Generative AI for images, video, and creative media — Sora, DALL·E, Midjourney, Stable Diffusion, and more.
992 articles
Researchers built a zero-shot AI framework that transfers the camera motion from a single reference video onto any static image. The approach is aimed at making such camera work accessible to non-experts. Source: bioengineer.org
The Clef decision model family is growing with Clef-omni, which natively handles audio, video, images, and text in a single pipeline. The lineup also gains a faster Clef and a lower-cost Clef-flash variant. Source: blog.cloudflare.com
Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-GGUF is a text-to-text GGUF release designed to run locally. It comes with native text, image, and video capabilities. Source: hackernoon.com
ChatGPT's image generation can turn text prompts, sketches, or uploaded images into branded visuals and product mockups. The feature is pitched as a quick way to produce consistent, brand-aligned creative assets. Source: openai.com
Qwen Image 2.1 Turbo supports both image generation and editing in just eight steps. Its weights are released under a research-only license, while a newly live API is available with verified pricing. Source: kingy.ai
Nikon said it stripped the winner of its Small World in Motion competition of the title because of how AI was used in his entry. The decision has sparked controversy around the contest. Source: nytimes.com
New data from Overchat AI indicates users pick Chinese AI models more often than Western ones when creating images and videos. The findings were published on October 8, 2026. Source: natlawreview.com
Magnific announced Magnific One on October 8, 2026, an image generation model that the company says decides a picture's art direction before rendering it. Source: unite.ai
Google has unveiled a detector tool that checks whether an image, text, video or audio file was produced with AI. It turned up an enormous volume of AI-generated music. Source: independent.co.uk
Magnific One centralizes brand guidelines, flags deviations and lets employees correct outputs. The approach could make AI image generation far more practical for company teams. Source: venturebeat.com
Rana Hanocka, an AI researcher at the University of Chicago, has launched Thrixel, a platform for generating 3D content. Source: gamesbeat.com
OpenAI is set to test ads woven into one of ChatGPT's most popular tools, image generation, for U.S. users. The company has not disclosed which advertisers will appear. Source: thecooldown.com
The integration brings 4K AI image-to-video generation to YouCam users, with 10-bit color, steadier motion and smoother camera movement across five mobile apps and the online editor. Source: businesswire.com
Pollo AI builds on GPT-5.6, GPT-6 Astra and GPT-Image-2.5 to help creators produce detailed images and cinematic video ads. Source: openai.com
Google is making SynthID Detector available to all users. The tool can identify audio, video and images produced by AI tools from OpenAI, Google and others. Source: pcmag.com
On October 6, Google open-sourced EmbeddingGemma 2, a compact model that can search photos, video and audio without an internet connection. The whole search engine fits into less than 600MB of storage. Source: eu.36kr.com
ShengShu Technology released Vidu Q4 Preview on October 7, 2026, the first public look at its next-generation flagship model. The preview focuses on expressive audio and video generation. Source: unite.ai
Reka announced Rho-1 on October 5, 2026, a 19-billion-parameter research preview. The model understands and generates text, images and video, and extends to robot actions. Source: quasa.io
Google introduced Gemini Nano Banana 2.1, a new model for generating and editing images. It supports 1K, 2K and 4K resolutions. Source: root-nation.com
Google DeepMind's EmbeddingGemma 2 brings text, image, video and audio search to consumer devices. It needs less memory and depends less on cloud AI. Source: techrepublic.com