SeaArt Furry XL V1.0
Detalles
Obras relacionadas
V1.0
565.4K
1.3K
511
...Ver más
This is SeaArt's first open-source model: Furry Base Model. This model was developed through training on millions of furry images, offering a rich source of original furry images.
Recommended prompts:
The prompt generation rules for the Furry Base Model incorporate a variety of elements, including part names, authors, character names, detailed content of the scene, and quality indicators.
Among these, high-quality terms like "best quality" may have a notable bias. If -related terms are necessary, please avoid adding content in negative prompts.
To avoid content, use recommended negative prompts such as: "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name".
SeaArt will continue to improve and optimize this open-source model to meet the growing needs and expectations of users.
If you have any suggestions or feedback about the model, please join our Discord server >>> https://discord.gg/293BEcfZfW
Ver traducción
Conversar con el modelo
Anuncio
2024-03-20
Publicar modelo
2024-03-20
Añadir versión de modelo
2025-12-31
Actualizar información del modelo
Detalles del modelo
Tipo
Checkpoint
Fecha de lanzamiento
2024-03-20
Modelo básico
SDXL 1.0
Model Parameters
Parámetros de entrenamiento
Epochs：1
Steps：0
Introducción de versión
This is SeaArt's first open-source model: Furry Base Model. This model was developed through training on millions of furry images, offering a rich source of original furry images.
Recommended prompts:
The prompt generation rules for the Furry Base Model incorporate a variety of elements, including part names, authors, character names, detailed content of the scene, and quality indicators.
Among these, high-quality terms like "best quality" may have a notable bias. If -related terms are necessary, please avoid adding content in negative prompts.
To avoid content, use recommended negative prompts such as: "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name".
SeaArt will continue to improve and optimize this open-source model to meet the growing needs and expectations of users.
If you have any suggestions or feedback about the model, please join our Discord server >>> https://discord.gg/293BEcfZfW