Image model

Nucleus Image

Nucleus-Image is Nucleus AI’s open-source text-to-image model built on a sparse MoE diffusion transformer. It scales to 17B total parameters with only about 2B active per forward pass, aiming for a strong quality-efficiency tradeoff, and the model card says it matches or exceeds leading systems on GenEval, DPG-Bench, and OneIG-Bench.

Nucleus AI Image Closed apache-2.0
Type
Image
Weights
Closed
Downloads
141
Likes
261
Pipeline
text to image
License
apache-2.0

Model hub

NucleusAI/Nucleus-Image

Repo
NucleusAI/Nucleus-Image
Library
diffusers
Access
Public
Technical tags and languages
en diffusers safetensors moe sparse-moe diffusion text-to-image image-generation diffusers:NucleusMoEImagePipeline
Open on Hugging Face

Papers

1

More from Nucleus AI

3

About Nucleus AI

1

Nucleus AI is an AI research company building general intelligence systems and large language models. The company has released open-source models on HuggingFace, including a 22B parameter LLM trained on 500B tokens of RefinedWeb, and Nucleus-X, a RetNet-based model offering faster inference and lower memory requirements.