Video & Image Generation Model from @Ali_TongyiLab Discord: discord.gg/aRpnFqd7Y6
- Tweets 699
- Following 13
- Followers 32,269
- Likes 203
Pinned Tweet
This is Wan3.0.
Simple Input. Smart Creation. Where Imagination Meets Reality.
Wan3.0 is now generally available.
🎉 Launch offer: Get 30% off Wan3.0 (Standard) on Alibaba Cloud Model Studio and Qwen Cloud from August 23 to September 23.
142
124
2,781
10,991,749
Wan3.0 Prime is #1 and Wan3.0 is #3 on OpenRouter's Video Leaderboard — New & Trending.
Every request on this board is a creator choosing Wan. Thank you for that.
Now show us what you make with it — we're watching, and we can't wait
Full board ↓
openrouter.ai/rankings/video…
23
5
80
5,912
interesting idea!
くりえみさんのロボットカーニバルに出そうと思ったアニメです。
自分で納得がいかなかったので没にしたものですが供養でポストします。
工夫
全てWan3.0なのでコストが抑えられる
声は似てる部分はそのまま、おかしい部分は上からIrodoriTTSで乗せてます。
作ってみての感想
まず手描き風はコントロールが難しい、すぐフルアニメ調になっちゃう。
やはりアクションシーンはSeedanceが上（カメラワーク、人物の動きなど）
登場キャラを全て今のAIになぞったものにしてますｗ
お気に入りはソネット！
主人公クロ （Claude）
相方ジピテ（GPT）
などなど
1
31
3,808
📣 Wan3.0 is #1 overall on the new @ArtificialAnalysis Leaderboard.
Thank you to the team and evaluators, and to every creator building with Wan. The quality bar keeps rising — and so will we.
We are launching AA-Video-T2V v2.0, our new benchmark for evaluating text to video models, alongside AA-Video-T2V-Silent v2.0 for video generation without audio. Built on a new methodology, it judges every model at 1080p on a regularly refreshed prompt set, and ranks them across 10 use cases, 10 capabilities and a wide range of styles.
Video models are being adopted across more industries and workflows, from film studios to advertising agencies. Our new benchmark not only ranks models overall, but also shows which model is best for specific use case and video generation capability. Use cases are grounded in how consumers and enterprises use video generation. Capabilities draw on lab and academic research, and on how creators and businesses push video models today. We tag every prompt by use case (such as Live-Action Film and Marketing & Advertising) and by the capability it tests (such as Text Rendering and Audio Synchronization), and the overall benchmark samples evenly across both. Because of this, the overall ranking reflects a model's versatility across use cases and well-roundedness across capabilities. We also tag each prompt by visual style, such as photorealistic, 3D render, cartoon and anime, and hand-drawn illustration.
AI video is also moving onto bigger screens and into production, from microdramas to movie theaters, while low barrier to generate is resulting in a proliferation of low quality AI video content. The quality bar keeps rising, so we now judge every clip at 1080p and high bitrate.
We are launching AA-Video-T2V v2.0 with more than 68,000 high quality human preference votes from private evaluators based in US/UK over 1,000 prompts, and AA-Video-T2V-Silent v2.0 with more than 47,000 votes over 500 prompts.
Initial insights from an in-depth analysis of the 10 highest ranking models on the Artificial Analysis AA-Video-T2V v2.0 Leaderboard:
➤ Wan 3.0 ranks #1 overall and leads 10 of the 20 category boards, including Cartoon and Anime style and Animation & Gaming use case, at $12 per minute of video.
➤ Dreamina Seedance 2.5 ranks #2 and is the human performance specialist, #1 on both Human Anatomy and Dialogue & Lip Sync. At $34.12/min it is the most expensive model in the top 10.
➤ MiniMax H3 (768p) ranks #3, statistically tied with Seedance 2.5 at $4.80/min, about 1/7 of the price. It is also #1 on Text Rendering.
➤ FLUX 3 ranks #4, with its strongest results on Text Rendering (#3) and Dialogue & Lip Sync (#2).
➤ Gemini Omni Flash 1.1 ranks #5 and is the graphic 2D and audio specialist, #1 on UI/UX & Motion Design use case, Flat Design style and Audio Synchronization capability.
