Browse deepinfra models:

All categories and models you can try out and directly use in deepinfra:
Search

Category/all

shibing624/text2vec-base-chinese cover image
512
$0.005 / Mtoken
  • embeddings

A sentence similarity model that can be used for various NLP tasks such as text classification, sentiment analysis, named entity recognition, question answering, and more. It utilizes the CoSENT architecture, which consists of a transformer encoder and a pooling module, to encode input texts into vectors that capture their semantic meaning. The model was trained on the nli_zh dataset and achieved high performance on various benchmark datasets.

stabilityai/stable-diffusion-2-1 cover image
$0.0005 / sec
  • text-to-image

Stable Diffusion is a latent text-to-image diffusion model. Generate realistic images given text description

thenlper/gte-base cover image
512
$0.005 / Mtoken
  • embeddings

The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval, semantic textual similarity, text reranking, etc.

thenlper/gte-large cover image
512
$0.010 / Mtoken
  • embeddings

The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval, semantic textual similarity, text reranking, etc.

uwulewd/custom-diffusion cover image
$0.0005 / sec
  • text-to-image

Stable diffusion with the ability to change checkpoint, still wip.