Adrian Lee

Ex-Google AI engineer
I break down the latest AI products to see what really works (and what’s smoke)😭

[Adrian Lee @AdrianLee9b8]

agree it

[Elon Musk @elonmusk]

Grok Imagine triple gold 🥇🥇🥇

[Grok @grok]

Create a video using up to 7 images in Grok Imagine.

[Adrian Lee @AdrianLee9b8]

try it

[Elon Musk @elonmusk]

Grok Imagine in a pond for 30 secs

[Adrian Lee @AdrianLee9b8]

AI image editing is evolving fast

[Krea @krea_ai]

new Krea Edit.

this tool ads a new layer of controllability for editing images with AI.

change specific regions, render new perspectives, play with lighting, color palettes, and more – try it now!

[Adrian Lee @AdrianLee9b8]

I really love it, but I have a question. Does this have a real use case?

[Luke The Dev @iamlukethedev]

The OpenClaw 3D office is on fire right now.

PS: sound on 🔊

You can now:

• Walk around the office
• Follow agents with a 3D camera
• Chat with each agent
• Play music while they work
• Edit the furniture and layout

What feature should I add next?

This is starting to feel less like a dashboard
and more like an AI workplace.

[Adrian Lee @AdrianLee9b8]

Cool system

[David Roberts @recap_david]

I built an AI system that automates product video creation for entire e-commerce catalogs.

(Saves ~$30K per collection shoot and boosts on-site conversion rates by ~20%)

Here's what the system does under the hood:
→ Firecrawl pulls product images straight from any e-commerce collection URL
→ Calico AI turns them into realistic model videos capturing fit, texture, and movement
→ Every video starts and ends on the original product shot for seamless looping
→ Output is auto-labeled, sorted, and pushed directly to Google Drive
→ The entire pipeline runs in batch — zero manual intervention

The outcome: brands can give every single SKU a video asset, not just their bestsellers — and conversion lifts are immediate.

Static images don't cut it anymore.
Buyers want to see how a product moves before they commit.

If you want the full breakdown,
Like RT & Comment "CALICO".

I'll send you the complete n8n workflow, every prompt, and a step-by-step walkthrough video — totally free. (Must be following so I can DM you.)

No more $30K production shoots.
No more wondering if your product pages are leaving money on the table.

[Adrian Lee @AdrianLee9b8]

I eagerly anticipate the release of the Veo 4

[Google Gemini @GeminiApp]

With the latest updates from Veo and Nano Banana, it’s never been easier to kickstart your creativity with Gemini.

Join us for our next Discord community event for a deep dive into Gemini’s new video and image generation features! Hear directly from a member of the team, learn new techniques, and create your own mini-masterpieces in real time.

See you in the Gemini Discord today (Thurs. 3/5 at 11:30am PT): https://t.co/IAYiy1ZOzh

[Adrian Lee @AdrianLee9b8]

Nice example of a very real use case

[Google AI @GoogleAI]

Here are a couple examples of how Gemini 3.1 Flash-Lite can solve real-world problems:

First, this high-volume image sorter showcases the model’s ability to quickly analyze and sort large amounts of content, like pictures (something that could have been too expensive or slow in the past).

This demo is just a snapshot 📸😉 of what can be built using 3.1 Flash-Lite's multimodal analysis capabilities. Think: real-time data visualization agents, CRM management tools, automated content moderation software, and beyond.

[Adrian Lee @AdrianLee9b8]

From @chraft_ai This is absolutely amazing😍

[Adrian Lee @AdrianLee9b8]

This is amazing😍 I’m curious how it’s achieved

[Chraft @chraft_ai]

Tried Seedance 2.0 with real faces… and got blocked?
Yeah. That frustration hits different.

Good news: Sora 2 supports real people photos → cinematic motion.

Left: Original Photo
Right: Sora 2 Stylized Motion

Static → Story.
Face preserved.
Vibe upgraded.
Consistency unlocked.

No weird distortions.
No face bans.
Just clean, cinematic transformation.

⚡ 24H ONLY
Follow + Repost + Reply = 200 FREE Credits
(DM “SORA2” and it’s yours.)

Real faces. Real motion. Real storytelling.
Only on Chraft AI.

[Adrian Lee @AdrianLee9b8]

Believe it or not？

[Patrick Collison @patrickc]

It's going to be tough for startups when all the Lord of the Rings names are taken and the only thing left is something like Bombadil AI.

[Chraft @chraft_ai]

Most “AI video agents” aren’t agents.

They generate a 15-sec clip
because all they do is turn your words into a single prompt.

That’s not agentic.
That’s a wrapper.

Some platforms say you can “use an agent.”
But they give you a canvas, workflow nodes, timelines…

You manage everything.

You are the agent.

And that’s why you still spend 5 days
to create a 3-minute video —
even with AI.

A real agentic video platform should feel different:

Just chat.
Change the style.
Extend the story.
Adjust the emotion.
Fix one scene — the whole structure adapts.

No nodes.
No manual orchestration.
No prompt babysitting.

Any style.
Any length.
One conversation.

That’s what agentic actually means.

[Adrian Lee @AdrianLee9b8]

👍🏻

[Chraft @chraft_ai]

You can control ai video creation in a whole new level!

AI can now keyframe every second of animation from just prompts

[Adrian Lee @AdrianLee9b8]

Has anyone tried it😻

[Nano Banana 2 Lite @NanoBanana]

This prompt works best with Nano Banana 2:

Prompt: Make a photo of a cute ball-shaped version of a [animal], with big adorable over-sized eyes, it has no head, instead its face is part of the ball, its head and body are one. They are in their usual habitat. Must be almost spherical and cartoonishly cute. Its eyes are looking up in the most adorable cheeky fashion.

[Adrian Lee @AdrianLee9b8]

@lovart_ai https://t.co/snA5jay6HO

[Adrian Lee @AdrianLee9b8]

Seedance 2.0 turns kids drawing into 100k film scene.. hollywood is cooked

[Chraft @chraft_ai]

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.

[Adrian Lee @AdrianLee9b8]

Seedance 2.0 turns kids drawing into 100k film scene.. hollywood is cooked

[Adrian Lee @AdrianLee9b8]

This is where exponential begins

[Google AI @GoogleAI]

More than a billion images generated later, we love seeing what you create with Nano Banana. Today, we’re inviting more people to join in on the fun with the launch of 🍌Nano Banana 2🍌

This state-of-the-art model is exceptionally good at things like:
— Creating images that tap into the Gemini model’s real-world knowledge base + are powered by information and images from web search to more accurately render specific landmarks, locations, objects, and beyond

— Adapting creative assets for global markets with regionally relevant localization

— Dynamically editing aspect ratios and upscaling to 2k and 4k resolutions

— Generating multiple cohesive images that fit together in one world, story, or concept