No one took text-to-speech seriously for years. Even at its best, it was still obviously fake. That’s about to change. In the next few months, the boundary between interface and identity will begin to dissolve. It will reshape culture, commerce, and consciousness. We'll
MULTIMODAL AI
-
Aria Gen 2 Glasses: Advanced Wearable Technology for Machine Perception Research
By
–
Aria Gen 2 glasses mark a significant leap in wearable technology, offering enhanced features and capabilities that cater to a broader range of applications and researcher needs. We believe researchers from industry and academia can accelerate their work in machine perception,… pic.twitter.com/zbrIh4riZf
— AI at Meta (@AIatMeta) 4 juin 2025Aria Gen 2 glasses mark a significant leap in wearable technology, offering enhanced features and capabilities that cater to a broader range of applications and researcher needs. We believe researchers from industry and academia can accelerate their work in machine perception,
-
Dream Machine adds new video modification features
By
–
The future of filmmaking isn’t about starting over it’s about evolving what you already made. Same shot. Infinite worlds. Try Modify now inside Dream Machine:
-
New production features and presets for Dream Machine AI video generation
By
–
Built for real production use.
— God of Prompt (@godofprompt) 4 juin 2025
✅ Native 16:9, 720p support
✅ Multiple style variants per take
✅ Compatible with Dream Machine Ray 2
✅ Structured presets for precise control
Upload, select a preset, and transform. pic.twitter.com/8e6kBkb2LmBuilt for real production use. Native 16:9, 720p support Multiple style variants per take Compatible with Dream Machine Ray 2 Structured presets for precise control Upload, select a preset, and transform.
-
AI-Powered Motion Capture and Character Re-targeting Workflow
By
–
Motion capture, remixed.
— God of Prompt (@godofprompt) 4 juin 2025
Extract lip-sync, facial, or full-body motion from any clip.
Then apply it to:
A CG creature
A stylized variant
A surreal version of the same character
Real movement, limitless reinterpretation. pic.twitter.com/PajWesiWkyMotion capture, remixed. Extract lip-sync, facial, or full-body motion from any clip. Then apply it to: A CG creature
A stylized variant
A surreal version of the same character Real movement, limitless reinterpretation. -
Luma Labs Dream Machine for AI-powered video editing
By
–
Try it here: https://t.co/XdjLhWwM98
— God of Prompt (@godofprompt) 4 juin 2025
Traditional video edits are broken.
Want to change a scene?
You need:
– New takes
– New renders
– New tools
Modify Video flips that.
Keep the motion. Reimagine the world. pic.twitter.com/fBZcC9t3BBTry it here: https://
dream-machine.lumalabs.ai Traditional video edits are broken. Want to change a scene? You need: – New takes
– New renders
– New tools Modify flips that. Keep the motion. Reimagine the world. -
Dream Machine’s ‘Modify Video’ tool transforms film production workflows
By
–
Hollywood is in serious trouble…
— God of Prompt (@godofprompt) 4 juin 2025
AI just made reshoots, VFX, and green screens completely optional.
Dream Machine’s new tool "Modify Video" can change lighting, style, even the actor without touching the performance.
Here's how it works: pic.twitter.com/tPmitA1IktHollywood is in serious trouble… AI just made reshoots, VFX, and green screens completely optional. Dream Machine’s new tool "Modify Video" can change lighting, style, even the actor without touching the performance. Here's how it works:
-
SketchAgent: AI Research on Visual Generation and Sketch Manipulation
By
–
More details about SketchAgent: https://
bit.ly/43mTme1 Authors: @YVinker
,
@TamarRottShaham
, Kristine Zheng, AlexZhao, Judith E. Fan, & Antonio Torralba -
SketchAgent: LLM-Powered Stroke-by-Stroke Drawing Without Training
By
–
SketchAgent leverages an off-the-shelf LLM to draw stroke-by-stroke w/o training on any data — instead, the researchers developed a "sketching language" in which a sketch is translated into a numbered sequence of strokes on a grid. SketchAgent also provides textual annotations
-
SketchAgent: Multimodal AI Turns Natural Language Into Sketches
By
–
This method, called "SketchAgent," uses a multimodal language model to turn natural language prompts into sketches in a few seconds.
— MIT CSAIL (@MIT_CSAIL) 4 juin 2025
For example, it can doodle a cat either on its own or through collaboration, drawing w/a human or incorporating text-based input to sketch each… pic.twitter.com/3qUBbVQbAeThis method, called "SketchAgent," uses a multimodal language model to turn natural language prompts into sketches in a few seconds. For example, it can doodle a cat either on its own or through collaboration, drawing w/a human or incorporating text-based input to sketch each