BeatBandit - New era for storytellers

Turn a raw story idea into beats, scenes, treatment and a screenplay draft - 100 × faster, automatically applying professional screenwriter techniques, without losing control of your voice.

It’s happening!

🧵Read all about BeatBandit I started BeatBandit with a realization. AI is changing the world of storytelling.

Eventually producing a story into film, TV, animation, book, game will become 100x faster/cheaper than what is it right now.

Story creation needs to do the same.

Writing a screenplay can’t take months if producing it takes weeks.

We see a 100 companies focusing on creating AI production tools, but there doesn’t seem to be 100 companies focusing on helping people to write great stories.

Yet a polished production and fancy visuals are irrelevant if your story… well, sucks.

This challenge remains – how to write a good story?

I've been fortunate to be able to test "images with ChatGPT" for the past few weeks.

Short verdict: It's basically the best at everything

Like genuinely next level. Photorealism, illustration, genuine prompt comprehension, actual understanding, remixing with natural language.

Yes there are specific things it cannot do, but for many things it can do it's vastly superior to anything else currently out there.

For image generation, OpenAI is very much back! yes it does this

a red wine glass absolutely full of wine, overflowing, photograph

Hey did you know that Flux can do more than just photo models!

Flux 1 dev with 3 Loras + Magnific + Luminar for film grain

View end of🧵 for details. @bfl_ml


For these images, I didn't run the ultimate upscale step so they're a bit rougher in overall appearance (which I think fits).

If you want them smoother, run the Ultimate SD step before @Magnific_AI / your favourite upscaler.

I am probably the last person to do this tutorial - everyone did this a while ago - but no matter;

Consistent characters in MidJourney and SD

It's quite useful! 🧵





Step 1

Prompt something like this: "Two images side by side, <your character description>, photo booth portrait --ar 2:1"

And you'll get nice candidates. Let's go with image 3, press U3.

THIS IS THE NEXT.

Post Photographic Perspectives
A @fellowshiptrust project

Featuring my upcoming 500-piece main collection "REWORLD" (Day 1) and the fantastic post-photography group collection from 10 super-talented AI artists (Day 2), all pieces curated by yours truly.

https://twitter.com/fellowshiptrust/status/1630264682987819008

Check out the info and samples from the "REWORLD" collection from my interview with @halecar2

postphotography.xyz/in-conversation

Fashion 2.0

First try training Stable Diffusion v2.0 (512-base).

Some individual photos + tech details in the🧵

#stablediffusion #ai #portrait #fashion Fashion 2.0

Broken Camera

Selected images from the Rejected pile.

If you're not a fan of cursed images, best not to watch this video.
#stablediffusion #fashion #photos Broken Camera 1

Film Camera

Trained a new model for 'realistic photos' - whatever that ever means. It works pretty well.
Imagine where the quality will be in a year.
#stablediffusion #portrait Film Camera - few individual portraits

Songs of Wander

#ai #street #photography Songs of Wander 2

#stablediffusion #dreambooth

Dreambooth training for Stable Diffusion is extremely powerful. You can train a new token to the "person" class to create very convincing looking images of them. I've posted some examples in the past days.

But it's not the coolest thing you can do... You can train the "style" class to create new styles. For instance the "arcane" style is well known - it skews all results to this particular Riot games style.

https://twitter.com/_akhaliq/status/1584557965696466945?s=20&t=rhrANiGeN0p90LN3uQGe5g

But - that's not the coolest thing you can do...

Black portraits

Dreambooth training SD 1.5 model for photographic style.

#dreambooth #stablediffusion #portrait Black portraits #2

#dreambooth #stablediffusion #portrait

"Model Drinking Water"

#stablediffusion "Model Eating Bread"

#stablediffusion

Finetuned the new SD1.5 model with some realistic portrait photos, ran a quick test of quality.

No GFPGAN/CodeFormer used, no inpainting - there's details I could Photoshop here and there, but ... Not bad. Quickly looking, one might be fooled.

#stablediffusion #portrait Few more from the same test.

Andy Griffith (Matlock era) in...

Top Gun / Avengers / Star Wars / Game of Thrones

#andygriffith #dreambooth #stablediffusion Andy Griffith (Matlock era) in...

Mad Max Fury Road / Pirates of the Caribbean / Gone with the Wind / Star Trek

#andygriffith #dreambooth #stablediffusion

Jim Carrey as Bon Jovi

#jimcarrey #bonjovi Jim Carrey as Blink-182

#jimcarrey #blink182

Emma Stone as Gollum

#emmastone #gollum #dreambooth #stablediffusion Emma Stone in Pirates of the Caribbean

#emmastone #piratesofthecaribbean #dreambooth #stablediffusion

AI will make the creation of technically excellent art available to the masses. What does this mean to current artists? Do artists become extinct?
NO, I would argue. A short thread… 🧵 By “technically excellent art” I mean the way things look like. AI generated art will look spec-ta-cu-lar. Better than the skill level of 99% of artists. Already things like DALL·E 2 show what will be possible, and it’s just the beginning. Minds will be blown.