Artwork Image Generator is an artificial intelligence model designed to generate artistic images in various styles.

The ViT-S model (Vision Transformer-Small) is a variant of the Vision Transformer architecture, which applies the Transformer model to image recognition tasks. SimPool, short for "Simplified Pooling," is a pooling method designed to aggregate information from the ViT-S model s attention maps and produce a fixed-size representation for downstream tasks.

ZeroShot Image Classification CLIP is a task in the field of machine learning and image processing, aiming to predict the class or label of an image that has not been previously classified, in a dataset that the model has not been trained on with those classes.

Image Restoration is a compute vision task which restoring from the degraded images to clean images.

Prompt Extend is an innovative approach that aims to enhance the capabilities of language models and improve their response generation. It involves extending the initial prompt or query by providing additional context or specifications to guide the model's understanding and generate more accurate and relevant responses.

Jak's Woolitize Image Generator is a text to image task that focuses on applying a woolitize texture and appearance to generated images, creating images that convey warmth.

The goal of Image to Anime was to create a new version of the image that would possess the same clean lines and evoke the characteristic feel found in anime productions, capturing the unique artistry and aesthetics associated with this style.

Extract sections of images from your image by using OpenAI's CLIP and YoloSmall.

Donut consists of a vision encoder (Swin Transformer) and a text decoder (BART). Given an image, the encoder first encodes the image into a tensor of embeddings (of shape batch_size, seq_len, hidden_size), after which the decoder autoregressively generates text, conditioned on the encoding of the encoder.

Pix2Struct is an image encoder - text decoder model that is trained on image-text pairs for various tasks, including image captionning and visual question answering.

The main aim for this dataset is to cover a wide variety of social biases that are implied in text, both subtle and overt, and make the biases representative of real world discrimination that people experience RWJF 2017.

PathVQA consists of 32,799 open-ended questions from 4,998 pathology images where each question is manually checked to ensure correctness.

The goal of information-seeking dialogue is to respond to user queries with natural language utterances that are grounded on knowledge sources.

VQA-RAD consists of 3,515 question–answer pairs on 315 radiology images.

DocRED (Document-Level Relation Extraction Dataset) is a relation extraction dataset constructed from Wikipedia and Wikidata. Each document in the dataset is human-annotated with named entity mentions, coreference information, intra- and inter-sentence relations, and supporting evidence.