Adobe Firefly 🎇 Hands-on with Adobe's entry into the crowded AI art space. Does it live up to the hype?

I gave the Firefly beta an test drive. Let's dive into their diffusion-based AI art product with rock-solid data provenance, and a slick UX made with creators in mind. Oh and it does text!

Bilawal Sidhu @bilawalsidhu

Been hands-on with the beta of Adobe's cutting-edge Generative AI tool, and I'm impressed! 🤯 Here's a taste of the power of #AdobeFirefly 🎇 and what sets it apart in the increasingly crowded world of #AI art. Thread 🧵🎨

If you prefer watching/listening instead of reading, click here. Else read on :)

Bilawal Sidhu @bilawalsidhu

For starters, Adobe Firefly isn't one thing. It encompasses multiple AI models. It's a portal for testing new capabilities with creators, and eventually graduating them into products like Photoshop & Premiere that creators know and love. Meeting users where they are, if you will:

Bilawal Sidhu @bilawalsidhu

If you've used any text-to-image product (e.g. Stable Diffusion or DALL-E) At first glance, Adobe Firefly will be immediately familiar. But there's a few unique takes in Adobe's product experience. Let's dig in...

Bilawal Sidhu @bilawalsidhu

Adobe is using a diffusion-based model (not GigaGAN as many of us suspected!), so needless to say you can get some pretty photorealistic results.

Bilawal Sidhu @bilawalsidhu

Adobe's trained this model using Adobe Stock, which means the provenance of the data is rock solid. Adobe can't afford to alienate creators, so they have *not* trained models on Behance imagery yet, despite it being a treasure trove 💎 Will these moves woo AI art naysayers? 🤔

Bilawal Sidhu @bilawalsidhu

Firefly you can also generate text effects! Pick a font, type in some text, describe your style and voila - a new logo for my creator brand. I can totally see how this will be super useful inside photoshop or illustrator. No more complex layer effects to wrangle :)

Bilawal Sidhu @bilawalsidhu

Adobe's Firefly UX is unique in that you can provide a prompt (which describes the contents of your scene), and then you can augment it with bunch of parameters like style, color and tone, lighting and composition. This makes it super easy to iterate:

Bilawal Sidhu @bilawalsidhu

So let's say I like the the overall result, but I'm looking for a different camera angle, a slightly different aesthetic (e.g. low lighting, shot from below, cool tone). You can really dial in a look easily without futzing around with prompts. Pretty nice!

Bilawal Sidhu @bilawalsidhu

Stylized not your jam, and want to go back to a photorealistic result? As easy as clicking a button, and bam:

Bilawal Sidhu @bilawalsidhu

"Robot that toasts your bread and applies butter to it, in the style of rick and morty" produced some impressive results in Firefly:

Bilawal Sidhu @bilawalsidhu

You're probably wondering how hands look? Pretty coherent! Even with a prompt like this: Punjabi man in flannel shirt using AI voice dictation to create the client pitch deck while drinking espresso a cozy cabin, while wearing an Oculus VR headset, with a laptop on the table

Bilawal Sidhu @bilawalsidhu

@ericsnowden made an awesome analogy about ingredients and taking decades of Adobe tech combined with these newer models to make amazing recipes. And I have to say, the dishes do look good! Case in point:

That's a wrap for this out-of-band edition!
If you enjoyed this deep dive on Adobe Firefly (http://adobe.com/firefly), it’d help a ton if you:

- RT this thread to share with your audience

- Follow me on Twitter @bilawalsidhu (thanks for 10K ya’ll!)

- Subscribe to get these right to your inbox:

Bilawal Sidhu signing out — see ya’ll in the next one!