Sachin Kamath↗️’s Post

Name: Sachin Kamath↗️ on LinkedIn: #midjourney #chatgpt #flux | 21 comments
Uploaded: 2024-08-22T19:35:26.961Z
Duration: 12 s
Channel: Sachin Kamath↗️

Sachin Kamath↗️

AI x Creative Accelerator for Creative & Design Agencies - helping you innovate with latest AI tools, save time and supercharge your creative business or career | Creative Tech Entrepreneur

3mo

It is insane how ACCURATE this is! 🤯 I used FLUX Realism LoRA. Try this prompt: "Photo of a cat with a green eye and a yellow eye. Has a blue collar and a red bell. The background is a purple wall with a window. There's a lighthouse outside. Vibrant colors." Now try the same in Midjourney. I bet you will have a hard time getting it right. FLUX is on the rise for very good reasons. Developed by Black Forest Labs, the inventors of original Stable Diffusion. This is state-of-the-art generative deep learning models for media and to push the boundaries of creativity, efficiency and diversity. It excels at: +Composition, organic textures, art styles and text output. +Truly impressive language understanding and text control. +Lighting fast generation speed. Want to create with this? Comment bellow and I will send you a link where you can create for free with this same model. -- P.S. Want to turn your ideas into stunning AI-enhanced visuals in record time? Join our 3-week cohort-based course. Over 90% of Our Learners Experienced Business or Career Growth! 👉Join our waitlist, link in my bio. #midjourney #chatgpt #flux

21 Comments

Pedro Fernandez

Learning Solutions Specialist and AI thought leader

3mo

Any thoughts on “Mystic” from Freepik?

AIEntertainment (tm)

3mo

Love it. You're a talent Sachin Kamath↗️ that also teaches at this level. We're blessed. I share and promote you as long as you keep giving. AIEntertainment (tm)

Sreenivas G

CEO @A May Studios, 3D Environment, Photogrammetry, Vfx

3mo

Tried the same prompt on Gemini AI, Must say it did a Good Job. Gemini AI

1 Reaction

Ross Symons

I teach creatives how to use Generative AI

3mo

This is impressive. Wow!

Julien V.

Art director // Graphic Design // AI Designer //

3mo

Hey terrible ! I want testing flux and Lora plz Tks u very much //

Mati Ibañez Mendez

Creative Art Director | Cinephile | Branding Specialist | AI Argonaut

3mo

second try, with a twist on the prompt [One green eye and one yellow eye] Without having tried Flux yet I can say that I don't think it's better in terms of image creation. I've seen numerous reviews, but at least the prompt is more accessible. Midjourney can achieve the same result, but you have to use structured prompts and it may be less accessible for the average user. But I'll give a try to Flux...thanks for the post!

1 Reaction

Teri Campbell

Food Photographer | Video Director | AI Artist | Author

3mo

I’ve been hearing a lot about flux, but I have yet to try it out. Would love the link. Amazing stuff as always Sachin Kamath↗️

1 Reaction

Darcy Lorincz

Driving Digital Transformation | Live Streaming, Creator Economy, Gaming & Generative AI | Innovation through Strategic Leadership

3mo

I have to say that FLUX Pro stands out from a single image quality and prompt integrity perspecitve. I have not used with LORA yet so will defer any more opinion until trying that out.

Manoj A Menon

Emmy Award Nominated Designer / Creative Director @ MIKROS Animation (20+ Yrs -2D Animation/ ComicBooks & Illustration/Gaming (Console & Mobile)/Special Projects/Themeparks/Virtual Immersive )

3mo

Hey Sachin.. curious to play around with Flux. Do send me a link.

1 Reaction

Inbal Klein

Creative Marketer & AI Filmmaking Specialist | Transforming Brands with Viral Social Media Strategies | Innovation-driven Content Creator

3mo

Sometimes different prompts work better on other AI generators

See more comments

To view or add a comment, sign in

More Relevant Posts

Jumbi Edulbehram, PhD
7mo Edited
Report this post
🌟New from #NVIDIAResearch, VILA is a vision language model that can reason among multiple images, learn in context, and even understand videos. In the past, vision language models have struggled with in-context learning and reasoning within multiple images. 🤔Read our technical deep dive. #NVIDIASmartSpaces #NVIDIAMetropolis

Visual Language Models on NVIDIA Hardware with VILA | NVIDIA Technical Blog
Like Comment
To view or add a comment, sign in
OPT Machine Vision

