中文版模型说明 Neta Lumina Tech Report

📽️ Flash Preview

Introduction

Neta Lumina is a high‑quality anime‑style image‑generation model developed by Neta.art Lab.
Building on the open‑source Lumina‑Image‑2.0 released by the Alpha‑VLLM team at Shanghai AI Laboratory, we fine‑tuned the model with a vast corpus of high‑quality anime images and multilingual tag data. The preliminary result is a compelling model with powerful comprehension and interpretation abilities (thanks to Gemma text encoder), ideal for illustration, posters, storyboards, character design, and more.

Key Features

• Optimized for diverse creative scenarios such as Furry, Guofeng (traditional‑Chinese aesthetics), pets, etc.
• Wide coverage of characters and styles, from popular to niche concepts. (Still support danbooru tags!)
• Accurate natural‑language understanding with excellent adherence to complex prompts.
• Native multilingual support, with Chinese, English, and Japanese recommended first.

Model Versions

For models in alpha tests, requst access at https://huggingface.co/neta-art/NetaLumina_Alpha if you are interested. We will keep updating.

neta-lumina-v1.0

• Official Release: overall best performance

neta-lumina-beta-0624-raw (archived)

• Primary Goal: General knowledge and anime‑style optimization
• Data Set: >13 million anime‑style images
• >46,000 A100 Hours
• Higher upper limit, suitable for pro users. Check Neta Lumina Prompt Book for better results.

neta-lumina-beta-0624-aes-experimental (archived)

• First beta release candidate
• Primary Goal: Enhanced aesthetics, pose accuracy, and scene detail
• Data Set: Hundreds of thousands of handpicked high‑quality anime images (fine‑tuned on an older version of raw model)
• User-friendly, suitable for most people.

How  to  Use

Try it at Hugging Face playground

ComfyUI

Neta Lumina is built on the Lumina2 Diffusion Transformer (DiT) framework, please follow these steps precisely.

Environment Requirements

Currently Neta Lumina runs only on ComfyUI:

• Latest ComfyUI installation
• ≥ 8 GB VRAM

Downloads & Installation

Original (component) release

1. Neta Lumina-Beta
   • Download link: https://huggingface.co/neta-art/Neta-Lumina/blob/main/Unet/neta-lumina-v1.0.safetensors
   • Save path: ComfyUI/models/unet/
2. Text Encoder (Gemma-2B)
   • Download link:https://huggingface.co/neta-art/Neta-Lumina/blob/main/Text%20Encoder/gemma_2_2b_fp16.safetensors
   • Save path: ComfyUI/models/text_encoders/
3. VAE Model (16-Channel FLUX VAE)
   • Download link: https://huggingface.co/neta-art/Neta-Lumina/blob/main/VAE/ae.safetensors
   • Save path: ComfyUI/models/vae/

Workflow: load lumina_workflow.json in ComfyUI.

• UNETLoader – loads the .pth
• VAELoader – loads ae.safetensors
• CLIPLoader – loads gemma_2_2b_fp16.safetensors
• Text Encoder – connects positive /negative prompts to K Sampler

Simple merged release
Download neta-lumina-v1.0-all-in-one.safetensors,
md5sum = dca54fef3c64e942c1a62a741c4f9d8a,
you may use ComfyUI’s simple checkpoint loader workflow.

Recommended Settings

• Sampler: res_multistep/ euler_ancestral
• Scheduler: linear_quadratic
• Steps: 30
• CFG (guidance): 4 – 5.5
• EmptySD3LatentImage resolution: 1024 × 1024, 768 × 1532, 968 × 1322, or >= 1024

Prompt Book

Detailed prompt guidelines: Neta Lumina Prompt Book

Community

• Discord: https://discord.com/invite/TTTGccjbEa
• QQ group: 1039442542

Roadmap

Model

• Continous base‑model training to raise reasoning capability.
• Aesthetic‑dataset iteration to improve anatomy, background richness, and overall appealness.
• Smarter, more versatile tagging tools to lower the creative barrier.

Ecosystem

• LoRA training tutorials and components
  • Experienced users may already fine‑tune via Lumina‑Image‑2.0’s open code.
• Development of advanced control / style‑consistency features (e.g., Omini Control). Call for Collaboration!

License & Disclaimer

• Neta Lumina is released under Apache License 2.0

Participants & Contributors

• Special thanks to the Alpha‑VLLM team for open‑sourcing Lumina‑Image‑2.0
• Model development: Neta.art Lab (Civitai)
  • Core Trainer: li_li Civitai ・ Hugging Face
• Partners
  • nebulae: Civitai ・ Hugging Face
  • 生姜: Hugging Face
  • 孙一
• narugo1992 & deepghs: open datasets, processing tools, and models
• Naifu trainer at Mikubill

Community Contributors

• Evaluators & developers: 二小姐, spawner, Rnglg2
• Other contributors: 沉迷摸鱼, poi, AshenWitch, 十分无奈, GHOSTLX, wenaka, iiiiii, 年糕特工队, 恩匹希, 奶冻, mumu, yizyin, smile, Yang, 古神, 灵之药, LyloGummy, 雪时

Appendix & Resources

• TeaCache: https://github.com/spawner1145/CUI-Lumina2-TeaCache
• Advanced samplers & TeaCache guide (by spawner): https://docs.qq.com/doc/DZEFKb1ZrZVZiUmxw?nlc=1
• Neta Lumina ComfyUI Manual (in Chinese): https://docs.qq.com/doc/DZEVQZFdtaERPdXVh