by duongve
Open source · 27k downloads · 63 likes
NetaYume Lumina Image 2.0 is an advanced text-to-image generation model specializing in creating anime-style and realistic character images. It excels at producing detailed illustrations with sharp outlines, vibrant colors, and harmonious shading, while offering a deeper understanding of characters, particularly those from the Danbooru universe. The model stands out for its ability to accurately render accessories, clothing textures, hairstyles, and background elements, ensuring consistent and high-quality results. Perfect for artists, content creators, or anime enthusiasts, it brings scenes or characters to life from simple text descriptions. Its finely tuned approach allows it to maintain great versatility while optimizing performance in the realm of Japanese animation.
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:
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
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:
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
IV. Acknowledgments