Wan 3.0
30-second multimodal AI video with native audio
What it does
Direct complete 30-second AI video scenes with Wan 3.0. Combine up to 20 text, image, video, and audio references; generate native dialogue, music, and sound; control first-to-last-frame motion, camera direction, and adaptive aspect ratios; and export up to 1080P at 30fps. Built for product films, ads, cinematic sequences, and consistent character scenes—without reducing every production to a single prompt.
Wan 3.0 is a powerful text-to-video and image-to-video AI generator. Create professional videos online in seconds and get free credits when you sign up.
Wan 3.0 is a next-generation AI video model supporting videos up to 30 seconds, multimodal reference control, native audio, and stable long-shot creation. With inputs such as text, images, video, and audio, it provides a more coherent and cinematic end-to-end workflow for brand ads, ecommerce videos, film previs, and social media content. Wan 3.0 is a multimodal AI video model that turns text, images, video, and audio into complete clips up to 30 seconds, with 480P, 720P, and 1080P output. Start with a simple idea or existing assets. Wan 3.0 understands subjects, scenes, motion, camera direction, and sound together to create more coherent ads, product films, short stories, and social…from wan30.io
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com