Javi Lopez ⛩️ Profile picture
Dec 25, 2022 25 tweets 15 min read Read on X
17 tools and tricks I use the most to generate impressive images with AI 🤖.

This is my christmas gift to all of you 🎁!

Follow me on this travel, you won't regret 🧵⤵️
First of all, to arouse your interest...

Here you have 4 of the latest images that I have generated 100% with artificial intelligence using just a text description of mine.

Do you want to know what programs I have used?

The first 3 are obvious ⤵️
1️⃣ MidJourney — #midjourney

One of the questions I get asked the most is: what is your favorite AI software to generate images?

Without a doubt, for me it is @midjourney, due to its balance between coherence and an "artistic" touch.

midjourney.com
2️⃣ StableDiffusion — #stablediffusion

You can try it in web version (DreamStudio), Google Colab version or even download it to your computer.

@StabilityAI is an Open Source monster that has revolutionized the world of generative AI in recent months.

beta.dreamstudio.ai/home
3️⃣ DALL·E (@OpenAI) — #dalle2

The precursor of the revolution.

It has fallen a bit behind but it still hides some aces in the hole such as "in painting" and its "infinite canvas".

For the novel I'm writing I like the illustration style it achieves.

openai.com/dall-e-2/
4️⃣ Tencent Face Restoration.

Ideal for retouching a previously generated portrait with one of the above. It adds lot of detail and realism. Especially in eyes, lips, nose and cheekbones.

Very powerful and simple.

replicate.com/tencentarc/gfp…
5️⃣ CodeFormer.

Similar to the previous one, but more focused in photo restoration and detail enhancing. Incredible results!

huggingface.co/spaces/sczhou/…
6️⃣ FaceApp.

One of my secrets 😉. Don't tell anyone! Haha!

This is one of the most used mobile apps by instagramers who want to look handsomer / prettier.

Remarkably, applied to an AI-generated face, it achieves brutal levels of realism and detail.

faceapp.com
7️⃣ Lexica.

The fastest way to learn this discipline is, undoubtedly, to see lot of example prompts (the text description that generates the image).

Lexica is the world's largest prompt repository. On the order of MILLIONS of indexed descriptions.

lexica.art
8️⃣ Leiapix converter.

Simple and brutal.

Get a 3d effect on a 2d image. And it allows you to download it in video and GIF.

convert.leiapix.com
9️⃣ MugLife.

To animate faces: make them smile, talk, frown, stick out their tongues and much more!

muglife.com
🔟 Relight.

Another easy to use but potentially brutal app.

Upload an image/photo (mostly portraits) and change the lighting as you wish, with just a few well-placed clicks...

I use it more than I admit 😉

clipdrop.co/relight
1️⃣1️⃣ MovePic.

Another mobile app that I have fallen in love with.

For example: I have just generated this volcano in 5 minutes and with a few clicks I have animated the river of lava, the smoke and created a storm.

Who gives more for so little?

play.google.com/store/apps/det…
1️⃣2️⃣ I already talked about #dalle2, but I think I have to explain a bit more about its "out painting" capabilities: they need to have a special place on this list.

Check this out because It's awesome!

1️⃣3️⃣ Lexica Aperture.

Do you need to generate photographies that appear to be 100% real? Well, you can!

Don't try to use the "bikini" word in your prompts because... oh, just check it out yourself 😂

lexica.art/aperture
1️⃣4️⃣ Diffuse The Rest

You are going to have lots of fun with this one. Specially if you have children.

Just draw a quick and dirt sketch, write a prompt and watch magic happens! It converts your dirty sketch into something awesome.

huggingface.co/spaces/hugging…
1️⃣5️⃣ Img2img (Stable Diffusion).

Similar to the previous one, but more advanced. You will need some knowledge to install and run it in your computer. I'm sure that @NerdyRodent will be happy to help you :)

github.com/AUTOMATIC1111 Img2Image example created by @NerdyRodent.
1️⃣6️⃣ Prompt-to-Prompt.

Unfortunately you will also need some knowledge using Google Colab notebooks + Huggingface (token) for this one.

But if you give it some time, you really can convert ANYTHING to any OTHER thing. Like a miracle! 😂

Img by @DotCSV.

colab.research.google.com/drive/1pl7dPvV… Prompt 2 Prompt image generated by @DotCSV.
1️⃣7️⃣ BONUS: Riffusion 🎵.

This is not for generative images... this is for generative MUSIC!

Yes, you heard me well: a "text prompt to music" generator. It's quite limited nowadays, but it can already create some cool "lofi hip hop" beats, for example.

huggingface.co/spaces/fffilon…
Hope u liked this thread!

Would you like to learn more about AI image generation?

🔥 Follow me! 🔥

I'm working on a prompts bundle I will release soon, with detailed explanations to be able to create awesome images! It will include the MOST ADVANCED prompts I found.
BONUS TRACK!

@Scenario_gg will soon be released to everyone interested in creating resources for video games. I haven't had the opportunity of trying it yet, but the examples @emmanuel_2m is showing in his threads are awesome.
BONUS 2.

Soon I will be able to use @LeonardoAi_ too. I can't wait to see what they are cooking!
If you know any other useful AI tool, please tell me 🙏 and I will add it to this list 😉
OK, let's continue!

