Highlights💡 

CoDi: Any-to-Any Generation via Composable Diffusion [Paper], [Source code]

• Composable Diffusion (CoDi) is a novel generative model capable of generating any combination of output modalities.

• CoDi can generate language, image, video, or audio from any combination of input modalities.

• Unlike existing generative AI systems, CoDi can generate multiple modalities in parallel and is not limited to specific input modalities like text or image.

• CoDi aligns modalities in both the input and output space, even when training datasets for certain combinations of modalities are unavailable.

• The alignment in both input and output space allows CoDi to freely condition on any input combination and generate any group of modalities.

• CoDi employs a composable generation strategy by building a shared multimodal space through alignment in the diffusion process.

• This enables the synchronized generation of intertwined modalities, such as temporally aligned video and audio.

• CoDi is highly customizable and flexible, achieving strong joint-modality generation quality.

• CoDi outperforms or is on par with the unimodal state-of-the-art for single-modality synthesis.

MMS - Scaling Speech Technology to 1000+ languages [GitHub], [Announcement]

• Can do speech2text and text speech in 1100 languages.

• Can recognize 4000 spoken languages.

• Code and models are available under the CC-BY-NC 4.0 license.

• Half the word error rate of Whisper.

Tools & Links 🛠️

• GirlfriendGPT - Your personal AI companion [GitHub]

  • Custom Voice: Utilize EleventLabs to create a unique voice for your AI model.

  • Connected to Telegram: Directly send and receive messages from your AI companion via Telegram.

  • Personality: Customize the AI's personality according to your preferences.

  • Selfies: AI is capable of generating SELFIES when asked.

• Zeda.io - AI-powered product discovery for customer-focused teams [Link]

• SuperAgent - Deploy LLM Agents to production [Link]

• ChuckGPT AI - Create a meme using AI [Link]

• CodiumAI v6.0.0 - VS-Code Extension to Enhancing Your Code Quality [Link]

  • Auto-Generate a Suite of Tests –

  • Bug Identification and Fixes

  • Test Generation for Code Diff

  • Code suggestions

  • Run your tests

  • Custom test creation

  • and more features

• BarGPT - An Artificial Intelligence powered bartender. [Link]

• Vest - Stock Analysis made easy with AI. [Link]

• DreamBox AI - Turn your AI Designs into Physical Products. [Link]

• ZBrain - Build ChatGPT Apps With Private Data in Minutes [Link]

• DiagramGPT - Draw different kinds of diagrams using the power of GPT [Link]

• Mysteries AI - Play detective and figure it out! [Link]

• Kandinsky-2 - text2img model trained on LAION HighRes and fine-tuned on internal datasets [GitHub], [Demo]

• FaceSwap for consistent characters in Midjourney. [Link]

• Use Google Lens in Chrome to find similar real-life items for your AI-generated image! [Link]

• OpenAI - Governance of superintelligence [Link]

Unclassified 🌀 

• Fiverr - Find the right freelance service, right away [Link]

• WFH.Team - Work from anywhere in the world [Link]

• Add your link here ➜

Hope you enjoyed today's newsletter!

Brought to you by eeeziii

Did you know you can add Superpower Daily to your RSS feed https://rss.beehiiv.com/feeds/GcFiF2T4I5.xml

⚡️ Check out our Superpower ChatGPT extension on Chrome Web Store and Mozilla Add-Ons Page.