Graphics & imaging, web apps & web components. Dad, halfling bard, & founding engineer at @reve. Previously: Adobe, Facebook, Heroku

Greensboro, NC
Joined April 2008
Hunter Loftis retweeted
Reve's Chrome extension is here. Add images from across the web to Albums and References in Reve.
6
11
6
125
23,722
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.
1
6
1,404
Hunter Loftis retweeted
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.
3
8
45
2,427
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.
2
5
19
2,305
> The real creative work is that of iteration.
What is an image?
1
5
1,167
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.
2
2
13
1,317
Hunter Loftis retweeted
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.
Replying to @reve
We’re releasing an early version of our new text-to-image model, and we’re already a top three model on @arena
9
26
4
182
38,492
Hunter Loftis retweeted
Reve v1.5 is here. Our latest image model, now with 4K resolution.
36
68
19
604
583,803
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 ⬇️
8
445
Hunter Loftis retweeted
Any sufficiently advanced technology is indistinguishable from magic
Reimagine reality. reve.com
24
106
25
1,802
387,000
this is what I've been building
Reimagine reality. reve.com
1
2
1
16
3,000
Hunter Loftis retweeted
The Dark Side of Arch. Crafted in @reveimage
1
6
406
Hunter Loftis retweeted
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)
1
9
3
57
14,493
Hunter Loftis retweeted
Halfmoon is Reve Image — and it’s the best image model in the world 🥇 (🔊)
123
201
130
1,452
547,597
Hunter Loftis retweeted
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
13
24
8
249
603,765
The Halfmoon 🌓 reveal: Congratulations to @reveimage on creating the world’s leading image generation model with Reve Image! Reve Image has been in the Artificial Analysis Image Arena over the past week and is the clear leader, beating strong competition including Recraft V3, Google's Imagen 3, Midjourney v6.1, and Black Forest Lab's FLUX.1.1 [pro]. The model stands out for its impressive text rendering, prompt adherence, and aesthetics. Currently, the model is accessible through Reve’s website (link below), an API is not yet available. See below for example images and a link to try the model out for yourself 🧵
6
41
17
305
170,705
Help me test websockets across timezones? I just need you to wiggle your cursor / drag your finger from wherever you are right now: hunterloftis-deno-pointers.d…
2
1
Thanks folks, that's the data I needed!
1
After using a Steam Deck as my daily-driver for 3 months, I've finally given in and ordered an X1 Carbon with Fedora. 🧢 off to @valvesoftware - the deck is the smoothest Linux PC experience I've seen so far, but it takes a Jenga tower of virtualization to use as a dev machine.
1
3