SenseNova-U1-8B-MoT

by

sensenova

sensenova· 27 Apr 2026

MultimodalImage generation

A multimodal generation model by SenseTime, one of China's first AI startups, supporting text-to-image, image-to-text, and image editing.

Specs

Params8B

LicenseApache-2.0

Tags

modelsmodels/llms/multi-modalmodels/image-generationartifacts/21

Resources

Hugging Face — sensenova/SenseNova-U1-8B-MoT Paper / tech report Appeared in Artifacts Log #21

Adoption · Interconnects

RAM score

—

Hugging Face Downloads

42.5K

last 30d

80.4K

all time

HF Likes

287

Relative Adoption Metric contextualizes downloads against the model's size bucket.

Related Models

Similar Models

BLIP3o-Model-8B

BLIP3o

BLIP3o12 May 2025

Lumina-mGPT-2.0

Alpha-VLLM

Alpha-VLLM02 Apr 2025

ByteDance Seed

ByteDance Seed19 May 2025

DeepSeek

DeepSeek26 Jan 2025