Generative AI for images, video, and creative media — Sora, DALL·E, Midjourney, Stable Diffusion, and more.
952 articles
Google's new experimental open model swaps token-by-token decoding for parallel text diffusion, targeting local, low-latency, single-user GPU workloads. Source: marktechpost.com
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... Source: letsdatascience.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... Source: technology.org
NVIDIA has unveiled a new physical AI agent that can help researchers with data generation, simulation & evaluation for autonomous systems development. Source: 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... Source: appleinsider.com
When I finished writing my book, I thought it would be nice to create a short promotional video for it. At first, NotebookLM seemed like the perfect choice. Source: hackernoon.com
Clones Video - Producing presenter-led video content typically requires recording equipment, editing software, and significant production time -- Clones... Source: trendhunter.com
Last year, Nano Banana brought Gemini's intelligence to image generation and editing. Since then, it's helped millions of people restore old photos,... Source: blog.google
AI-generated videos can often suffer from low resolution, visual artifacts, and a lack of fine detail - Astra from Topaz Labs is designed to improve the... Source: trendhunter.com
Google Flow may not help me win an Oscar, but it's a fairly adept filmmaker for those looking to experiment with video generation. Source: au.pcmag.com
Video generation is no longer a matter of luck at last. Source: eu.36kr.com
Becoming a film director used to require significant resources. For many aspiring directors, the gap between imagination and execution was simply too wide. Source: tynmagazine.com
Having trouble getting the right image out of ChatGPT, Gemini, or another AI tool? Follow this prompt for higher-impact results. Source: zdnet.com
Nano Banana Pro (Gemini 3) delivered the strongest overall performance in our testing, combining excellent image quality and text rendering. Source: memeburn.com
Microsoft AI has announced a family of seven in-house models spanning reasoning, coding, image, voice, and transcription, alongside plans to build a... Source: etvbharat.com
The all-in-one platform connects AI video, image, music, templates and effects to help creators and small teams produce multi-format content online. Source: accessnewswire.com
KLING AI 1 - Creating high-quality visual content traditionally requires specialized design skills, video editing expertise, or significant production... Source: trendhunter.com
SINGAPORE, June 5, 2026 /PRNewswire/ -- DomoAI has added Seedance 2.0 to its image-to-video tools, so creators can now turn any image into a short… Source: aapnews.aap.com.au
xAI has released "grok-imagine-video-1.5-preview," an image-to-video model that turns still images into cinematic videos at up to 720p based on text prompts... Source: the-decoder.com
ai labeling - The new AI disclosure labels on YouTube are designed to help viewers quickly identify content that has been created or significantly modified... Source: trendhunter.com