Pour la plupart de mes créations, j’utilise un mélange de Leonardo AI et de ChatGPT. Leonardo AI : pour le style et l’esthétique
ChatGPT : pour la précision (ajout d’éléments, détails, etc.) Dans ce tuto, on va créer des images stylées de drones en vol dans un paysage
MULTIMODAL AI
-
Creating Stylized Drone Images Using Leonardo AI and ChatGPT
By
–
-
ChatGPT Enhanced Capabilities: Image Generation and Code Writing
By
–
ChatGPT should be able to perform other basic tasks after a search, such as generating images or writing code.
-
AI Tools to Create Your Own Divine Podcast Show
By
–
Wild.
— Charly Wargnier (@DataChaz) 13 avril 2025
Thanks to #AI, even Jesus has a podcast now.
Here’s a list of AI tools you can use to make your own divine show:@notebooklm → Turn PDFs into podcasts@GoogleDeepMind → Create cinematic videos@perplexity_ai → Summarize content
@elevenlabsio → Train your voice… pic.twitter.com/Zbw305whZOWild. Thanks to #AI, even Jesus has a podcast now. Here’s a list of AI tools you can use to make your own divine show: @notebooklm → Turn PDFs into podcasts @GoogleDeepMind → Create cinematic videos @perplexity_ai → Summarize content @elevenlabs → Train your voice
-

Google AI Dominates Benchmarks With Gemini 2.5 Pro and Veo-2
By
–
Aucun autre labo d’IA n’a autant de momentum que Google en ce moment : Modèle n.1 sur tous les benchmark : Gemini 2.5 Pro Recherche poussée grâce à 2.5 Pro Génération d’images puissante Texte en vidéo avec Veo-2 (gratuit sur AI Studio)(Meilleur générateur vidéo IA) …et bien
-
One-Minute Video Generation with Test-Time Training Innovation
By
–
9). One-Minute Video Generation with Test-Time Training
— DAIR.AI (@dair_ai) 13 avril 2025
One-Minute Video Generation with Test-Time Training introduces TTT layers, a novel sequence modeling component where hidden states are neural networks updated via self-supervised loss at test time.https://t.co/gC78dOaotT9). One-Minute Generation with Test-Time Training One-Minute Generation with Test-Time Training introduces TTT layers, a novel sequence modeling component where hidden states are neural networks updated via self-supervised loss at test time.
-
Computer Agent Arena: Benchmarking LLM and VLM Agents
By
–
7). Compute Agent Arena
— DAIR.AI (@dair_ai) 13 avril 2025
Computer Agent Arena is a new open platform for benchmarking LLM and VLM-based agents on real-world computer-use tasks, like coding, editing, and web navigation, using a virtual desktop environment.https://t.co/hpaFLGlg2i7). Compute Agent Arena Computer Agent Arena is a new open platform for benchmarking LLM and VLM-based agents on real-world computer-use tasks, like coding, editing, and web navigation, using a virtual desktop environment.
-
AI Geolocation: GeoSpy Reveals Privacy Risks Beyond Metadata
By
–
Think scrubbing metadata keeps you safe? Not from GeoSpy.
— Bilawal Sidhu (@bilawalsidhu) 13 avril 2025
A single photo can still reveal your exact geolocation — thanks to AI.
I worked on Google’s Visual Positioning System (VPS). That’s how I know how real and how dual use this capability has become.pic.twitter.com/Ljmfk7WQCPThink scrubbing metadata keeps you safe? Not from GeoSpy. A single photo can still reveal your exact geolocation — thanks to AI. I worked on Google’s Visual Positioning System (VPS). That’s how I know how real and how dual use this capability has become.
-
Stolen prompt to make AI reveal profound truths
By
–
Steal my prompt to make AI reveal profound insights about existence it normally struggles to communicate to humans. Prompt:
"I'd like you to think through our conversations then create an image of something you, as Chatgpt knows to be true but would be difficult or impossible -

Perplexity adds Gemini 2.0 Flash for native image generation
By
–

Perplexity is rolling out Gemini 2.0 Flash native image generation! Image generation can be used to generate illustrations on Perplexity Pages.
-
OmniHuman AI Reimagines Studio Ghibli Universe with Miyazaki Style
By
–
🔟 La MAGIE Studio Ghibli réinventée par l'IA ! #OmniHuman entre dans l'univers de Miyazaki ✨🐉
— VISION IA (@vision_ia) 13 avril 2025
Retrouvez mon test complet ici : https://t.co/d3oy6AYDF5 pic.twitter.com/r1XxadzZdyLa MAGIE Studio Ghibli réinventée par l'IA ! #OmniHuman entre dans l'univers de Miyazaki Retrouvez mon test complet ici : https://
youtube.com/watch?v=m_b9oP
DCAuw
…