Barsee 🐶 Profile picture
Mar 21, 2023 7 tweets 3 min read Read on X
Midjourney v5 is the beast of image generation

I generated these 8 realistic images in less than 6 minutes, crazy fast and easy: 🧵

Prompts are in the ALT a man in his 20s happy with his white dog in Dandelions at tstreet style photo of John Wick with his dog, shot with FujiStreet style of a guy riding in BMW S 1000 RR in Cinque Terr
2. Prompt:

Bird's Eye View of a young blonde woman in the middle of the sea around waves, with orange and purple tones at night with stars, shot with Fujifilm Pro 400H, film noir style, realistic and detailed clothes, Cinematic, Color Grading, portrait Photography, 4k
3. Prompt:

Blue Ferrari F40 in Dandelions at the Lake Seealpsee, shot with Fujifilm Velvia 50, High detailed, High contrast 4k
3. Prompt:

A boy happy with his dog in Switzerland, shot with Ilford HP5 Plus
4. Prompt:

Portrait Photography of Leonardo DiCaprio in titanic ship, shot with Kodak Portra 400, High Contrast, natural lighting, 4k
5. Prompt:

Red Ferrari F40 in Dandelions at the Lake Seealpsee, shot with Fujifilm Velvia 50, High detailed, High contrast 4k --ar 16:9
That's the end of the thread.

Comment your thoughts and feedback on these images and prompts.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Barsee 🐶

Barsee 🐶 Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @heyBarsee

May 23
We just had one of the biggest weeks in AI.

-Google launched Veo 3
-OpenAI and Jony introduce IO
-Anthropic launched Claude 4
-Apple Glasses & Google Glasses
-Tesla Optimus huge progress
-Anthropic CEO 2026 AI prediction
-CEO AI doubles

Here's EVERYTHING you need to know:
1. Google dropped Veo 3, its latest AI video model that generates near-real videos with full audio, sound effects, and dialogue.

Designed to rival OpenAI’s Sora.

2. Google also unveiled Flow, an AI filmmaking tool that combines Veo, Imagen, and Gemini, allowing users to create 8-second video clips from text.

Read 14 tweets
Mar 27
We just had one of the biggest days in AI.

-Deepseek-V3
-Google Gemini 2.5
-GPT-4o image generation
-Zapier MCP protocol
-H&M AI clones
-China’s AI training breakthrough
-AI cancer detections breakthrough

Here's EVERYTHING you need to know:
1. Google dropped Gemini 2.5, their most intelligent AI model ever.

It’s a powerhouse in reasoning and coding, debuting at the top of LMArena by a wide margin.

2. DeepSeek has released Deepseek-V3.

-major boost in reasoning performance
-outperforms Sonnet 3.5
-competes with Claude 3.7 in coding & math Image
Image
Read 15 tweets
Mar 26
It's been 24 hours since OpenAI unexpectedly shook the AI image world with 4o image generation.

Here are the 14 most mindblowing examples so far (100% AI-generated):

1. Studio ghibli style memes
Image
Image
Image
Image
3. A screenshot of Wikipedia page with proper explanations for how cats work
Read 17 tweets
Mar 9
Manus AI is the closest thing to AGI we've seen

This is AI agent that combines Deep Research + Operator + Claude Computer

9 wild examples and use-cases.

1/ Analyzes Tesla stock in just 1 hour, a task that usually takes professional analysts two weeks.

2/ While Tesla's FSD takes a power user to his coffee meeting, Manus preps him with all the key talking points.

3/ Plans full trips on its own. It assigns itself tasks, browses the web, researches flights and hotels, and builds an itinerary... complete with budget and food recommendations.
Read 10 tweets
Mar 8
The last few days in AI is insane 🤯

12 most incredible developments from Google, OpenAI, Alibaba, Unitree, Manus and more

1/ China unveils new Quantum Computer ‘Zuchongzhi-3’—a 105-qubit machine that performs calculations one million times faster than Google's Supercomputer. Image
2/ A new AI agent called 'Manus' is taking over the internet.

People are calling this China's second DeepSeek moment.

Reports suggest it is more accurate than DeepSeek, capable of simultaneously handling financial transactions, research, purchasing, etc
Newly released footage shows Manus automating approximately 50 tasks, creating a rather dystopian scenario.

Read 15 tweets
Mar 4
AI-generated videos are getting out of hand.

This is ridiculous how far we have come in just 1 year. It might get its own ChatGPT moment soon.

Here are 12 leading AI models that just changed AI-generated videos forever: 🧵
1. Hailuo AI's T2V-01 Director Mode

— Lets you control AI-generated camera movements with plain English
— Adds cinematic depth & dynamic shots effortlessly

2. Google Veo 2

— It can generate 4K video generation up to 2 minutes long
— Understands real-world physics & human motion
— Hyper-realistic results

Read 15 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(