New models and features in AI image, video, voice and music generation, from Midjourney, Sora, Veo, Suno and more.
Alibaba just revealed FashionChameleon, a video framework that lets users interactively swap a moving model's clothes during generation. Running at 23.8 FPS on a single GPU, it keeps motions fluid and identities consistent using clever cache rescheduling. Why it matters: it paves the way for truly interactive virtual dressing rooms in live commerce.
A live-action and AI hybrid film starring Paul Rudd and Chris Rock is set to premiere at the Cannes Film Festival next week. Directed by Dustin Yellin and produced by Darren Aronofsky, the project blends live camera footage with AI generation. It marks one of the highest-profile crossovers of generative video into mainstream cinema yet.
Resemble AI just launched DramaBox, a directable speech model that treats prompts like movie scripts. Text inside quotes becomes dialogue, while everything outside directs the performance—from venomous whispers to mid-sentence giggles and deep sighs. It supports voice cloning, bakes in deepfake-proof watermarks, and is available for local download if you have 24GB of VRAM.
Krea just launched Krea 2, its first proprietary foundation model built completely from scratch. Designed specifically for aesthetic diversity and stylistic control, it marks the company's shift from building wrappers on third-party tech to owning the underlying models. Early access is open now.
Pixal3D just released its pixel-aligned image-to-3D pipeline, generating 3D assets with remarkable geometric precision and texture fidelity. By explicitly projecting 2D pixels into 3D structure rather than relying on loose attention cues, it solves long-standing alignment issues. Why it matters: 3D creators now get assets that actually match the input image close to true reconstruction quality.
Google just revealed Gemini Omni, a native multimodal model capable of reasoning across text, images, and audio to generate and edit coherent video. It introduces conversational video editing with consistent physics, rolling out first as a 10-second Flash model across Shorts and the Gemini app.
Alibaba just introduced Continuous-Time Distribution Matching (CDM), a distillation technique that accelerates image diffusion models down to 4 sampling steps. Unlike predecessors like DMD2 that often produce waxy, over-smoothed results, CDM preserves fine details without complex auxiliary reward models. It brings near real-time, high-fidelity generation to standard GPUs.
Researchers just introduced SwiftI2V, an efficient framework that turns a single image into an 81-frame 2K video. Instead of heavy end-to-end rendering or generic upscaling, it sketches a low-res motion draft first and details it segment-by-segment. It slashes compute time by 202x, making 2K video generation viable on a single consumer GPU with 24GB VRAM.
Video Rebirth just launched Bach 1.0, an AI video engine capable of generating 30-second multi-shot films in native 1080p with integrated audio. The model tackles character consistency and camera control across cuts, debuting at #6 on the Artificial Analysis Video Arena. It is now open for public testing with free credits.
Microsoft just introduced Map2World, an AI framework that creates complete, explorable 3D worlds from simple top-down segment maps. Users color-code zones and assign text prompts to generate coherent environments—like blending modern skyscrapers with ancient ruins—while retaining consistent object scale across expansive scenes.
Researchers just introduced UniVid-X, a multimodal video framework that can decode and generate intrinsic properties like surface normals, lighting, albedo, and alpha transparency layers. Instead of treating video generation as flat RGB frames, it allows creators to relight scenes with custom lighting or swap characters and backgrounds with fine-grained precision.
ElevenLabs just launched ElevenMusic, a new platform built on its proprietary music model that lets users discover, remix, create, and earn from AI tracks. It marks a major expansion beyond AI voice cloning into music generation, giving creators a built-in monetization path for their songs.
Alibaba just launched Qwen-Image-2.0-Pro, its latest text-to-image model featuring upgraded image quality, multilingual text rendering, and sharper instruction following. The new model debuted at #9 worldwide on Arena's Text-to-Image leaderboard, also cracking the top 10 for portraits and photorealistic styles. It is available to test on ModelScope alongside an official API.
Grok Imagine just upgraded its image-to-video generator, bringing significantly sharper audio and tighter lip sync to every generation. Dialogue now tracks mouth movements much more accurately while sound matches the scene context, helping creators generate clips that look and sound far more natural.
Ideogram just launched Custom Models, letting teams train image generation models on their private brand assets instead of generic internet datasets. The update locks down brand-specific art direction, typography, and visual identity across every output, and is available immediately for Team, Pro, and Enterprise subscribers as well as via API.
An open-source workflow built on PlayCanvas allows anyone to scan an entire house with just a smartphone and explore it directly in a web browser. Instead of traditional 3D polygons, it uses millions of tiny light clouds to render photorealistic spaces in files smaller than a TikTok video. It drops scanning costs to around $200, giving freelancers a fast new side hustle.
OpenAI just launched ChatGPT Images 2.0, giving its image generation engine a serious boost in visual reasoning and text rendering. The model now reliably prints text in scripts like Chinese, Japanese, and Arabic, while improving stylistic precision across photography and manga. Best of all, it is already live inside ChatGPT.
Researchers just introduced UniGeo, an image editing framework that allows users to manipulate the camera with precise angles. By turning an image into 3D geometric representations and running it through video models, it lets you pan and tilt views without structural distortion. The model is marked as coming soon.
Google just connected its Gemini app with Nano Banana 2 and Google Photos to roll out personalized image generation. Instead of uploading reference photos or writing intricate descriptions, Gemini can automatically use your labeled family members and pets to create custom art in styles like claymation or watercolor. The feature is rolling out first to U.S. Google AI subscribers.
Alibaba’s ATH team just introduced Happy Oyster in beta, a new world model that generates interactive 3D environments on the fly from multimodal inputs. Similar to Google’s Genie 3, it lets you roam dynamic worlds and direct characters via text prompts. Early access is currently open via a waitlist.
