# Nucleus-Image > Nucleus-Image is an open-weight text-to-image model from Nucleus AI, released in April 2026 under Apache 2.0. It is a sparse mixture-of-experts diffusion transformer: 17B parameters in total, but only about 2B are active for each pass, chosen from 64 routed experts per layer. On Kenerate AI it runs in the browser for 3 credits per image, with a negative prompt, a seed and 7 aspect ratios. URL: https://kenerateai.com/models/nucleusai/nucleus-image Publisher: Kenerate AI (https://kenerateai.com) Last updated: 31 October 2026 ## Key facts - Official name: Nucleus-Image - Hugging Face ID: NucleusAI/Nucleus-Image - Maker: Nucleus AI - Released: April 2026 (arXiv 2604.12163) - Size: 17B total · ~2B active per pass - Architecture: Sparse MoE diffusion transformer, 64 experts - Licence: Apache 2.0 - On Kenerate: 3 credits per image - Inputs: Text prompt + negative prompt + seed - Aspect ratios: 7 — 1:1, 3:4, 2:3, 9:16, 4:3, 3:2, 16:9 ## Steps 1. Open the model — Go to /app/image and pick Nucleus Image (the button on this page selects it). Sign in free to get started. 2. Write the prompt — Lead with the subject, then the setting, lighting, camera or art style and colours. Plain, specific sentences work better than keyword lists. 3. Add a negative prompt — List what must not appear — for example "text, watermark, extra fingers, blur" — and pick one of 7 aspect ratios. 4. Lock the seed — When a picture is close, keep its seed and change one word at a time; each re-run costs 3 credits. ## In depth ### Mixture of experts in plain words A normal diffusion transformer runs every parameter on every step. Nucleus-Image splits most of its layers into 64 specialist blocks and lets a router choose which ones handle each part of the picture, so about 2B of its 17B parameters are busy at once [1][2]. The first 3 layers stay dense, and one shared expert in each MoE layer sees every token [1]. Two details from the paper make it cheaper still: text tokens only provide key-value pairs to the image tokens, and those are cached across denoising steps [1][3]. The result is a big model whose per-step compute is closer to a small one. ### Nucleus-Image vs Qwen-Image vs Z-Image on Kenerate All three are open-weight models you can run without a GPU here. Pick by input and job, not by headline score: - Nucleus Image — 3 credits, text only, negative prompt + seed, 7 aspect ratios. Cheap text-to-image tests. - Z Image Base — 3 credits, 1 uploaded image with a strength slider. Cheap image-to-image. - Qwen Image — 6 credits, edits 1 uploaded image, strong lettering. - Qwen Image 3.0 — 9 credits, up to 3 references, on the free plan. Best of the four for words in the picture. ### Prompts that work with Nucleus-Image The model reads prompts with an 8B vision-language encoder (Qwen3-VL-8B-Instruct) [1], so full sentences beat tag lists: "A ceramic teapot on a linen tablecloth by a rainy window, soft morning light, shallow depth of field, muted greens". Name positions explicitly ("a red bicycle to the left of a blue door") — spatial position is its best GenEval category [1]. Use the negative prompt for artefacts you keep seeing, and lock the seed once the composition is right. References: [1] NucleusAI/Nucleus-Image — Hugging Face model card: https://huggingface.co/NucleusAI/Nucleus-Image [2] Nucleus-Image: Sparse MoE for Image Generation — arXiv 2604.12163: https://arxiv.org/abs/2604.12163 [3] NucleusMoE-Image pipeline — Hugging Face Diffusers docs: https://huggingface.co/docs/diffusers/en/api/pipelines/nucleusmoe_image [4] WithNucleusAI/Nucleus-Image — GitHub: https://github.com/WithNucleusAI/Nucleus-Image ## FAQ Q: What is Nucleus-Image? A: Nucleus-Image is an open-weight text-to-image model from Nucleus AI, published on Hugging Face as NucleusAI/Nucleus-Image and described