This model uses the StyleGAN1 architecture and is trained with the StyleGAN2 regularization technique. It can generate realistic facial images with a resolution of 128×128. The model is trained on the FFHQ dataset and supports features such as style mixing, noise injection, and truncation tricks.

Computer VisionSafetensorsOther

A LoRA model based on Stable Diffusion for generating anthropomorphic versions of the Sugar Riot BOSS from Final Fantasy XIV, including three different forms.

Computer VisionDiffusers

LoRA model developed based on Krile's appearance in Final Fantasy XIV 7.x storyline, including standard attire, facial features, and weapon sub-models

Computer VisionDiffusers

This model is designed for time series forecasting, supports the English language, and uses a specific license (bethana15).

Scientific ComputingTensorflowEnglish

A LoRA model fine-tuned based on FLUX.1-dev, specifically designed for generating grayscale sketch-style images

Computer VisionDiffusers

A LoRA model trained on the FLUX.1-dev base model for generating deep blue and white line style illustrations.

Computer VisionDiffusers

LoRA adapter trained on the FLUX.1-dev base model for generating images with unique artistic style

Computer VisionDiffusers

A text-to-image generation model based on FLUX.1-dev foundation model with LoRA fine-tuning, capable of generating adorable animals and objects with a woolly Play-Doh style.

MultimodalDiffusers

A LoRA model fine-tuned based on the FLUX.1-dev foundation model, specialized for generating text-to-image conversions with TOK style

MultimodalDiffusers

A LoRA model fine-tuned on the FLUX.1-dev base model for generating images with specific artistic styles

MultimodalDiffusers

LoRA stylized model trained on FLUX.1-dev base model, specialized for generating illustrations with specific artistic styles

MultimodalDiffusers

A LoRA model fine-tuned based on the FLUX.1-schnell foundation model, specialized in generating cute comic-style images

Computer VisionDiffusers

LoRA model for generating the Nanamo character from Final Fantasy XIV, including both formal dress and facial feature versions

Computer VisionDiffusers

FFusion FFXL400 is a collection of LoRA models based on Stable Diffusion XL, focusing on providing diverse style and theme generation capabilities through low-rank adaptation technology.

Computer VisionDiffusersEnglish

FFusionXL-BASE is a text-to-image generation model based on SDXL. It optimizes the training speed, supports multiple languages, and is suitable for various application scenarios.

Computer VisionDiffusersEnglish

An SDXL-based LoRA model specializing in generating 3D potion bottle images

Computer VisionDiffusersEnglish

FFUSION AI is a latent diffusion model developed based on Stable Diffusion 2.1 technology, focusing on text-to-image generation. This model transforms text prompts into vivid artworks through advanced diffusion technology, supporting various creative and research application scenarios.

Computer VisionDiffusersMultiple Languages

A translation model specifically designed for converting Japanese text in the game 'Final Fantasy XIV' into Korean

Natural Language ProcessingTransformersMultiple Languages