3,208 followers
4mo
Report this post
👩🎓 What is the difference between common character recognition and OPT's? 👩🔬 Common character recognition has difficulty recognizing characters with complex background features. 💁♀️ OPT uses deep learning character recognition algorithms, which can accurately recognize characters with indistinct features. The algorithm has strong compatibility and is suitable for different backgrounds, styles, fonts, and sizes, significantly improving the accuracy and stability of text recognition. 🎨 Follow us and learn more here:https://www.optmv.net/ #characterrecognition #deeplearning #recognitionalgorithms #textrecognition
Like Comment
To view or add a comment, sign in
Michael Liebenthron

AI doesn’t stand still. It’s a living, changing entity that powers change throughout every industry across the globe. As it evolves, so do we all. From the visionaries, healers, and navigators to the creators, protectors
7mo
Report this post
🌟New from #NVIDIAResearch, VILA is a vision language model that can reason among multiple images, learn in context, and even understand videos. In the past, vision language models have struggled with in-context learning and reasoning within multiple images. 🤔Read our technical deep dive.

Visual Language Models on NVIDIA Hardware with VILA | NVIDIA Technical Blog
Like Comment
To view or add a comment, sign in
Pedro Mário Silva

Senior Solutions Architect
7mo
Report this post
🌟New from #NVIDIAResearch, VILA is a vision language model that can reason among multiple images, learn in context, and even understand videos. In the past, vision language models have struggled with in-context learning and reasoning within multiple images. 🤔Read our technical deep dive.

Visual Language Models on NVIDIA Hardware with VILA | NVIDIA Technical Blog
Like Comment
To view or add a comment, sign in
Johan Barthelemy

Senior Developer Relations Manager | Strategic Researcher Engagement | AI/ML/DL
7mo
Report this post
🌟New from #NVIDIAResearch, VILA is a vision language model that can reason among multiple images, learn in context, and even understand videos. In the past, vision language models have struggled with in-context learning and reasoning within multiple images. 🤔Read our technical deep dive.

Visual Language Models on NVIDIA Hardware with VILA | NVIDIA Technical Blog
Like Comment
To view or add a comment, sign in
Jomar Silva
7mo
Report this post
🌟New from #NVIDIAResearch, VILA is a vision language model that can reason among multiple images, learn in context, and even understand videos. In the past, vision language models have struggled with in-context learning and reasoning within multiple images. 🤔Read our technical deep dive.

Visual Language Models on NVIDIA Hardware with VILA | NVIDIA Technical Blog
Like Comment
To view or add a comment, sign in
Darrin P Johnson, MBA
7mo
Report this post
🌟New from #NVIDIAResearch, VILA is a vision language model that can reason among multiple images, learn in context, and even understand videos. In the past, vision language models have struggled with in-context learning and reasoning within multiple images. 🤔Read our technical deep dive.

Visual Language Models on NVIDIA Hardware with VILA | NVIDIA Technical Blog
Like Comment
To view or add a comment, sign in
Aleks Polak

Account Manager General Accounts @ NVIDIA | AI & HPC Technology Evangelist
7mo
Report this post
🌟New from #NVIDIAResearch, VILA is a vision language model that can reason among multiple images, learn in context, and even understand videos. In the past, vision language models have struggled with in-context learning and reasoning within multiple images. 🤔Read our technical deep dive.

Visual Language Models on NVIDIA Hardware with VILA | NVIDIA Technical Blog
Like Comment
To view or add a comment, sign in
Marc Edgar

Senior Alliance Manager for Medical Instruments - NVIDIA
6mo
Report this post
🌟New from #NVIDIAResearch, VILA is a vision language model that can reason among multiple images, learn in context, and even understand videos. In the past, vision language models have struggled with in-context learning and reasoning within multiple images. 🤔Read our technical deep dive.

Visual Language Models on NVIDIA Hardware with VILA | NVIDIA Technical Blog
Like Comment
To view or add a comment, sign in
Prashant Bhende

Technical Project Manager at Nvidia | Machine Learning Enthusiast
7mo
Report this post
🌟New from #NVIDIAResearch, VILA is a vision language model that can reason among multiple images, learn in context, and even understand videos. In the past, vision language models have struggled with in-context learning and reasoning within multiple images. 🤔Read our technical deep dive.

Visual Language Models on NVIDIA Hardware with VILA | NVIDIA Technical Blog
Like Comment
To view or add a comment, sign in

26,925 followers

984 Posts

View Profile Connect

Sachin Kamath↗️’s Post

More Relevant Posts

Explore topics