Word from Google is that this isn't supported by the model yet. So those aspect ratios probably aren't native Veo 3 but some sort of post processing
MULTIMODAL AI
-
Netflix AI Embeds Personalized Ads Directly Into Content
By
–
¿Te imaginas ver anuncios que parezcan parte de tu serie favorita? Netflix lo hará real 🚨
— Juan Merodio (@juanmerodio) 10 juin 2025
En 2026 Netflix lanzará una IA que incrusta publicidad directamente en películas y series, adaptando mensajes según tus intereses y momento vital pic.twitter.com/V6zKfp1wsH¿Te imaginas ver anuncios que parezcan parte de tu serie favorita? Netflix lo hará real En 2026 Netflix lanzará una IA que incrusta publicidad directamente en películas y series, adaptando mensajes según tus intereses y momento vital
-
How to create a talking avatar for your AI influencer
By
–
Votre influenceuse IA peut parler :
— Jouhatsu | AI Influence Operator (@Jouhatsu_ai) 10 juin 2025
Vous pouvez également créer des avatars parlants sur Apob comme je l'ai fait ici.
Voici comment :
1. Accédez à votre profil d'influenceur IA
2. Cliquez sur « Avatar parlant »
3. Sélectionnez une image que vous avez générée
4. Téléchargez un… pic.twitter.com/tQh5lWpSuTYour AI influencer can talk: You can also create talking avatars on Apob as I did here. Here's how: 1. Go to your AI influencer profile 2. Click on 'Talking Avatar' 3. Select an image you generated 4. Upload a
-
Transform your images into video with AI, try for free
By
–
Image en Vidéo
— Jouhatsu | AI Influence Operator (@Jouhatsu_ai) 10 juin 2025
Sélectionnez votre image de base et appuyez sur "Générer".
Préparez-vous à booster votre activité grâce à votre modèle IA !
Essayez Gratuitement : https://t.co/LSPCvAt7eO pic.twitter.com/n4xBT1NXOZImage to Select your base image and press "Generate". Get ready to boost your business with your AI model! Try for Free:
https://mega.apob.ai/Jouhatsu2 -
Live Voice Mode Becomes Essential AI Companion Planning Tool
By
–
I didn’t realize how much I loved live voice mode until ChatGPT and Claude broke. It is now a staple of my morning routine (when things aren’t all on fire and I have time to think) to companion plan.
-
LLaVA-1.5: Building State-of-the-Art AI Visual Assistants
By
–
Ever wondered how a state-of-the-art AI visual assistant is actually built?
— Satya Mallick (@LearnOpenCV) 10 juin 2025
Our new technical deep dive breaks down the LLaVA-1.5 architecture, its groundbreaking Visual Instruction Tuning, and the open-source datasets that changed the game for multimodal AI.
A must-read for… pic.twitter.com/USfjcJ8fkeEver wondered how a state-of-the-art AI visual assistant is actually built?
Our new technical deep dive breaks down the LLaVA-1.5 architecture, its groundbreaking Visual Instruction Tuning, and the open-source datasets that changed the game for multimodal AI. A must-read for -
Retro Diffusion Plus: Upgraded Pixel Art AI Model
By
–
New: Retro Diffusion Plus! Specializing in high-quality pixel art, this upgraded model offers 11 new styles, improved prompt accuracy, and enhanced image clarity. You can choose any style or customization options using the ‘Additional input’ button below the chat. (1/2)
-
Multimodal Reasoning Emerges from Online RL Training
By
–
We also found that multimodal reasoning capabilities emerge naturally after online RL (even when RL is only done on math & code text data), as long as you start from an initial multimodal model.
-
Krea 1 Artist Program Results Showcase
By
–
here are some Krea 1 results from folks on our Artist Program. these ones are from @edbyus
-
Krea 1 Supports 1.5K Native Resolution and 4K Upscaled
By
–
Krea 1 supports 1.5k native resolution and up to 4k upscaled.