Share this page!

Maybe Scrolly?
Emm Profile picture
Twitter logo
Nov 3 • 14 tweets • 10 min read
Tonight's dreamboothing is about grenades 💣(!).

I made a #dreambooth finetune from a few Sci-Fi grenade illustrations.

Explosive thread 🧵👇

#AI #StableDiffusion ImageImageImageImage
First, some random grenades, no specific adjectives. Image
But they look great in blue too! ImageImageImageImage
Green + urban background ImageImageImageImage
Or just military olive green, white background. ImageImageImageImage
How about complementary colors. Purple + yellow ⬇️ ImageImageImageImage
Orange + blue + black steel Image
Green and red? Plus, the elongated "spray shape" is worth trying. Thanks, #img2img 🙏 ImageImageImageImage
I was a bit less successful with more elaborated prompt engineering, but I'll keep pushing. "A soldier is holding a red grenade in his hand, HDR, 8K, realistic". Image
Some SciFi firefighter equipment? ImageImageImageImage
More random trials. ImageImageImageImage
If you like this thread, feel free to like/RT/comment, or follow. More experiments & feedback on the amazing #Dreambooth tech coming soon.

@natanielruizg & his team rock :) Image
All this was quickly generated (10 minutes) using very simple prompts (e.g. “a blue grenade”). No more endless prompting with random, inconsistent results.

Cut through the noise and get straight results with Dreambooth (and soon with us :)
Image

• • •

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

Keep Current with Emm

Emm 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 @emmanuel_2m

Emm Profile picture
Nov 5
Let’s keep using #StableDiffusion to design or create #game assets, quickly and consistently.

In 15 min, generated an army of golems with similar shapes and sizes, but various “materials” (lava, rock, water, ice, forest, sand, gold…).

No in-painting is needed. Thread 🧵 Image
Step 1 (as in my previous examples with chests - ), I made a Dreambooth finetune w. just 11 pics.

As soon as the model was trained, the first step was randomly generating a large set of images w. a simple prompt ("golem, detailed, realistic, 3D rendering") ImageImage
Each golem can be extracted by removing the images' backgrounds (reco: @photoroom_app).

Some of the designs are amazing. However, the golems all look very similar to each other. Let's separate them into categories. Image
Read 12 tweets
Emm Profile picture
Nov 4
People loved the "treasure chests" #AI experiment I posted yesterday! However, the chests were all closed 🤨.

So I quickly ran a second training on a different dataset, and this time, gold and diamonds are overflowing from the open chests! 🪙🤑💰

ImageImageImageImage
I also used #img2img to instantly generate dozens of variants, "inspired“ by a single original photograph.

This provides consistent assets (similar shape, size, or materials) with some slight variations. It's up to the artist/user to select which one looks best. Image
Same thing here, using #img2img - however, I prompted "steel chest" instead of "wooden chest"

While it's not 100% perfect, there's still more steel in these chests than in the previous ones.

Also, some of the assets are disjoint or show anomalies. Some fine-tuning is necessary Image
Read 4 tweets
Emm Profile picture
Nov 3
#Dreambooth will change how 2D game assets are being designed or generated.

Today's exploration: treasure chests 💎💰.

I trained Stable Diffusion with some low-poly treasure chests (23 images). 1h later, here's what's possible (🧵): ImageImageImageImage
At first, I randomly generated a set of 64 items, without any specific prompt engineering ("a treasure chest"). Image
Here's a close-up view: Image
Read 11 tweets
Emm Profile picture
Oct 28
I designed 160 weapons for a heroic fantasy game, inspired by World of Warcraft... in just a few minutes.

A short thread on Generative AI & gaming 🧵

#GenerativeAI #AI #StableDiffusion #Dreambooth #Midjourney #Dalle #Gaming #UGC
Generative AI is likely to go big in vertical communities such as gaming, per @Tocelot - “The fringe is where revolutions start”.

AI can help design and quickly create new gaming environments, textures, scenes, characters, weapons, skins... or props.

@Tocelot Dalle, Midjourney or StableDiffusion generate exquisite images. However, it’s challenging to reconstruct specific subjects while maintaining high fidelity to their key visual features. Even w dozens of detailed iterations, the outcome is rarely consistent. Prompting is daunting…
Read 8 tweets
Emm Profile picture
Sep 23, 2021
I've listened to hundreds of podcasts and interviews about the Metaverse, but this one honestly stands out as one of the best so far. In just 30 min, @AdamDraper explains why NFTs matter and why they will be a key element of the #Metaverse

A thread 🧵👇
And because I really enjoyed it, I extracted are some key quotes from the transcript. But you should listen to the video too! And learn about NFTs, the Metaverse, DAOs, identity in the metaverse, and why you want to be part of new technologies that seem like “jokes” at first.
“Scarcity on the internet is gonna be a big deal. People are saying that we're in an NFT bubble. I think people are negative with hope, they hope that it pops so that they can buy in”.
Read 20 tweets
Emm Profile picture
May 11, 2021
So last WE, I went down into the Catacombs of Paris. If you're not familiar, it's an insane anthill-like network of 200 mi. of galleries and chambers, centuries-old, 60 ft beneath the surface. @NewYorker wrote about it in 2019: newyorker.com/news/dispatch/…. Here's a short story.

1/12
The goal was to 3D scan as many places as possible, using only the iPhone 12 Pro/LiDAR (and two powerful LED lights). And so we spent 12 hrs underground, walking (or crawling) more than 20 miles, and scanning 30 different places using @Scaniverse, @PolycamAI, and @Sitescape

2/12
All scans were uploaded to @Sketchfab and the whole series is available here: sketchfab.com/edemaistre/col…. Interestingly I was able to process all the scans immediately on the device, down below (without service). Cool way to demonstrate the power of LiDAR scanning w the iPhone

3/12
Read 12 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 on Twitter!

Send Email!

:(