# Multi-scenario application
Voc2vec Hubert Ls Pt
Apache-2.0
voc2vec is a foundational model specifically designed for non-verbal human data, built on the HuBERT framework and pre-trained on 125 hours of non-verbal audio data.
Audio Classification
Transformers English

V
alkiskoudounas
114
1
Blip Large Long Cap
Bsd-3-clause
A long-text image description generator fine-tuned based on BLIP, suitable for text-to-image prompts and image dataset annotation
Image-to-Text
Transformers

B
unography
26.87k
5
Everything V1
Openrail
An anime-style Stable Diffusion model fine-tuned from Anything V3, supporting high-quality image generation with danbooru tags
Image Generation English
E
TheRafal
90
12
Image Captioning Portuguese
Apache-2.0
This model converts images into Portuguese descriptions, trained on ViT and GPT2 architectures.
Image-to-Text Other
I
adalbertojunior
17
1
Featured Recommended AI Models