Researchers just open-sourced SCOPE, an interactive world model for FPS games built on Wan2.2. It supports 10-DoF gamepad and keyboard controls—like moving, aiming, and firing at the same time—and generates consistent 20 FPS video with zero-shot transfer across unseen game styles. Model weights, code, and dataset are live on GitHub.
Researchers open-sourced ASASR, an image super-resolution tool built on FLUX.1-dev that delivers faithful 4x upscaling while suppressing distorted hallucinated details. It uses adversarial Sobolev DPO alignment and a dual-LoRA setup to preserve true structures. Code, model weights, and a browser demo on Hugging Face Spaces are now available.
Researchers just introduced SEGA, a training-free method that lets diffusion transformers generate coherent images far beyond their original training resolution. By dynamically scaling RoPE embeddings according to spatial-frequency energy at each denoising step, it balances global layout with fine textures. It means existing models like Flux can output 4096×4096 visuals without costly fine-tuning.
Arq.live just unveiled GLITCH, a voice-to-film system that lets directors cast characters, build worlds, and block scenes simply by speaking. Multiple AI agents work in sequence like a virtual crew, producing a complete short film from a single laptop in under eight minutes. It moves AI video away from prompt typing toward how filmmakers actually direct.
Krea just launched LoRA fine-tuning in beta for its Krea 2 image model, allowing creators to train on their own custom styles, objects, or characters with high precision. It represents the platform's most powerful customization engine yet, handing creators vastly tighter control and visual consistency across their projects.
Researchers just introduced Lift4D, a framework that reconstructs full dynamic 4D scenes from a single monocular video. By combining single-view 3D estimation with diffusion priors, it reconstructs non-rigid motion and hallucinates unobserved angles, allowing you to orbit around moving objects from a single clip.
Researchers just introduced PhysX-Omni, a unified framework that generates simulation-ready 3D models with real physical properties like materials and kinematics. It also introduces the PhysXVerse dataset and a six-attribute benchmark, bringing generative 3D assets much closer to practical robotics simulation.
Figma just added native AI agents right into its collaborative canvas, letting designers create, edit, and iterate on files using plain text prompts. The design-tuned assistant even lets you run multiple agents at the same time for different tasks. Why it matters: you can now offload tedious layout tweaks and mockups without ever leaving the artboard.
Google just connected Project Genie to Street View imagery, letting users and AI agents turn real-world coordinates into playable, stylized simulations like an underwater Golden Gate Bridge. It is a huge step for training embodied AI and robotics in grounded virtual worlds. The prototype is now rolling out to Google AI Ultra subscribers at $200 a month.
Odyssey just dropped two frontier world models, Starchild-1 and Agora-1, pushing generative video into interactive simulation. Starchild-1 generates synchronized audio and video on the fly without fixed runtimes, while Agora-1 lets up to four players interact inside the same live-rendered game world with a shared state. It is a major shift from static clips to real-time playable realities.
OpenAI just teamed up with Google DeepMind to embed invisible SynthID watermarks across images from ChatGPT, Codex, and its API. It also rolled out a public verification portal that cross-checks C2PA credentials and watermarking signals. Why it matters: combining metadata with resilient invisible watermarks makes AI media far harder to forge or launder.
ByteDance just open-sourced Lance, a lightweight unified multimodal model with 3B active parameters that handles understanding, generation, and editing for both images and videos. Basically, it allows users to continuously tweak video clips through multi-turn dialogue, though running it locally requires a beefy 40GB GPU.
Leonardo AI just integrated 3D object generation directly into its workspace, letting creators turn 2D concept art into production-ready 3D models without switching tools. The workflow creates multi-angle reference views and exports .glb files with quad or triangle meshes ready for rigging, game engines, and 3D printing. Indie game developers and makers can basically skip the multi-app shuffle.
Researchers just introduced PanoWorld, a generative spatial world model designed for full-home virtual tours. Feed it a 2D floorplan and a style reference, and it generates interconnected, furnished 360-degree panoramas where furniture and layouts don't mutate as you move between rooms. The model and code aren't out yet, but it promises a big leap for real estate VR.
Creators are chaining GPT Image 2 with Seedance 2.0 to automate video production. The setup uses ChatGPT Image 2 to generate a 12-frame storyboard with camera and character notes, then feeds it into Seedance 2.0 to render full cinematic scenes.
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.
Developer Neilson just open-sourced a 3D generation toolkit built specifically for Anthropic's Claude Code. It takes a single reference image and automatically generates complete 3D environments—including meshes, physics simulations, lighting setups, and audio. Basically, developers using Claude Code can now spin up interactive 3D worlds without manual asset modeling.
Articraft just open-sourced an agentic system that generates articulated, working 3D objects instead of static meshes. By prompting AI models like GPT or Claude to write code that defines parts, joints, and sanity checks, it outputs fully functional mechanisms. Why it matters: Generating interactive, multi-part objects has long bottlenecked robotics simulation, and this cracks the workflow wide open.
Researchers from Shanghai Jiao Tong University and Shanghai AI Lab unveiled Warp-as-History, a method that guides AI video camera paths without heavy control modules. By disguising camera warps as visual history and tuning on just one video, it enables precise camera control across unseen scenes while naturally generating missing angles.
Nvidia just unveiled SANA-WM, an open-source 2.6B-parameter world model that converts a single image into an interactive 720p video controlled by keyboard inputs. A distilled version running on a single RTX 5090 can denoise a full minute of footage in just 34 seconds. It brings real-time world generation within reach of consumer hardware, with weights slated to drop soon.
