🎨 Image & Video Generation

Generative AI for images, video, and creative media — Sora, DALL·E, Midjourney, Stable Diffusion, and more.

1,210 articles

Multiverse Computing releases Comet 60B, a slimmed-down open-source multimodal model

Multiverse Computing has launched Comet 60B, an open-source multimodal AI model. It reduces the total parameter count of Nvidia's Nemotron 3.5 Super VL. Source: theaiinsider.tech

Crun AI debuts leaderboard ranking LLM, video, image and audio models

Crun AI has launched a leaderboard that lets users compare leading models across LLM, video, image and audio categories. Models are ranked side by side on both performance and price. Source: financialcontent.com

Adobe Firefly explained: inside Adobe's AI-native platform

Although the AI boom took off in 2022–2023, Adobe's experiments with AI reach back much further, roughly a decade. The piece offers an overview of Adobe Firefly and what it means for the company's AI strategy. Source: dailypioneer.com

Top 10 AI video generators favored by marketing agencies and brand teams

The article presents a list of ten AI video generators trusted by marketing agencies and brand teams. The source snippet itself contains only generic site boilerplate about The Hype Magazine. Source: thehypemagazine.com

A Workflow for Putting Readable Text Into AI-Generated Video

AI video models still tend to garble any text that appears on screen. The author shares the title-card and in-world text workflow used on the Lost Garden project to keep lettering from turning into gibberish. Source: hackernoon.com

Black Forest Labs Releases FLUX 3 Image Klein With Open Weights

Black Forest Labs (BFL), the Freiburg-based AI research lab focused on visual intelligence, announced on Oct. 15, 2026 that it is releasing FLUX 3 Image Klein with open weights. The move widens access to its frontier visual models. Source: markets.businessinsider.com

NVIDIA Launches Nemotron 3.5 Super VL, a 120B Open Multimodal Model

NVIDIA has released Nemotron 3.5 Super VL, an open vision-language model designed for always-on enterprise agents. The model has 120 billion parameters. Source: marktechpost.com

Turning Product Photos Into Video Ads With Nano Banana 2.1 and Vidu Q4

Static product photos can feel repetitive across store listings, social media, and paid ads. The article explains how AI tools, here Nano Banana 2.1 and Vidu Q4, can turn those images into video ads. Source: bbntimes.com

SGLang and Miles Offer Day-0 Support for Muse Spark Open

Muse Spark Open is an open-weight multimodal mixture-of-experts model built on an 816B-parameter text transformer backbone. SGLang and Miles support it from the day of release. Source: lmsys.org

TwelveLabs Launches Jockey, an AI Agent That Finds Scenes in Video

TwelveLabs announced on the 16th the official launch of an AI agent called Jockey by TwelveLabs. It acts as an AI secretary that locates scenes in video on its own. Source: mk.co.kr

Seedance 3.0 pushes AI video generation toward feature-length control

Seedance 3.0 stretches single-clip generation to 30 seconds and expands its multimodal reference stack nearly sixfold. It targets creators and marketers building longer video content. Source: startupfortune.com

China clears Alibaba AI models for Apple's iPhone Duo and other handsets

Regulatory approval of Alibaba's AI models opens the door for Apple to finally roll out Apple Intelligence in China. The launch has been stalled for years by regulatory delays. Source: scmp.com

Google unveils Gemini 4 Argon, its latest frontier model

Google is giving developers, enterprises, scientists and consumers access to Gemini 4 Argon, which it describes as its latest frontier model built for tackling hard problems. Source: blog.google

Baseten adds Runway's Gen-4.5 and Aleph 2.0 to its dedicated inference platform

Enterprises can now deploy Runway's Gen-4.5 and Aleph 2.0 video generation and editing models, including fine-tuned variants, in secure single-tenant environments on Baseten. Source: unite.ai

Higgsfield stretches AI video from one minute to more than ten

Higgsfield is giving creators longer clips through GPT-6 Astra, sharper visuals via GPT-Image-2.5, and a route toward voice-driven filmmaking with GPT-Live. Source: openai.com

Qwen-Image-2.1-Turbo on a desktop: BaoCut 3.5 and first local timings

Qwen-Image-2.1-Turbo was released without a formal launch. BaoCut 3.5 now runs it locally on a Mac Mini M2, and the first Mac timings are available. Source: orcarouter.ai

1min.AI lifetime deal: text, image, audio and video in one app for $70

A 1min.AI Advanced Business Plan lifetime license, priced at $70 instead of $540, covers a team of up to 20. It bundles GPT-5.5 Pro, Claude 4.6 Sonnet, Gemini 3.1 Pro and dozens of other AI tools. Source: 9to5toys.com

VSDC 11.3 brings AI video generator, Garmin and DJI telemetry, new templates

VSDC 11.3 widens its AI-assisted creation features and adds sports telemetry tools for action-camera, cycling and drone footage. The update was announced from Sofia, Bulgaria. Source: elpasotimes.com

Pairing AI image and video tools for stronger digital content

High-quality digital content has become a core part of online marketing, brand building and social media growth. The piece looks at how combining AI image and video tools can improve the results. Source: bbntimes.com

We Tested 2026's Top AI Image Generators So You Can Pick the Right One

A hands-on comparison of the biggest creative AI image tools, designed to help you match a generator to your project needs and budget. Source: cnet.com