Image Captioning Model created with VisionEncoderDecoderModel architecture using "microsoft/swinv2-base-patch4-window12to16-192to256-22kto1k-ft" as image_encoder and "openai/gpt2" as text_decoder. It has been trained on a variant of the WikiArt dataset that can be found at "AterMors/wikiart_recaption".

Downloads last month
101
Safetensors
Model size
240M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for AterMors/Swin2-GTP2_art-caption

Dataset used to train AterMors/Swin2-GTP2_art-caption