video-generation
World Labs' Atlas generates a minute of 1440p video you can actually steer News
World Labs introduced Atlas on September 1, 2026, a world model pretrained from scratch on text, images, video and 3D that grounds every input image at a position in space, letting it generate up to a minute of 1440p video with exact camera control instead of text-prompt guesswork.
Teacher forcing and exposure bias Lesson
Teacher forcing trains a sequence model by always feeding it the correct previous token instead of its own output, which makes training fast and stable but leaves the model unprepared for its own mistakes at generation time -- a mismatch called exposure bias.
Evoke keeps a generated world's memory outside the video model News
Alaya Lab released Evoke, a 14-billion-parameter open-weights world model that stores scene geometry in an external bank indexed by camera position instead of inside the image generator, letting an interactive generated world stay consistent for hours.
Video models look right 92 percent of the time and do the task 38 percent News
A new benchmark scores AI video generation on two separate axes and finds the best model reaches 91.8 percent on visual reliability but only 37.8 percent on actually completing the instructed task, quantifying a gap that fidelity metrics have been hiding.
Deepfake detectors for crisis video collapse once the clip gets reshared News
A benchmark of 17,886 crisis videos found that a single round of ordinary resharing dropped the best purpose-built AI-video detectors from catching 46 percent of fakes to catching 1.4 percent.
MiniMax put its video-with-sound model on Hugging Face News
MiniMax released the weights for H3, a multimodal generation model that produces video with native stereo audio, two weeks after promising them at launch, and it has already been downloaded more than two million times.
A world model that keeps the map outside the model News
Evoke stores scene geometry in an external memory bank indexed by camera position and retrieves only what the current view needs, letting an interactive world model run open-ended sessions without its context growing.
The open world model ships inference and keeps the training code News
AlayaWorld released inference code and pretrained weights for an interactive world model with long-horizon memory, but the training code is still an unchecked box, the license is a community license, and running it requires a gated Google model plus a ByteDance depth model.
A closed-loop benchmark caught nine world models forgetting the room News
A new benchmark replaced scripted evaluation with an AI agent pursuing long-horizon goals inside generated worlds, and found that all nine leading world models lose spatial consistency and forget what happened out of frame.
One checkpoint turns a compatible video model into a 4D world builder News
Researchers skipped the pixels entirely, feeding a video model's final internal representation straight into a 4D decoder, and got a single checkpoint that works unchanged across multiple video generators after training on about a thousand clips.
LTX-2.5 ships open weights and a chart that races its own hardware News
Lightricks released LTX-2.5 with downloadable weights, free commercial use under $10M in revenue, and a rebuilt generation stack whose new diffusion decoder spends rendering compute where the scene is complex.
The open video model tops out at fifteen seconds, not twenty-six News
MiniMax's H3 weights have drawn 2,900 stars in four days, but the company's own repository caps a single generation at fifteen seconds and says the hosted component it left out is critical to output quality.
MiniMax Shipped H3's Weights and Kept the Best Part Hosted News
MiniMax released the weights for its H3 video-and-audio generation model, and its own model card says the input-processing stage that is critical to output quality is not included in the release and the 2K output stage is not open-sourced at all.
DistillAlign explains why fast video models get prettier and more repetitive at the same time News
A new preprint shows that the standard technique for speeding up video generators optimises a mathematical objective that deliberately concentrates on safe, common outputs, and that adding a diversity-preserving loss back during that stage more than doubled the paper's coverage measure without giving up the quality gain.
ByteDance's Seedance 2.5 generates a 30-second single take, and still cannot promise a face across a cut News
ByteDance Seed announced Seedance 2.5 on 31 July, a joint audio-video model producing single clips of up to 30 seconds extendable twice, roughly doubling its predecessor's maximum take length while documenting no persistent character identity across separate shots.
Seven new papers cannot agree what a world model is made of News
PhiZero compresses video into a learned alphabet of state transitions, but six competing late-July papers argue the substrate should instead be executable simulator code, explicit game state, paired re-renderings, distribution coverage, architecture, or action intent.
NVIDIA shipped a drop-in kernel that nearly halves video generation time News
NVIDIA released code on July 28 for Sol-Attn, an attention kernel that decides which parts of a long video to compute exactly while approximating the rest inside a single pass, reporting up to 2.1 times faster video generation with no retraining and no weight changes.
