⏳ 3 days left.
The World's Biggest AI Video Contest winners will be revealed LIVE on March 17 at 3PM PT ⚡️
8,752 submissions
$500K prize pool
Who takes it home?
🔔 Click “Notify me” on the YouTube livestream so you don’t miss it.
The Gemini Discord server is back with another edition of everyone’s favorite community event: Prompt Like a Pro!
Join us tomorrow (Friday, 3/13) at 12:30pm PT as a member from the Gemini team spotlights some use cases from our server members and offers tips and ideas to take them to the next level. We'll be covering Nano Banana, Gemini Live, Veo, Personal Intelligence, and more.
Not in the Gemini Discord yet? Join us here: https://t.co/IAYiy1ZOzh
And The Award goes to... Higgsfield Soul Cast!
Uncanny Valley no more. Soul Cast is the ultimate solution to plastic-looking characters.
🕴 Exclusive rights: reserve your AI Actor so it's yours only
🕴 Even a simple prompt becomes a biography
🕴 Looks, era, even an archetype - every detail is fully customizable
New era of castings is here.
📸 New on Lovart: Multi-Angles
Drag to rotate, tilt, and scale.
One image, every angle, no prompt needed.
→ Subject Mode: move the subject directly
→ Camera Mode: move the virtual camera
Like + reply + follow – 30 lucky winners get 300 credits each!
Gemini 3.1 Flash-Lite is our most cost-efficient Gemini 3 series model 🔦
Folks who are keen to experiment with it in Gemini CLI can do so with an API key and the -m flag.
❯ gemini -m gemini-3.1-flash-lite-preview
Official support for it in /model will be coming soon 🔜
🚨 800 FREE CREDITS — 24 HOURS ONLY
We just launched LTX-2.3, our most powerful video model yet. High-res. Fast. Cinematic. Native lip-sync.
Follow + Retweet this post to get 800 credits sent to your DMs.
SNEAK PEEK: Soul Cinema Preview 🎬
We just dropped Soul Cinema Preview, our new in-house AI photo model focused on cinematic-grade image generation.
Enjoy FREE gens for new users & up to 10k previous ones*
Built specifically for images with rich textures, deep mood & cinematic quality.
Pair it with Soul ID for character consistency & Soul HEX for precise color control. Guess when the full version is dropping!
*for Pro, Ultimate, and Creator plans
Smarter. Faster. Gemini 3.1 Flash-Lite is here⚡
The model offers uncompromising speed & intelligence at scale by focusing on:
— Cost-efficiency: Priced at just $0.25/1M input and $1.50/1M output tokens, it gets work done faster at a fraction of the cost of larger models, including a 45% increase in output speed compared to Gemini 2.5 Flash
— Compute control: 3.1 Flash-Lite comes with flexible thinking levels so you can actively select how much the model “thinks” for a given task, based on the complexity of your project
— Scalable intelligence for building: The model can handle high volume tasks at scale while keeping costs down *and* can tackle complex workloads where in-depth reasoning is needed, like generating user interfaces or detailed instruction following
3.1 Flash-Lite is rolling out in preview today via the Gemini API in @GoogleAIStudio and Vertex AI.
“UGC ads don’t work anymore.”
No — bad UGC ads don’t work anymore.
Most are just AI-made noise.
Same hook. Same face. Same script.
People don’t skip ads.
They skip boredom.
UGC didn’t die.
Lazy storytelling did.
If you want attention, stop generating content.
Start generating stories.
$500,000 Contest Entry - IN DESPAIR
In the moment when everything collapsed, revenge began.
🎥: by jaemin_yoo
Note: The video featured here is user-created fan art. Higgsfield does not claim ownership over any of the elements depicted, which are owned by their respective rights holders.
$500,000 Contest Entry - TAILS OF STEEL
In a 1990s megacity, criminal gangs unite under the rule of the mysterious supervillain Chrome Cat, who seeks total control over the city and turns the streets into a territory of fear and submission, until three heroes decide to challenge his growing cat empire.
🎥: by neosoznal
Note: The video featured here is user-created fan art. Higgsfield does not claim ownership over any of the elements depicted, which are owned by their respective rights holders.
Guess what?
This wasn’t made with Seedance 2.0.
It was built with Chraft and Seedance 1.5 — in just 30 minutes.(it doesn't let you wait 4 hours)
Yes, you’ll spot flaws.
Yes, some frames aren’t perfect.
But that’s not the point.
This is before 2.0.
If 1.5 can already do this in half an hour…
what happens when 2.0 drops?
We’re not watching improvement.
We’re watching acceleration.
Most image models still struggle with text.
Nano Banana 2 doesn’t.
Posters. UI. Ads. Thumbnails.
The text actually looks right.
Honestly, this should be your default image model now.
Meet Lovart Skills. ✨
Packaged design instructions that take you from idea to professional visual outcomes.
Choose what you want to create, and the agent runs full workflows automatically.
Like + reply + follow – 15 lucky winners get 500 credits each!
Nano Banana 2 is here.
Our latest image model gives you the power of Pro at the speed of Flash. You can create images with real-world accuracy, add text in many languages, and bring your wildest ideas to life faster with vibrant lighting, richer textures and sharper details. 🧵