April 4th, 2023

TALES OF TOMORROW

ISSUE #5

Hey there!

Welcome to Tales #5, the newsletter that brings you a game-changing AI model for the audio industry, the latest Midjourney updates, a chance to partner with Runway on their Gen-1 development, and: a Flamingo.

Yep, once again a nice little list of exciting news and opportunities in the field of AI-powered creative storytelling. 🚀

Have fun exploring!

🗞️ Latest Updates

Introducing Niji V5: Midjourney's Updated Anime-Trained Model

​Midjourney has been hard at work refining the Niji model, a model specifically tuned for anime aesthetics. It's basically V5 for anime and early results are nothing short of fantastic!

Get started with Niji V5 by simply adding "--niji 5" to your prompts. Niji V5 also comes with new "stylize" and "aspect ratio" settings, check them out here.

Left: old Niji model, right: Niji V5

​
Apply Now: Runway Looking For Creatives To Test Gen-1 Custom Characters & Styles

Runway announced that they are looking to partner with a few folks to test gen-1 models for custom characters or styles. If you have a use case for that and would like to be part of the early test, check out their application form here.

Meanwhile, Runaway already opened public access to Gen-1 and announced that Gen-2 will soon enter the alpha test phase. No kidding, there is a certain possibility that Runway (who was an early developer of Stable Diffusion) will reshape the online video landscape within the next few months.

Trist @tristwolff 1/ 🚀 Runway's groundbreaking #Gen1 is here! @runway has the tech, the network, and the community to reshape the online video landscape. Here's why we should get ready... 🧵👀 pic.twitter.com/B6K0OdlyKj March 28th 2023 3 Retweets 28 Likes

​

🔦 Project Spotlight

AUDIT: The Future Of Audio Editing?

AUDIT is an instruction-guided audio editing model based on latent diffusion models. You read that right! Audio editing with text prompts. Results are top-notch across multiple audio editing tasks. This has the potential to crush the audio industry. It's not publicly available yet but you can check it out here.

Get A Glimpse At ChatGPT Plugins with TheSamurai.AI

With an OpenAI key, you can use TheSamurai.AI's web app and check out some of the upcoming ChatGPT plugins (Code Interpreter, Google Search, Wolfram Alpha, and Klarna)
​

🔬 Paper corner

Flamingo: The All-Purpose Visual Language Model

Flamingo is a highly effective and efficient model family designed for image and video understanding tasks, with minimal task-specific examples required. The team behind Flamingo released data showing its exceptional performance that could open the door to a wide range of possibilities, including visual assistants that support users in daily life.

​

Kandinsky 2.1: Enhanced Text & Image Integration

Kandinsky comes with a new approach building on DALL-E, diffusion models and CLIP increasing the visual performance. You can try it via this Hugging Face demo.​
​

What else?

A new Midjourney feature brings fresh possibilities for AI artists and designers, Decktopus offers AI-generated presentations and GPT4All brings GPT-3'ish capabilities to your laptop.

​

Twitter Wisdom

We hope you enjoyed reading Tales Of Tomorrow and found some inspiration! 😊 If so, please share "Tales Of Tomorrow" on Twitter.

Also, if you want your project featured or if there is a topic you would like us to cover, please don't hesitate to reply to this email - don't be shy, we would love to hear your feedback and do our best to include your wishes in issue #5!

Until then, keep creating! ❤️

Peace.

Tristan

113 Cherry St #92768, Seattle, WA 98104-2205
​Unsubscribe · Preferences​