in the April 2026 paper "Nucleus-Image: Sparse MoE for Image Generation" (arXiv 2604.12163). It is a sparse mixture-of-experts diffusion transformer with 17B parameters in total and about 2B active per pass, released under Apache 2.0. Q: What does "sparse mixture of experts" mean for an image model? A: Instead of one big feed-forward block in every layer, 29 of the model's 32 layers hold 64 smaller "expert" blocks plus one shared expert. A router sends each part of the image to a few experts, so only about 2B of the 17B parameters do work on each step. The model keeps the knowledge of a large network while each step costs closer to a small one. Q: How much does Nucleus-Image cost on Kenerate? A: 3 credits per image — about $0.03 to $0.035 depending on which credit pack you buy. Credit packs are one-time purchases with no subscription. Nucleus Image is not on the free plan; Qwen Image 3.0 and Flux 2 Dev are. Q: Can I use Nucleus-Image online without a GPU? A: Yes. Kenerate AI runs Nucleus Image in the browser, with no Diffusers install and no download of the 17B weights. Pick it in /app/image, write a prompt, add a negative prompt if you want, choose an aspect ratio and generate. Q: Nucleus-Image vs Qwen-Image — which is better? A: Nucleus AI reports a GenEval score of 0.87, which it says matches Qwen-Image, and it reuses Qwen's VAE and a Qwen3-VL text encoder. On Kenerate Nucleus Image costs 3 credits and is text to image only; Qwen Image costs 6 credits and can edit one uploaded picture, and Qwen Image 3.0 (9 credits, free plan) is the stronger pick for words inside the picture. Q: Nucleus-Image vs Z-Image? A: Both cost 3 credits on Kenerate. Z Image Base is Alibaba Tongyi's dense 6B model and can remix an uploaded image with a strength slider. Nucleus Image is a 17B mixture-of-experts model with a negative prompt and seed but no image input. Use Z Image for image-to-image, Nucleus for text-only prompts where you want to exclude things. Q: Is Nucleus-Image free and open source? A: The weights are free under Apache 2.0, and Nucleus AI says it released the training code and dataset too. Running it yourself needs a GPU that can hold the full 17B weights in BF16 plus the 8B text encoder. On Kenerate it is a paid model at 3 credits per image. Q: How do I run Nucleus-Image in Diffusers? A: Install the latest Diffusers from GitHub, load NucleusAI/Nucleus-Image with DiffusionPipeline in bfloat16 and move it to CUDA. The model card's quick start uses 50 steps and guidance 4.0, and enabling the text KV cache speeds up sampling. The 7 native sizes run from 768×1344 to 1344×768. Q: Are the Nucleus-Image benchmark scores independent? A: No. GenEval 0.87, DPG-Bench 88.79 and OneIG-Bench 0.522 come from Nucleus AI's own model card and paper, measured on the base model at 1024×1024 with 50 steps. We found no independent benchmark yet, so treat them as vendor claims and judge with your own prompts. ## Related pages - Z Image: https://kenerateai.com/model/z-image - Qwen Image: https://kenerateai.com/model/qwen-image - ERNIE-Image: https://kenerateai.com/models/baidu/ernie-image - Boogu-Image: https://kenerateai.com/models/boogu/boogu-image - Open source AI image generator: https://kenerateai.com/open-source-ai-image-generator - Stable Diffusion online free: https://kenerateai.com/stable-diffusion-online-free - All models: https://kenerateai.com/model ## Sources - NucleusAI/Nucleus-Image — Hugging Face model card: https://huggingface.co/NucleusAI/Nucleus-Image - Nucleus-Image: Sparse MoE for Image Generation — arXiv 2604.12163: https://arxiv.org/abs/2604.12163 - NucleusMoE-Image pipeline — Hugging Face Diffusers docs: https://huggingface.co/docs/diffusers/en/api/pipelines/nucleusmoe_image - WithNucleusAI/Nucleus-Image — GitHub: https://github.com/WithNucleusAI/Nucleus-Image