Nucleus-Image

About

What Nucleus-Image is

🌐 <a href="https://withnucleus.ai/image"<bWebsite</b</a&nbsp;&nbsp; | &nbsp;&nbsp;🖥️ <a href="https://github.com/WithNucleusAI/Nucleus-Image"<bGitHub</b</a&nbsp;&nbsp; | &nbsp;&nbsp;🤗 <a href="https://huggingface.co/NucleusAI/NucleusMoE-Image"<bHugging Face</b</a&nbsp;&nbsp; | &nbsp;&nbsp;📑 <a href="https://arxiv.org/abs/2604.12163"<bTech Report</b</a Introduction Nucleus-Image is a text-to-image generation model built on a sparse mixture-of-experts (MoE) diffusion transformer architecture. It scales to 17B total parameters across 64 routed experts per layer while activating only ~2B parameters per forward pass, establishing a new Pareto frontier in quality-versus-efficiency. Nucleus-Image matches or exceeds leading models including Qwen-Image, GPT Image 1, Seedream 3.0, and Imagen4 on GenEval, DPG-Bench, and OneIG-Bench. This is a base model released without any post-training optimization (no DPO, no reinforcement learning, no human preference tuning). All reported results reflect pre-training performance only. We release the full model weights, training code, and dataset, making Nucleus-Image the first fully open-source MoE diffusion model at this quality tier. Key Features - Sparse MoE efficiency: 17B total capacity with only ~2B active parameters per forward pass, enabling high-quality generation at a fraction of the inference cost of dense models - Expert-Choice Routing: Guarantees balanced expert utilization without auxiliary load-balancing losses, with a decoupled routing design that separates timestep-aware assignment from timestep-conditioned computation - Base model, no post-training: This is a base model. All benchmark results are from pre-training alone, without DPO, reinforcement learning, or human preference tuning - Multi-aspect-ratio support: Trained with aspect-ratio bucketing from the outset at every resolution stage, supporting a range of output dimensions - Text KV caching via diffusers: Text tokens are excluded from the transformer backbone entirely and their KV projections are cached across all denoising steps. This caching is natively integrated into the diffusers pipeline. Simply enable it with TextKVCacheConfig for automatic speedup with

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How image models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys nucleus-image for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (nucleus-image below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/images/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nucleus-image","prompt":"a red bicycle","size":"1024x1024"}'

Details

Languages, data & research

Papers

Licence

Open weights

Sources

Weights & code

Explore

More image models