A video caption generation model based on VILA-v1.5-8B, capable of generating detailed and human-preference-aligned captions for input videos.

MultimodalTransformers

A LoRA model trained on 96x96 Pokémon sprites and BLIP image captions for generating Pokémon trainer-style pixel images

MultimodalDiffusers

xGen-MM is a series of multimodal foundation models developed by Salesforce AI Research, improved based on the BLIP series, and trained on high-quality image captions and interleaved image-text data.

MultimodalSafetensorsEnglish

Tarsier-34b is an open-source large-scale video-language model focused on generating high-quality video captions and achieving leading results in multiple public benchmarks.

MultimodalTransformers

Florence-2-SD3-Captioner is an image caption generation model based on the Florence-2 architecture, specifically designed for generating high-quality image captions.

MultimodalTransformersMultiple Languages

A CLIP model trained on the Recap-DataComp-1B dataset using LLaMA-3 generated captions, suitable for zero-shot image classification tasks

MultimodalOpenclip

LoRA model trained on 96x96 Pokémon sprites and BLIP image captions for generating pixel-style Pokémon trainer characters

Computer VisionDiffusers

This is a vision encoder-decoder model based on ViT and Turkish GPT-2 for generating Turkish image captions.

MultimodalTransformersOther

This model is an image-to-text model, focusing on generating captions for images.

Computer VisionTransformers

A vision-language model fine-tuned from Microsoft's git-base model, specifically designed to generate descriptive text captions for images from the anime 'One Piece'

MultimodalTransformersMultiple Languages

A deep learning-based model that converts input images into descriptive captions.

MultimodalTransformersEnglish

This model is a fine-tuned image-to-text generation model based on the BLIP architecture, specifically designed to generate captions describing high-level actions in images.

MultimodalTransformersEnglish

A video caption generation model based on Timesformer and BERT architectures, capable of generating descriptive captions for video content.

MultimodalTransformers

FuseCap is a framework specifically designed for generating semantically rich image captions, leveraging large language models to produce fused image descriptions.

MultimodalTransformers

Pix2Struct is a vision-language understanding model optimized for generating functional description captions from UI interface screenshots

MultimodalTransformersMultiple Languages

A vision-language model pre-trained on COCO and fine-tuned on a football dataset, proficient in generating image captions

MultimodalTransformers

This model can generate captions for any photo in a cinematic narrative style, trained on movie posters and plot summaries, primarily for entertainment purposes.

MultimodalTransformersOther

GIT is a Transformer decoder-based vision-language model capable of generating image captions and performing visual question answering

MultimodalTransformersMultiple Languages