Piattaforme e modelli AI

Gli utenti iscritti al programma Insider di Windows 11 possono usare una versione di Microsoft Foto che permette di accedere al servizio Designer.

WhatsApp introduce la generazione di immagini AI real time. Gli utenti USA provare la funzione aprendo una chat con Meta AI alimentato da Llama 3.

Dopo una breve fase in beta, l'app Adobe Express è finalmente disponibile per tutti gli utenti Android: è un concentrato di AI generativa.

Google ha rilasciato negli USA due nuove IA generative per la creazione di immagini (ImageFX) e audio (MusicFX). Ecco come provarle gratis dall'Italia

Hugging Face ha appena presentato Idefics2, la nuova versione open source del suo Vision-Language model, con migliori capacità OCR.

Il celebre dipinto di Leonardo Da Vinci ha preso letteralmente viva grazie all'intelligenza artificiale di Microsoft. Si chiama Vasa-1 la tecnologia che consente di animare foto o immagini. Le persone ritratte cantano o parlano con espressioni facciali e labiali quasi perfetti. Vasa-1 non è una IA aperta al pubblico. Microsoft ha diffuso alcuni video - come quello della Gioconda che urla i versi di 'Paparazzi', un brano rap dell'attrice Annna Hathaway - per mostrare le capacità del modello di intelligenza artificiale. a cura di Pier Luigi Pisa

Meta ha confermato di avere in programma un primo rilascio di Llama 3, la prossima generazione del suo LLM, entro il prossimo mese.

OpenAI si prepara a lanciare il nuovo aggiornamento del suo strumento di IA generativa, ChatGPT, con la promessa di miglioramenti sostanziali.

Con il nostro generatore di immagini con IA di alta qualità, puoi liberare tutta la tua creatività e creare immagini di altissima qualità, sicure da usare ai fini commerciali e royalty-free da stampare, inserire nei tuoi post sui social o in promozioni online

Discover amazing ML apps made by the community

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Learn step-by-step on how to create a dataset, train your custom model and generate images

More creativity, less searching for stock imagery. Introducing Text to Texture, now available in #Substance3DSampler (beta). #Substance3D #AdobeFirefly

A graphic design app that helps you create professional quality social media posts, invitations, digital postcards, graphics, and more. Start with your idea and create something unique for you.

Thanks for watching me ramble on, just to recap my process is outlined below followed by the links in operation order. Please subscribe if you'd like to see ...

Dive into the fun with AI! Generate images, edit details, composite VFX, expand borders, and explore even more possibilities! Read more about Stable Diffusion 3: https://stability.ai/news/stable-diffusion-3-research-paper 🔥 Black Mixture Discord: https://discord.gg/n2N7Hgvn7n My Favorite Motion Graphics Assets, Plugins, Templates, and MORE!! 🔌⚡ AEJUICE: https://bit.ly/aejuicebundlesale Instant 3D Models from Text Prompts: https://meshy.ai/ Before you get creating, make sure you hit the subscribe button because I may go over helpful tips and tricks in a future tutorial. Or just hit the subscribe button because you liked the video and appreciate free videos😉. If you like what we're doing and want to support: https://www.youtube.com/channel/UCOwFX-YFktXxEIX7-IPjlKQ/join Follow on IG: @blackmixture

Find out more about AI Animation, and register as an AI creative for free at https://aianimation.comThis video is an in-depth tutorial, where I take you thro...

I troppi errori commessi da gemini hanno convinto Google a bloccare la generazione di immagini di persone di Gemini, la sua intelligenza artificiale generativa.

null

Factorizing Text-to-Video Generation by Explicit Image Conditioning

🗞️ The visual daily newsletter on business and tech. 📈 Analyzing the news with 1 visual per story. 👇 Join our 250,000+ subscribers here.

Meta's new AI tools, Emu Edit and Emu Video, are set to redefine the landscape of digital creativity, offering unprecedented control in image editing and a novel approach to video generation.

Today marks the launch of Stable Cascade in its research preview. This innovative text to image model introduces an interesting three-stage approach, setting new benchmarks for quality, flexibility, fine-tuning, and efficiency with a focus on further eliminating hardware barriers.

This time we are going back to basics! This is a deep dive into how ComfyUI and Stable Diffusion works. It's more than a basic tutorial, I try to explain how Comfy works underneath. Please note that this is a test video, let me know what you think and it you'd like me to publish more videos like this together with my usual content. Debug node is part of the comfyui essentials: https://github.com/cubiq/ComfyUI_essentials Discord server: https://discord.com/invite/W2DhHkcjgn 00:00 Intro 00:28 The Checkpoint 04:19 The Clip 04:50 The KSampler 06:43 Samplers and Schedulers 11:03 Conditioning 12:21 Conditioning Concat 13:08 Conditioning Combine 14:08 Conditioning Average 15:42 Timestepping 17:08 Texture inversion and Word weighting 18:02 Unet Clip VAE loaders 19:51 Outro

Manually Install ComfyUI on Linux or Windows

In this video I'm going over the easiest way to install ComfyUI on a windows computer as well as some tips and tricks to make your life easier. Github https://github.com/comfyanonymous/ComfyUI Civitai Model https://civitai.com/models/4823/deliberate ComfyUI Manager https://civitai.com/models/71980/comfyui-manager 0:00 Beginning 2:02: Getting Model 2:42 Pulling Models and more from other places on your computer 5:04 Basic Workflow 7:19 Hi Res Fix workflow 9:24 Install Comfy Manager 11:44 Extra Tips and Tricks

How To Install ComfyUI And The ComfyUI Manager. For those of you who want to get into ComfyUI's node based interface, in this video we will go over how to install ComfyUI and the ComfyUI manager which will be needed for future videos. It's a pretty simple process that anyone can follow. Please make sure to download all these files Git https://git-scm.com/downloads ComfyUI https://github.com/comfyanonymous/ComfyUI ComfyUI Manager https://github.com/ltdrdata/ComfyUI-Manager 7-Zip https://7-zip.org/ Models Stable Diffusion 1.5 https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main CivitAI https://civitai.com/models ⏲Time Stamps 0:00 Intro 0:14 Install Git 1:00 Install ComfyUI 3:20 Download models 4:15 Intro to the ComfyUI Interface 6:16 How to install the ComfyUI Manager 7:35 Interface options 8:40 How to install custom nodes 10:14 Redirect existing models to ComfyUI 11:47 What's next? **Disclaimer Affiliate Links Below** 📸 Gear I use Sony A7C CAN https://amzn.to/3spWX8C Sony 35mm 1.8 CAN https://amzn.to/36Apekr OBS (FREE) https://obsproject.com/ Editor Davinci Resolve https://www.blackmagicdesign.com/ca/products/davinciresolve/ Audio: Rode Podmic https://amzn.to/35sSnxv 🎵 Epidemic Sound 🔦 Find us on: Discord: https://discord.gg/Z6GEsyxd4V Instagram: https://www.instagram.com/monzonmedia/ Facebook: https://www.facebook.com/MonzonMedia