SevenTnewS

video generation

12 published articles

LLMs & Models4 min read

AI Video Generation

Alibaba's Wan3.0 sells video by the second: $6 for a 30-second clip

Wan3.0 can turn a PDF or a brand deck into a 30-second video in one generation, with per-second API pricing that tops out at $0.20 for 1080P. We break down the per-clip math and the gaps Alibaba admits in its own testing.

2026-08-16

Vision & DiffusionFeatured5 min read

Video AI research

How Context-Matched Distillation stops video teachers from seeing the future

Video distillation has long trained causal students against teachers that score whole clips with future knowledge. CMD replaces that scoring with a causal teacher, adds prefix-scored targets, and reports state-of-the-art results among autoregressive methods.

2026-08-14

LLMs & Models5 min read

Video generation

MiniMax scrapped its proven architecture to make H3 do everything

MiniMax says H3 unifies text, image, video and audio generation in one model, prices 2K output below a third of mainstream models, and plans to open the weights within days. The small print is the real story: the company abandoned the architecture that gave it an edge to get there.

2026-08-07

Vision & DiffusionFeatured3 min read

AI Video Generation

Wan3.0-Video charges by the second: a 30-second clip runs to $6

Alibaba's Wan3.0-Video bills per second on DashScope, with a 30-second 1080P clip costing $6 per generation. We break down the pricing tiers, the multi-input workflow, and the questions the listing leaves unanswered.

2026-08-07

AI4 min read

AI Video Generation

MiniMax H3 prices video at a third of rivals, ranks No. 1 in editing

MiniMax H3 packs text, image, video and audio into one model, prices output at a third of mainstream per-second rates and ranks first in video editing on Artificial Analysis. The weights are promised within days. How the output holds up outside the company's own demos is the open question.

2026-08-06

Vision & Diffusion4 min read

Computer Vision, World Models & AI Research

PhiZero: teaching video AI to think in physics before it renders

PhiZero, a CASIA world model, learns a compact discrete "physical language" from raw video and uses it to reason about how a scene will evolve before rendering frames. The authors argue this reason-then-render design produces more physically coherent video than direct pixel prediction.

2026-07-31

NVIDIA Research3 min read

AI Research

Video generation gets 120x faster on one GPU, inside Nvidia's hybrid attention breakthrough

Nvidia Research's SANA-Video 2.0 combines linear and periodic softmax attention in a 3:1 ratio to run 120x faster than Wan 2.2 on one H100. The hybrid design recovers full-rank expressiveness while keeping inference at 13 seconds for a 720p clip. The caveats: the benchmarks stop at 720p and bundle the attention change with proprietary optimizations.

2026-07-31

AI4 min read

Video generation

MiniMax H3 undercuts video rivals and plans open weights

MiniMax packs image, video and audio generation into one model, prices output at under a third of mainstream per-second rates, and plans to open the weights within days. How well the outputs hold up outside its own demos is the open question.

2026-07-30

Vision & Diffusion4 min read

AI Research

VideoCoCo fixes AI video's broken physics by thinking in Blender code

VideoCoCo treats executable Blender code as a chain of thought: a coding agent scripts a scene, a simulator plays it out, and a video engine makes the result photorealistic. The split targets text-to-video's physics problem and posts best average scores on PhyGenBench and VBench-2.0.

2026-07-30

LabFeatured3 min read

KlingTeam

Video generation's dirty secret is finally on the record

KlingTeam introduces MultiRef-Compass and KeyFrame-Compass, two benchmarks that push video generation models beyond text-to-video and into multi-reference and keyframe-conditioned tasks. Early tests on eight and nine systems respectively show consistent failures in binding entities, preserving temporal order, and handling dense constraints.

2026-07-26

AIFeatured1 min read

Video generation & game engines

The game engine rule that generative models keep forgetting

Video generative models are often called the next generation of game engines. But without solid state tracking, they forget what happened two frames ago. A new paper dissects the problem and offers a dataset of over 90 hours of Black Myth: Wukong gameplay as a resource for fixing it.

2026-07-23

AIFeatured3 min read

Artificial Intelligence

MiniMax just shipped a model for every AI job you can name

Chinese AI startup MiniMax launches M3, Hailuo 2.3, MiniMax Code, and new speech/music models, broadening its product lineup in a competitive landscape.

2026-07-06