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 no code changes to the inference loop
Progressive resolution training: Three-stage curriculum (256 → 512 → 1024) with progressive sparsification of expert capacity
Architecture
Architecture
Nucleus-Image is a 32-layer diffusion transformer where 29 of the 32 blocks replace the dense FFN with a sparse MoE layer containing 64 routed experts and one shared expert (the first 3 layers use dense FFN for training stability). Image queries attend to concatenated image and text key-value pairs via joint attention. Text tokens are excluded from the transformer backbone entirely, participating only as KV contributors. This eliminates MoE routing overhead for text and enables full text KV caching across denoising steps.
Routing uses Expert-Choice with a decoupled design: the router receives the unmodulated token representation concatenated with the timestep embedding, while expert MLPs receive the fully modulated representation. This prevents the adaptive modulation scale — which varies by an order of magnitude across timesteps — from collapsing expert selection into timestep-dependent routing, preserving spatial and semantic expert specialization.
Model Specifications
Specification
Value
Total parameters
17B
Active parameters
~2B
Architecture
Sparse MoE Diffusion Transformer
Layers
32
Hidden dimension
2048
Attention heads (Q / KV)
16 / 4 (GQA)
Experts per MoE layer
64 routed + 1 shared
Expert hidden dimension
1344
Text encoder
Qwen3-VL-8B-Instruct
Image tokenizer
Qwen-Image VAE (16ch)
Training data
700M images, 1.5B caption pairs
Training curriculum
Progressive resolution (256 → 512 → 1024)
Total training steps
1.7M
Benchmark Results
Overall Performance
Nucleus-Image achieves state-of-the-art or near state-of-the-art results on all three benchmarks despite activating only ~2B of its 17B parameters per forward pass. All results are from the base model at 1024x1024, 50 inference steps, CFG scale 8.0.
Benchmark
Score
Highlights
GenEval
0.87
Matches Qwen-Image; leads all models on spatial position (0.85)
DPG-Bench
88.79
#1 overall; leads in entity (93.08), attribute (92.20), and other (93.62)
OneIG-Bench
0.522
Surpasses Imagen4 (0.515) and Recraft V3 (0.502); strong style (0.430)
1import torch
2from diffusers import DiffusionPipeline
3from diffusers import TextKVCacheConfig
45model_name ="NucleusAI/Nucleus-Image"67pipe = DiffusionPipeline.from_pretrained(model_name, torch_dtype=torch.bfloat16)8pipe.to("cuda")910# Enable Text KV caching across denoising steps (integrated into diffusers)11config = TextKVCacheConfig()12pipe.transformer.enable_cache(config)1314# Supported aspect ratios15aspect_ratios ={16"1:1":(1024,1024),17"16:9":(1344,768),18"9:16":(768,1344),19"4:3":(1184,896),20"3:4":(896,1184),21"3:2":(1248,832),22"2:3":(832,1248),23}2425prompt ="A weathered lighthouse on a rocky coastline at golden hour, waves crashing against the rocks below, seagulls circling overhead, dramatic clouds painted in shades of amber and violet"26width, height = aspect_ratios["16:9"]2728image = pipe(29 prompt=prompt,30 width=width,31 height=height,32 num_inference_steps=50,33 guidance_scale=4.0,34 generator=torch.Generator(device="cuda").manual_seed(42),35).images[0]3637image.save("nucleus_output.png")
Highlights
Portraits & People
Nucleus-Image generations of human subjects and portraits, spanning diverse cultures, ages, and artistic styles. From expressive character studies to fine-grained close-ups with intricate skin texture and detail.
Fantasy, Surrealism & Nature
Nucleus-Image generations spanning fantasy, surrealism, animation, and the natural world.
Commercial & Everyday Imagery
Nucleus-Image generations across product photography, architecture, typography, food, and world culture, demonstrating versatility in commercial, conceptual, and everyday imagery.
