. Always private

Launch
46
P

Parlor

On-device, real-time multimodal AI with features similar to GPT-Live

Launch
47
G

GLM-skills

Official skills for the GLM family of models

Launch
48
N

Nucleoid

Synthesized Logic Language for World Models

Launch
49
V

VLMEvalKit

Open-source evaluation toolkit of large multi-modality models

Launch
50
U

Utopia

World's first open-source enterprise world model

Launch

About SenseNovaU1

S

SenseNovaU1

Unifying Multimodal Understanding and Generation with NEO-unify Architecture

SenseNova U1 is a new series of native multimodal models that unifies multimodal understanding, reasoning, and generation within a monolithic architecture. It marks a fundamental paradigm shift in multimodal AI: from modality integration to true unification. Rather than relying on adapters to translate between modalities, SenseNova U1 models think-and-act across language and vision natively.

Price
Free
Category
Design
Website
light-ai.top