New models and features in AI image, video, voice and music generation, from Midjourney, Sora, Veo, Suno and more.
Adobe just launched its Firefly Video Model in beta, bringing text-to-video, image-to-video, and multilingual audio translation into the Firefly web app. The model delivers 1080p clips with keyframe and camera controls, with Adobe highlighting it was trained strictly on licensed content to guarantee commercial safety.
Luma AI just rolled out image-to-video generation powered by Ray 2 inside Dream Machine. Users can drop in virtually any still picture—historical paintings, artifacts, personal photos, or internet memes—and animate them into motion. It is available right now.
Christie’s is hosting its first auction dedicated solely to AI-generated art, spotlighting works trained on artists' own inputs and a robot painting live. But the backlash was immediate: an open letter demanding the auction's cancellation collected over 1,800 signatures in less than 24 hours over copyright and uncredited training data.
Pika just launched Pikaswaps, a new video editing feature that lets creators swap out specific objects, clothing, and backgrounds inside video clips. Users can brush over a target area and replace it using text prompts or reference images, making complex VFX and green screen composites as easy as prompting.
Pika just launched Pikadditions, a new video editing feature that lets you insert any AI-generated person or object into existing footage. Whether it is your own recording or a classic clip, the tool blends elements straight in, and new signups get 15 free generations right out of the gate.
Google just opened up its flagship Imagen 3 image generation model to developers via the Gemini API. Priced at $0.03 per image, it delivers high-fidelity visuals across styles while embedding SynthID watermarks. Paid API users get access first, with a free-tier rollout coming soon.
Spline just introduced Spell, a new diffusion-based AI model capable of generating full 3D environments from a single image in minutes. Outputs can be exported as Gaussian splats, meshes, or video while maintaining realistic multi-view physics and reflections without awkward morphing.
Runway just launched Frames, its new text-to-image generator engineered for high-fidelity, cinematic visuals. Available to Unlimited and Enterprise subscribers, it packs 19 preset styles and lets users seamlessly turn generated stills into video using tools like Gen-3 Alpha Turbo with a single click. Runway is gunning straight for Midjourney's crown.
Black Forest Labs just launched the FLUX Pro Finetuning API, allowing creators to customize flagship FLUX Pro models with as few as 1 to 5 reference images. The custom finetunes reliably preserve unique characters or visual styles at up to 4 megapixels and work seamlessly across the full FLUX tool suite.
Luma AI just released Ray2, its next-gen video model trained with 10x the compute power of Ray1. It brings coherent physics, cinematic camera controls, 1080p output with 4K upscaling, and seamless video extensions up to 30 seconds. It is live now for paid Dream Machine subscribers on web and iOS.
Freepik just launched AI video generation with sound directly inside its AI Suite, supporting multiple modes and formats. Instead of generating silent clips and hunting for soundtracks in separate apps, creators can now get complete audiovisual clips in a single workflow.
Stability AI and NVIDIA just rolled out SPAR3D at CES, turning single 2D images into detailed 3D objects in just 0.7 seconds. The architecture pairs a point diffusion model with a triplane transformer, letting creators edit point clouds and rebuild meshes in 0.3 seconds. Weights are open on Hugging Face for RTX AI PCs.
Polish director Patryk Vega just set his $15M biopic Putin for a Jan 10 premiere across 64 countries. The production used AI visual effects to superimpose the Russian president's real face onto an actor over his body language. Why it matters: It brings deepfake-level AI straight into feature-length cinema, sparking fierce ethical debate along the way.
Midjourney just rolled out Pinterest-inspired moodboards and multi-profile personalization, letting creators train custom aesthetic models directly from curated image collections. Users now only need 40 image ratings to build a profile instead of 200, and can seamlessly switch between distinct named styles for different creative projects.
Google just unveiled Veo 2, a new video model that generates clips up to 4K resolution spanning several minutes while understanding cinematic prompts like lens focal lengths and depth of field. Alongside it, an upgraded Imagen 3 launched globally in ImageFX, also powering a new image-remixing experiment called Whisk. Veo 2 is currently rolling out via a waitlist on VideoFX.
NYU Tisch just partnered with Runway to embed its AI video tools into a new graduate virtual production course this spring. Based at the Martin Scorsese Virtual Production Center, film students will experiment with generative video across the entire workflow, from initial concepting to final thesis projects.
Pika just launched Pika 2.0, upgrading visual fidelity and text alignment across its video generator. The headline update is Scene Ingredients, a new feature allowing creators to upload reference images of people, places, and objects to maintain visual consistency across generated shots.
Manchester City and Puma just launched an AI kit generator powered by DeepObjects, inviting fans to design the club's 2026-2027 third kit. The Puma AI Creator gives users 15 credits to generate virtual jersey concepts and submit up to two entries by December 20th. The winning submission will mark the first AI-generated kit ever worn in an official match.
xAI just rolled out Aurora, a new autoregressive image generation model for Grok on X. Trained on billions of web examples, it tackles notoriously tough challenges like text rendering, logos, and photorealistic portraits, alongside native support for image editing inputs. It is now live in select countries and rolling out to all users within a week.
AMD just released and open-sourced Nitro Diffusion, a pair of one-step text-to-image models based on Stable Diffusion 2.1 and PixArt-Sigma. Trained on AMD Instinct MI250 accelerators, they match full-step visual quality in a single inference step for both data centers and edge PCs. Code and weights are now up on Hugging Face and GitHub.
