Generative AI for images, video, and creative media — Sora, DALL·E, Midjourney, Stable Diffusion, and more.
487 articles
Aurora Mobile (NASDAQ: JG) announced that its Modellix.ai platform has integrated ShengShu Technology's Vidu Q3 video generation model and launched Vidu... stocktitan.net
Video creation used to begin with a camera. Today, it can begin with a sentence. With AI video generators, creators can turn simple text prompts into short... technology.org
meshyai #Quasa #QUA Meshy AI (featured on Quasa.io/projects/meshyai) is one of the fastest and most powerful AI 3D model generators in 2026. It turns text... quasa.io
SINGAPORE, June 15, 2026 (GLOBE NEWSWIRE) -- Aurora Mobile Limited (NASDAQ: JG) (“Aurora Mobile” or the “Company”), a leading provider of customer... globenewswire.com
Mirage, a video world model from Microsoft Research and several universities, stores scene information directly in latent space instead of pixel-based point... the-decoder.com
Google's Gemini Omni brings conversational video editing into Flow, Flow Music, Gemini and YouTube Shorts. The real test is whether Google can make AI. startupfortune.com
Elon Musk just told his 200M+ followers to try the latest Grok Imagine — and if you haven't checked in recently, you've missed a lot. xAI's image and video... basenor.com
Avataar AI's distilled video model is priced at $0.005 for every second of generation. techcrunch.com
AI image generation statistics 2026: 24B Firefly assets, Midjourney 19.83M users, market share, copyright rulings, deepfake fraud data. sqmagazine.co.uk
Addressing this demand, CapCut has introduced its latest iteration in creative technology, positioning the Dreamina Seedance. thehypemagazine.com
Google's Gemini Omni Flash ranks first in Video Arena for text-to-video and image-to-video, surpassing competitors with multimodal editing capabilities. cryptobriefing.com
Creating video content traditionally requires editing skills, production tools, and significant time investment -- Pika Labs AI is an AI-powered video… trendhunter.com
Google DeepMind released DiffusionGemma on June 10, an open-weights 26-billion-parameter model that uses diffusion instead of autoregressive decoding to... mlq.ai
In this comprehensive MidJourney review, discover exactly how much it costs, explore its AI image generator features, and find the best plan. ventureburn.com
Google DeepMind has added an unusual sibling to its Gemma 4 open model family. DiffusionGemma, released on June 10, abandons the word-by-word generation... technology.org
Martin Scorsese signed on last year as a partner and adviser to **Black Forest Labs**, according to The New York Times, and appears in a company video using... letsdatascience.com
Google's new experimental open model swaps token-by-token decoding for parallel text diffusion, targeting local, low-latency, single-user GPU workloads. marktechpost.com
NVIDIA has unveiled a new physical AI agent that can help researchers with data generation, simulation & evaluation for autonomous systems development. aimagazine.com
Apple added native photorealistic image generation to Image Playground at WWDC 2026, bringing photo-realistic AI-created images to the app for the first... appleinsider.com