NetaYume Lumina Image 2.0
par duongve
Open source · 27k downloads · 63 likes
2.3
(63 avis)ImageAPI & LocalÀ propos
NetaYume Lumina Image 2.0 est un modèle avancé de génération d'images par texte, spécialisé dans la création d'images de style anime et de personnages réalistes. Il excelle dans la production d'illustrations détaillées, avec des contours nets, des couleurs vibrantes et des ombres harmonieuses, tout en offrant une meilleure compréhension des personnages, notamment ceux issus de l'univers Danbooru. Le modèle se distingue par sa capacité à restituer avec précision les accessoires, les textures vestimentaires, les coiffures et les éléments de fond, garantissant des résultats cohérents et de haute qualité. Idéal pour les artistes, les créateurs de contenu ou les passionnés d'anime, il permet de donner vie à des scènes ou des personnages à partir de descriptions textuelles simples. Son approche fine-tunée lui permet de conserver une grande polyvalence tout en optimisant les performances dans le domaine de l'animation japonaise.
Documentation
NetaYume Lumina Image v2.0
I. Introduction
NetaYume Lumina is a text-to-image model fine-tuned from Neta Lumina, a high-quality anime-style image generation model developed by Neta.art Lab. It builds upon Lumina-Image-2.0, an open-source base model released by the Alpha-VLLM team at Shanghai AI Laboratory.
This model was trained with the goal of not only generating realistic human images but also producing high-quality anime-style images. Despite being fine-tuned on a specific dataset, it retains a significant amount of knowledge from the base model.
Key Features:
- High-Quality Anime Generation: Generates detailed anime-style images with sharp outlines, vibrant colors, and smooth shading.
- Improved Character Understanding: Better captures characters, especially those from the Danbooru dataset, resulting in more coherent and accurate character representations.
- Enhanced Fine Details: Accurately generates accessories, clothing textures, hairstyles, and background elements with greater clarity.
The file NetaYume_Lumina_v2_all_in_one.safetensors is an all-in-one file that contains the necessary weights for the VAE, text encoder, and image backbone to be used with ComfyUI.
II. Model Components & Training Details
- Text Encoder: Pre-trained Gemma-2-2b
- Variational Autoencoder: Pre-trained Flux.1 dev's VAE
- Image Backbone: Fine-tune NetaLumina's Image Backbone
III. Suggestion
System Prompt: This help you generate your desired images more easily by understanding and aligning with your prompts.
For anime-style images using Danbooru tags:
VB.NET
You are an assistant designed to generate anime images based on textual prompts.
You are an assistant designed to generate high-quality images based on user prompts and danbooru tags.
Recommended Settings
- CFG: 4–7
- Sampling Steps: 40-50
- Sampler:
- Euler a (with scheduler: normal)
- res_multistep (with scheduler: linear_quadratic)
IV. Acknowledgments
- narugo1992 – for the invaluable Danbooru dataset
- Alpha-VLLM - for creating the a wonderful model!
- Neta.art and his team – for openly sharing awesome model.
Liens & Ressources