A new benchmark grades video models on film craft instead of whether clips look nice News
FilmBench scores text-to-video and reference-to-video models against professional cinematic criteria such as camera language, shot continuity and performance, using prompts reverse-engineered from professionally selected film clips, with the dataset and toolkit released publicly.
Classifier-Free Guidance Lesson
Classifier-free guidance is the knob that makes image and video models actually follow your prompt: it runs the model twice - once with your prompt, once without - and pushes the output along the difference.
Black Forest Labs launches FLUX 3 -- image, video, audio, and a robot that never renders the video News
Black Forest Labs announced FLUX 3 on July 23 as a unified image, video and audio model with 20-second video and native audio, available only in early access, with open weights deferred to a later Dev release.
A Wave of AI World Models Landed, and the Useful One Keeps the Real Game Engine News
Several AI world models hit Hugging Face this week, and the most commercially credible restyles a real game engine's frames in real time rather than trying to generate the game itself.
Two New Papers Split World Models Into Simulators and Streamers News
A pair of papers argues the field of interactive video AI is forking: one track pushes world models toward game-engine-like simulators with explicit state, the other reframes video as a persistent world plus a stream of events for real-time interaction.
A video generator, repurposed as a perception model, matches specialists with up to 500x less data News
GenCeption repurposes a pre-trained video generative diffusion model as a feed-forward perception system, matching specialist vision models on depth, surface normals, pose and segmentation while using 7x to 500x less training data - and generalizing from synthetic-only training to real footage.
Vidu S1 generates video you can steer with your voice in real time News
A new paper introduces Vidu S1, a video model that generates interactive 540p video at up to 42 frames per second on consumer GPUs and lets users reshape the scene on the fly with voice commands, without the drift that usually breaks long AI video.
Diffusion models: how AI turns noise into images and video Lesson
Diffusion models generate images and video by starting from pure random noise and removing it step by step until a coherent picture emerges -- the technique behind Stable Diffusion, Sora, and interactive video systems like Vidu S1.
New world models generate depth and motion, not just video, to train robots News
A cluster of world-model papers led by RynnWorld-4D shows AI generating synchronized color, depth, and motion instead of flat video, so robots can practice manipulation inside a generated world and turn predictions directly into actions.
Meta unveils Muse Image and Muse Video, its first in-house media generators News
Meta Superintelligence Labs previewed Muse Image and Muse Video, its first homegrown media-generation models, and built 'agentic tool use' directly into the image model instead of treating generation as passive prompting.
'World model' was too vague, so researchers wrote a 58-page definition News
With 'world model' stretched to mean everything from video generators to robot simulators, a 58-page technical report set out to pin down a single scientific definition - as a wave of new papers pushed the field from world-models-as-pretty-video toward world-models-as-working-tools.
Google ships a faster, cheaper image model and hands developers conversational video editing News
A lightweight version of Google's image model now makes a picture in about four seconds for a fraction of a cent, while a new video model lets developers edit clips by talking to it.
NVIDIA's new method stops AI dream-worlds from breaking the laws of physics News
PhysisForcing trains video-generating world models to keep objects solid and interactions believable, raising how often a robot's imagined plan actually works.
AI video has a consistency problem. This model targets it. News
DomainShuttle goes after the tug-of-war in subject-driven text-to-video: keeping a specific character or object recognizable across frames while still letting the scene move freely.
NVIDIA shrinks video generation down to real time News
A new NVIDIA recipe distills slow video-generating AI into a fast version that can stream frames live and react to your actions.
What are world models? Lesson
A world model is an AI system's internal understanding of how an environment works — not just what it sees right now, but what will happen after an action, and what would have happened differently. Central to planning, robotics, and the next generation of physical AI.
Turn the camera away, and the AI's world freezes News
A new benchmark tests whether video AI systems can track what happens to parts of a scene the camera isn't currently showing. Across 23 models, the answer is mostly no — and making the models larger made the problem worse, not better.
Turn around, and the world disappears News
AI video models that are supposed to "understand" a 3D scene only remember what's on screen — pan away and back, and things have reset. Bigger models are worse at it.
h3-studio Tool
Local front end for MiniMax H3 built on ComfyUI 0.30.0 or newer, with a VRAM meter, idle GPU release and a service setup so the video model hands the card back to other workloads. Its notes document H3 needing roughly 15.5 GB in the NVFP4 build, which is the practical ceiling on a 16 GB card.
Wan Streamer v0.3 Tool
Streaming audio-visual interaction model that treats a video as a persistent world plus a time-varying event stream, running full-duplex real-time conversation at 640x368 / 25fps with roughly 550ms total interaction latency.