2️⃣0️⃣. Remove.bg

The delete backgrounds and/or to add new ones!

remove.bg

Tip by @destinykrainbow.
2️⃣1️⃣ Cleanup Pictures.

For removing extra stuff in images. Bye, bye to those things you don't want! Super useful.

Tip by @destinykrainbow.

cleanup.pictures

• • •

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

Keep Current with Javi Lopez ⛩️

Javi Lopez ⛩️ 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 @javilopen

Nov 27
IT'S FINALY HERE

🔥 Magnific Skin Enhancer 🔥

• No more AI plastic skins!
• Enhance EVERYTHING in your image, not only the skin!
• 3 different flavours + easy presets: improve light, level or reality, color grading, etc.

Let's dive in + tutorials + tips 🧵👇 Image
Image
First of all, if you can't wait, here you have the link! AVAILABLE NOW on Magnific & rolling out to Freepik users today!

I’ll also randomly grant access to some of you who reply with a interesting message 😘

👇👇👇

magnific.ai
You’ve been asking for a Skin Enhancer in Magnific for ages!

So I want to apologize for taking so long. But hey, better late than never!

Skin Enhancer is built for pros who need CONTROL, so it comes in 3 flavors to cover every level:

- Flexible + presets
- Creative
- Faithful Image
Read 14 tweets
Oct 26
Professional photographers don’t know they can improve their work with advanced AI upscaling.

I tested it on my old Nikon photos from Tokyo (2014) and the results blew my mind 🤯

Super quick tutorial 🧵👇
1. Upscale in Magnific AI:

- Precision
- v2 (Sublime)
- 6x (usually 4x is ok, but this one looked better)
- Sharpen: 15%
- Smart Grain: 2% (the photo was already quite grainy)

2,000 x 1,328 => 12,000 x 7,968 🤯 Image
2. That's all, enjoy! 😂

I was never so easy to improve your old (or new) professional photograpies, vfx, illustrations, etc!

Enjoy!

Read 11 tweets
Oct 24
AI upscaling in 2025 is absolutely wild 🤯

This shouldn't be possible... But here we are!

Super quick tutorial 👇
This is a combo of two upscalers inside Magnific:

1. One pass of Magnific Creative (2x)

"Vivid" preset with Illusio engine (that is perfect for architecture, 3d, etc): Image
2. A second pass of Precision v2 Sublime (4x)

With Sharpen 30% and just a small bit of Smart Grain (4%) Image
Read 6 tweets
May 25
There's no way Hollywood won't be affected by this.

I created this whole scene in less than 2h using Veo 3 (AI video), Magnific (upscaling), Suno (music, except the first 3s 😉) and CapCut (editing).

The Cambric Explosion of content has already started!

Full tutorial 👇
1. Idea

I've had this idea (a mood) of mixing a 7-eleven at night and a 🐲 for over 2y now.

The concept came to me then, but it wasn't until now that I've been able to bring it to life visually.

Veo 3 feels like being back in Apr 2022, when DALL·E 2 hit my brain like a truck.
2. Video generation using Veo 3 inside Freepik (not yet available but soon)

I used ChatGPT to craft all the prompts and then did all the video generation inside Freepik using Veo 3.

Something I've learned is that Veo 3 can handle really long and complex prompts, so don't hesitate to use very detailed descriptions to express the vision you want to create.

Example:

"Close-up shot of a pair of hands reaching toward a dusty black tome resting on a low shelf inside a dimly lit 7-Eleven. The book has a worn leather cover with a flaming dragon etched in glowing, fiery lines across the front. Above the image, an unreadable title is inscribed in ancient golden runes. The hands pick up the book slowly and carefully, as if sensing its weight and age. At the edges of the frame, part of a red puffy vest is visible over a faded denim jacket and a plaid shirt sleeve, revealing just enough of the young man’s layered clothing to hint at his presence."Image
Read 9 tweets
May 22
Just got access to Veo 3 and the first thing I did was try the Will Smith spaghetti test. SOUND ON
Spaguettis are so cooked. But flamenco is so back!

"A dog dressed as a female flamenco dancer dancing flamenco on a tablao in a bar in Seville."

😅😂
One of my usual favourite tests. The soldier riding a dog during WW2.
Read 24 tweets
Apr 29
⚡ IT'S FINALLY HERE!

F-Lite: our first foundational model for image generation. A collaboration between Freepik ♥️ Fal.

• Open Source
• Fully commercially usable
• 10B parameter DiT trained on 80M images
• Trained with 100% licensed data

Link + info 🧵👇 Image
We’ve been secretly working on this for months! It feels good to finally share it!

LINKS:

• Regular version: more predictable and prompt-faithful, but less artistic: fal.ai/models/fal-ai/…

• Texture version: is more chaotic and error-prone, but delivers better textures and creative compositions: fal.ai/models/fal-ai/…

• Paper: github.com/fal-ai/f-lite/…

Enjoy!Image
Image
Image
Image
Congrats to @cloneofsimo, @ivanprado, @kuer5ord, @info_libertas and the rest of the team that built this model from scratch!

I did nothing except to test it 😍 Image
Image
Read 7 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!

:(