


Dad, halfling bard, & founding engineer at @reve AI. Previously: Adobe, Facebook, Salesforce, Heroku


My current favorite Reve feature - a few seconds on my phone & a non-designer like me can put together something actually usable.
Introducing Templates. Add your touch to any layout. Swap in your product, copy, or brand, and watch the elements harmonize.

Introducing Reframe and Relayout in Reve. Reframe is much better than traditional diffusion outpainting or something like Generative Fill in Photoshop because: - The entire image is regenerated so everything is perfectly harmonized (changes in light, reflections, subtle adjustments in camera angle, etc). - You can use it to "push in" or zoom as well as outpaint. - It uses the world's best 4K model. Relayout allows you to pick new aspect ratios for images and to reimagine them as if they'd been created that way from the beginning. That means laying out text more effectively and aesthetically, filling in plausible details, etc. Accelerate your creative velocity with Reframe and Relayout. Both are available now in Reve.

Our research team is just incredible. Meta kept the #2 rank for < 24 hours!
Reve 2.1 is here. The world’s best 4K image model just got better. Greater prompt understanding, world knowledge, and stronger foreign-text rendering.

> The real creative work is that of iteration.
What is an image?

Don't miss the deep dive into how our research team hit this level of quality with 0.1x the training resources: blog.reve.com/posts/the-layo…
Today, we’re launching Reve 2.0, the best 4K image model in the world. We invented a new way to generate and edit any image using precise layouts. For the first time, it’s possible to create images you can touch.

Reve's new text-to-image model is here. Really proud of the team to rank at #3 with the big labs. To my knowledge, we are the first lab to use native pixel space diffusion without latent autoencoder at 4k (16MP) resolution for production level image generation.
We’re releasing an early version of our new text-to-image model, and we’re already a top three model on @arena


It was very fun to pull this editor together for the 1.0 launch with @dkrajews123. We're shipping bugfixes & improvements already based on feedback. Let us know what works for you & what doesn't!
Discovered an insanely cool feature in the new @reve image model. You can now edit specific objects within an image - move, delete, or prompt changes while keeping the rest consistent. Watch me manipulate this scene ⬇️

Any sufficiently advanced technology is indistinguishable from magic
Reimagine reality. reve.com

this is what I've been building
Reimagine reality. reve.com


The Dark Side of Arch. Crafted in @reveimage

Typography in generative models has been a hard problem to solve. Reve Image 1 does not only generate long text, but also it is very good at stylized typography. You can generate designs like this, it follows the prompt faithfully.
Excited to come out of stealth at @reveimage! Today's text-to-image/video models, in contrast to LLMs, lack logic. Images seem plausible initially but fall apart under scrutiny: painting techniques don't match, props don't carry meaning, and compositions lack intention. (1/4)

Halfmoon is Reve Image — and it’s the best image model in the world 🥇 (🔊)

Anyone else try Reve image generator yet? @reveimage Discovered it earlier today and it's DAMN GOOD, very nice surprise! Aesthetics are excellent! Solid prompt adherence as well. Censorship is also quite relaxed. Results can look very cinematic! Highly recommend trying it when you can, it seems like their servers are overloaded right now. preview.reve.art/app Brought one of the frames I generated with Reve to life using @Kling_ai