MULTIMODAL AI

→ View original post on X — @rachelmetz

Curiosity about Bard’s image captioning capabilities and potential risks

By

@rachelmetz

–

10 May 2023 19h24

ok honestly i'm v curious to see what kinds of captions bard comes up with for images… this could be useful but also it could go sideways in so many ways.

→ View original post on X — @nathanbenaich

Meta AI’s Angela Fan Presents Text Generation Research in London

By

@nathanbenaich

–

10 May 2023 18h49

Welcoming @MetaAI 's Angela Fan at The Research and Applied AI Summit on June 23 in London! Angela focusses on research in text generation, including her recent work on No Language Left Behind and Universal Speech Translation for Unwritten Languages.

Extensible AI Tool with Multimodal Built-in Capabilities

By

–

10 May 2023 18h26

It comes with built-in tools: • Document QA
• Speech-to-text and Text-to-speech
• Text {classification, summarization, translation, download, QA}
• Image {generation, transforms, captioning, segmentation, upscaling, QA}
• Text to video It is EXTENSIBLE by design.

Transformers Agents: Democratizing ML with Multimodal Control

By

–

10 May 2023 18h25

We just released Transformers' boldest feature: Transformers Agents. This removes the barrier of entry to machine learning Control 100,000+ HF models by talking to Transformers and Diffusers Fully multimodal agent: text, images, video, audio, docs… https://
huggingface.co/docs/transform
ers/transformers_agents
…

Building AI Agents with LLMs for Multimodal Tasks

By

–

10 May 2023 18h25

Create an agent using LLMs (OpenAssistant, StarCoder, OpenAI …) and start talking to transformers and diffusers It responds to complex queries and offers a chat mode. Create images using your words, have the agent read the summary of websites out loud, read through a PDF

→ View original post on X — @waitin4agi_

Turn Action Figures into AI Friends with Raspberry Pi Pico

By

@waitin4agi_

–

10 May 2023 16h48

Raspberry Pi Pico (can access Wi-Fi) + GPT API w/ personality + voice input via Whisper and output via Coqui (and training data) + action figure = make your action figures your friends with a small ‘stick on’.

→ View original post on X — @kirkdborne

Hybrid Image Models: Combining Tabular Data with Vision Intelligence

By

@kirkdborne

–

10 May 2023 16h17

Learn about Hybrid Image Models at https://
abacus.ai/vision_hybrid by @abacusai What is a Hybrid Model? Combines your tabular data with images to extract powerful insights. Improves model performance by overlaying structured data with unstructured vision data. Applies

→ View original post on X — @kirkdborne

Abacus AI Deep Learning Computer Vision Solutions

By

@kirkdborne

–

10 May 2023 16h08

@abacusai uses state-of-art #DeepLearning models to solve #ComputerVision problems: • Classification & Detection
• Hybrid Image Models
• Image Segmentation You bring your images, and they take care of the rest. http://
abacus.ai/vision
——
#AI #MachineLearning #DataScience

JAX Diffusers Sprint Winners Showcase ControlNet Applications

By

–

10 May 2023 13h24

Announcing the winners of JAX Diffusers sprint First place: https://
huggingface.co/spaces/control
net-interior-design/controlnet-seg
… Second place: https://
huggingface.co/spaces/ioclab/
brightness-controlnet
… Third Place: https://
huggingface.co/spaces/vllab/c
ontrolnet-hands
…