A technical dive inside our new "Midjourney Scanner" pic.twitter.com/wJBHz2O7ro
— Midjourney (@midjourney) 18 juin 2026
A technical dive inside our new "Midjourney Scanner"
MULTIMODAL AI
-
Technical dive inside the new Midjourney Scanner
By
–
-
Fei-Fei Li: Spatial Intelligence in the AI Model War
By
–
"The World's AI Model War" (Not that we need another AI war)
https://fastcompany.com/91549046/fei-fei-li-world-labs-ai-gets-physical-models-spatial-intelligence
… @FastCompany
with the profile
@drfeifei -
3 years of AI progress: Modelscope vs Grok Imagine 1.5
By
–
3 years of AI progress! Incredible 😍
— Amitav Bhattacharjee (@bamitav) 18 juin 2026
Modelscope (left), Grok Imagine 1.5 (right)#AIart️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️ #AIartwork #AIvideo #grok #AI #artificialintelligence @AlbertoEMachado @Eli_Krumova… pic.twitter.com/VfMZpskwqq3 years of AI progress! Incredible Modelscope (left), Grok Imagine 1.5 (right) #AIart️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️️ #AIartwork #AIvideo #grok #AI #artificialintelligence @AlbertoEMachado @Eli_Krumova
-
Seedance 2.5 arrives in early July, no model equals it
By
–
Holy shit: Seedance 2.5 arrives early July. And no text-to-video model has even come close to Seedance.
-
Runway API Launches Recipes for One-Call Generative Media Features
By
–
New on the Runway API: Recipes.
— Runway (@runwayml) 17 juin 2026
Drop production-ready generative media features into your platform, with one API call. Recipes are Runway-built endpoints with our prompting and workflow expertise packaged in. Polished results, without building or maintaining the workflow… pic.twitter.com/mpVolrNL6sNew on the Runway API: Recipes. Drop production-ready generative media features into your platform, with one API call. Recipes are Runway-built endpoints with our prompting and workflow expertise packaged in. Polished results, without building or maintaining the workflow
-
SAM 1/2/3 pods discussion: concepts and intent in videogen
By
–
see our SAM 1/2/3 pods with @nikhilaravi and @josephofiowa
, the rise of concepts is definitely part of it, although imo "intent" is more of a videogen problem (see our @EthanHe_42 pod) than pure CV -
Fable uses ThreeJS and GPT-Realtime-2 for interactive kid experience
By
–
Under the hood, Fable generates the world with ThreeJS, and GPT-Realtime-2 lets the kid answer out loud, ask questions, etc. As you can see, there are still small issues and paper-cuts throughout (it's a POC!), but the possibility of what this could become is absolutely insane!
-
AI can create new things, not just watchable films
By
–
Just saw another guy write "AI can't create compelling movies."
— Robert Scoble (@Scobleizer) 17 juin 2026
While Elon says that by the end of the year Grok will make "watchable films" by the end of the year.
Misses the whole point.
We can use AI to do new things now. Like @cbdoane did here. Just added to my AI video… https://t.co/FhznSWJI4UJust saw another guy write "AI can't create compelling movies." While Elon says that by the end of the year Grok will make "watchable films" by the end of the year. Misses the whole point. We can use AI to do new things now. Like @cbdoane did here. Just added to my AI video
-
An AI-native email platform integrated with Codex and MCP agents
By
–
An AI native email platform built from the ground up to run entirely from inside Codex, ChatGPT, and any AI agent via MCP.
— Robert Scoble (@Scobleizer) 17 juin 2026
Your agents now have their own email.
And it learns and gets better over time. https://t.co/UPRwAKxEw3An AI-native email platform built from the ground up to run entirely from inside Codex, ChatGPT, and any AI agent via MCP. Your agents now have their own email. And it learns and gets better over time.
-
Example outputs from Midjourney, NBP, ChatGPT Image 2
By
–
Example outputs,
Midjourney, NBP, ChatGPT Image 2. Full prompts in alt.