Vidu (Vidu S1 Stream Model) Tool
A working AI video generator with text-to-video, image-to-video, and reference-to-video modes; the new S1 Stream Model targets real-time, interactive, voice-steerable video at up to 42 FPS/540p on consumer GPUs. Free credits to try, paid plans for more.
Sol-Attn (Sol-Engine) Tool
NVIDIA's drop-in sparse attention kernel for long-video diffusion transformers, released July 28 for HunyuanVideo-13B and Wan2.1-T2V-14B. Screens compressed key/value blocks inside a single online-softmax pass, so exact attention goes where it matters and skipped blocks get an approximate correction. Training-free, no weight changes, reported up to 2.1x for generation and 2.3x for editing. The repo marks end-to-end re-benchmarks for the two integrated pipelines as pending.
Seedance 2.5 on Dreamina Tool
ByteDance's newest joint audio-video model, announced 31 July, generating a single take of up to 30 seconds extendable twice, with white-model control, green-screen editing and camera and blocking controls. Note that the 4K output, 50-reference limit and 180-second beta advertised on this page are marked Coming Soon.
MiniMax-H3 Tool
Open weights for MiniMax's omni-modal model that generates four to fifteen second video with native stereo audio. The locally deployable base runs at 768p through diffusers or SGLang; the prompt-interpretation and 2K regeneration stages stay behind MiniMax's API, and the licence excludes the US, EU, UK, and South Korea.
MiniMax H3 GitHub Tool
Official repository for running H3 locally, including inference code and MiniMax's own prompt-writing skills for getting usable results out of the multimodal context format.
LTX-2.5 Tool
Lightricks' open-weight video foundation model, shipped 11 August with a new diffusion decoder, native multishot generation, 4K HDR and automatic clip-length prediction. Runs locally on 16GB of VRAM, or through a per-second API. Free for commercial use below $10M annual revenue.
Hailuo AI Video Tool
MiniMax's hosted front end for H3, for trying the model in a browser before downloading tens of gigabytes of weights. Supports text-to-video, image-to-video, first-and-last-frame and reference-to-video workflows.
Gemini Omni Flash Tool
Google's new video model offering developers programmable conversational editing - generate and revise clips up to ten seconds by describing changes in words.
FilmOps + FilmBench Tool
Public benchmark assets for judging generated video on professional film craft instead of generic prettiness. FilmOps ships six specialized operators covering shot scale, composition, camera angle, color and tone, character layout and camera movement; the companion FilmBench dataset supplies prompts reverse-engineered from professionally selected clips, most of which require multi-shot continuity. Authors report weaker agreement with human raters on audio and editing than on visual categories.
FLUX 3 (early access) Tool
Black Forest Labs' unified generation model, producing video up to 20 seconds with native synchronized audio from text, image, video or keyframe inputs. Video is behind an early-access request today; image access is promised in the following weeks and open weights are deferred.
Evoke Tool
Open-weights 14B world model that generates a navigable video world you can steer with a camera and text mid-session, keeping scene geometry in an external memory bank so places stay consistent when you look back. Apache 2.0, with every training-stage checkpoint published, not just the final one.
ComfyUI-SolAttn-H3 Tool
A ComfyUI custom node that wires NVIDIA's training-free Sol-Attn sparse attention into the native MiniMax-H3 video path using public ModelPatcher APIs, so it drops in without modifying any ComfyUI core files. Keeps a prefix sink exact and sparsifies the remaining attention via a tunable threshold, with the gain growing as sequence length grows.
Atlas (early access) Tool
World Labs' new omni world model for spatial intelligence: generates up to a minute of 1440p video along a camera path you specify exactly, reconstructs real scenes from two or three photos, and outputs explicit 3D. No public weights or API yet -- early access is by request.
AlayaWorld Tool
Inference code and pretrained weights for an autoregressive world model with real-time camera control, prompt switching and long-horizon memory consistency, using an explicit 3D cache for spatial recall plus a compressed frame-history embedding. Training code is not included and the weights ship under a community license.
10S-Comfy-nodes (LTX Tiled Sampler) Tool
A drop-in replacement for ComfyUI's SamplerCustomAdvanced that fixes LTX 2.5's broad colour smearing by sampling in spatial tiles, keeping each tile inside the model's training token count instead of running a 2x-upscaled latent, then stitching with cosine-Hann overlap blending. Actively maintained with external contributions.