See below for the use case, capability and style breakdowns 🧵
16
6
113
8,529
AI video quality gets the attention. Economics determine what actually scales.
In this Wan3.0 workflow:
10 seconds.
1080p.
$1.82 on @AskVenice.
That changes the conversation from:
"Can AI generate this?"
to:
"How much content can we now afford to produce?"
Johnny Mai from Alibaba Cloud × Jordan Urus at Venice.ai.
Want to bring Wan3.0 to your team?
Learn More →
docs.dingtalk.com/notable/sh…
#Wan3 #CreatorEconomy #AIProduction #ContentCreation
5
4
52
4,833
This is where AI video starts getting interesting.
One prompt.
→ cinematic motion
→ 1080p output
→ generated sound
Johnny Mai from Alibaba Cloud and Jordan Urus from Venice ai put Wan3.0 through a simple end-to-end workflow.
The distance between an idea and a finished scene is getting very small.
Want to bring Wan3.0 to your team?
Learn More →
docs.dingtalk.com/notable/sh…
#Wan3 #TextToVideo #AIVideo #GenerativeAI
7
6
79
5,824
The Topview Wan3.0 Challenge is already halfway through.
USD 15,000 prize pool. Deadline: September 30.
The earlier you jump in, the more runs you get ↓
What could you create with @alibaba_wan? 👀
Make an AI video. Show us your wildest idea. Compete for a share of USD 15,000 🏆
The Topview Wan3 Challenge is here—and free Wan3 video generations are available to help you get started.
📅 September 4–30, 2026
🎬 Minimum 30 seconds
🎥 720p or higher
Ready to create your next world?
Follow us and repost this post to get 3 FREE Wan3 video generation credits! 🎁
Join the challenge here 👉 topview.ai/activity/topview-…
#TopviewAI #Wan3 #TopviewWan3Challenge #AIVideo #AIFilm #AIArt #CreatorChallenge
4
12
2,806
腕には参りました。
WAN3.0の可能性をここまで広げてくれて、ありがとうございます。次もきっと
#TopviewAI #Wan3 #TopviewWan3Challenge
@TopviewAIJP
TopviewのWAN3.0でアクションアニメ的な物を制作してみやしたよ(｀・ω・´)ゞ
うんうん、楽しいぞ！可能性はすごく感じる…。
あとはワイの腕次第かな(´；ω；`)ｳｩｩ
8
4
63
6,491
I suspect the creator hit record mid-game.🤫
I just made a GAME VIDEO with @nadou_pro x Wan 3.0 👀
The quality is honestly wild. But the consistency between scenes?
That is what got me. 🔥
AI video is getting scary good.
#NadouPro #wan3 @Alibaba_Wan
4
46
6,570
With just a photo of your own, you can swap in any scene and set it in motion.
Made with the Peel-Off Sticker skill on wan.video and generated by Wan 3.0 ↓
8
7
96
7,316
Wan retweeted
Greedy Innkeeper
Created with Wan 3.0 on @nadou_pro @Alibaba_Wan
Late one night, a weary merchant arrives at a quiet village inn, carrying a mysterious red travel bag. While preparing his dinner, the innkeeper notices his valuables and secretly devises a plan to steal them using a magical herb said to make people forget.
But the merchant is not as unsuspecting as he appears.
As the innkeeper's plan unfolds, a hidden secret is revealed, turning her clever scheme against her. What begins as a simple night at an old roadside inn becomes a tense tale of greed, deception, and an unexpected twist.
Sometimes, the person you think you've fooled has already seen through you.
#NadouPro #wan3
83
64
964
89,280
A story maker's entry for the OpenArt AI Ad Awards — made exclusively with Wan 3.0.
As a story maker, I try not to be a one-trick pony. I love jumping between different genres and styles.
This is my second entry for the OpenArt AI Ad Awards, and I used Wan 3.0 exclusively for this one.
#OpenArtAdAwards #wan30
@openart_ai
@Alibaba_Wan
2
32
3,554
We're pleased to announce that Wan3.0 ranked #2 in the Overall Video category on @openart_ai's OpenArt Arena.
30-second takes, native audio, any reference — creators love what Wan3.0 makes possible.
And we love what creators make with it. Keep them coming.
16
8
128
8,117