multimodal

🔮 Build multimodal AI services via cloud native technologies · Neural Search · Generative AI · Cloud Native

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

🪩 Create Disco Diffusion artworks in one line

SDK for interacting with stability.ai APIs (e.g. stable diffusion inference)

notes for software engineers getting up to speed on new AI developments. Serves as datastore for lspace.swyx.io writing, and product brainstorming, but has cleaned up canonical references under the /Resources folder.

In-App assistant SDK to build a multimodal conversational UX for websites and web apps (JavaScript, React, Angular, Vue, Ember, Electron)

🧬 The data structure for multimodal data · Neural Search · Vector Search · Document Store

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

In-App assistant SDK to build a multimodal conversational UX for iOS applications (Swift, Objective-C)

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

In-App assistant SDK to build a multimodal conversational UX for Android applications (Java, Kotlin)

In-App assistant SDK to build a multimodal conversational UX for applications created with Flutter (iOS and Android)

In-App assistant SDK to build a multimodal conversational UX for applications created with Ionic (React, Angular, Vue)

Transformers at any scale

Easily compute clip embeddings and build a clip retrieval system with them

A curated list of Multimodal Related Research.

In-App assistant SDK to build a multimodal conversational UX for Apache Cordova applications

WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.