SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics SmolVLA is a compact, open-source VLA model built for low-cost training and real-world deployment on consumer hardware, enabling efficient language-driven robot control without sacrificing performance.
MULTIMODAL AI
-
Gen-4 Images: High Fidelity Generation with Stylistic Control
By
–
Gen-4 Images lets you generate high fidelity images with unprecedented stylistic control. (1/6)
-
AI-Generated Short Film Uses ElevenLabs Midjourney Kling and More
By
–
Magnifique court-métrage fais 100% par IA (très court métrage… mais quand même ! )
— VISION IA (@vision_ia) 9 juin 2025
☑️ Voix des personnages : nouvelle Alpha ElevenLabs v3
☑️ Script : ChatGPT
☑️ Images : Midjourney v7
☑️ Vidéo : Kling 2.1 Master, Veo 3, Higgsfield
☑️ Synchronisation labiale : Heygen Avatar IV… https://t.co/NsFAEOyWwcMagnificent short film made 100% by AI (very short film… but still!) Character voices: new Alpha ElevenLabs v3 Script: ChatGPT Images: Midjourney v7 Video: Kling 2.1 Master, Veo 3, Higgsfield Lip synchronization: Heygen Avatar IV Quality enhancement: Magnific
-
Veo 3 Impresses with Advanced Video Generation from Text Prompts
By
–
I'm impressed with how well Veo 3 handled this prompt:
— fofr (@fofrAI) 9 juin 2025
> The video depicts a half length view of a beautiful young woman with subtle brown eyes, and dark eyebrows, she is standing by a wall. A movie is being projected directly onto her. The movie is of an old and beautiful… pic.twitter.com/KZJpolYMh8I'm impressed with how well Veo 3 handled this prompt: > The video depicts a half length view of a beautiful young woman with subtle brown eyes, and dark eyebrows, she is standing by a wall. A movie is being projected directly onto her. The movie is of an old and beautiful
-
Testing Runway Gen3 Prompts on Veo 3 Fast Model
By
–
wait for it
— fofr (@fofrAI) 8 juin 2025
(I'm trying out some of my old Runway Gen3 prompts on Veo 3 fast) pic.twitter.com/G0CjneNKyvwait for it (I'm trying out some of my old Runway Gen3 prompts on Veo 3 fast)
-
AI generates epic dance track blending choir and chiptune
By
–
> a beautiful music track where a chamber choir sings amidst old video game chiptune, to make an epic dance track pic.twitter.com/iVxUuWytbl
— fofr (@fofrAI) 8 juin 2025> a beautiful music track where a chamber choir sings amidst old video game chiptune, to make an epic dance track
-
AI Generated Woman Delivers Emotional Oscar Acceptance Speech
By
–
> A woman gives an oscar acceptance speech. She is standing on a big stage, we can see her whole outfit. She gives an emotional speech thanking the prompt that made her exist. This young woman has striking blue-gray eyes and dark brown hair styled in a casual updo with loose… pic.twitter.com/khu1Rp7v2P
— fofr (@fofrAI) 8 juin 2025> A woman gives an oscar acceptance speech. She is standing on a big stage, we can see her whole outfit. She gives an emotional speech thanking the prompt that made her exist. This young woman has striking blue-gray eyes and dark brown hair styled in a casual updo with loose
-
Veo 3 Adds Advanced Video Audio Scene Ingredients Features
By
–
– all Veo 2 features on Veo 3 (scene ingredients, extension, start image)
– video scene ingredients (like taking a video’s style, audio, movement, direction, etc)
– audio scene ingredients (a voice, voices, music to incorporate)
– different aspect ratios
– 1080p/4k
– video from -
AI Models Predict Career and Academic Success from Facial Images
By
–
Une nouvelle étude affirme que les modèles d’IA peuvent prédire la réussite professionnelle et scolaire à partir d’une seule image du visage d’une personne.
-
AI Brings Old Black-and-White Family Photos to Life in Color Video
By
–
J'ai testé sur des photo de famille. C'est bluffant…
Je l'ai ensuite passé à une IA pour en faire une vidéo… incroyable les vielles photos en noir et blanc prennent vie en vidéo en couleur