
Download Manager @LumaLabsAI | WebGPU poor with diffusers.js
Space void
Joined June 2009
- Tweets62.7K
- Following392
- Followers1.2K
- Likes14.5K
Pinned Tweet
you can now generate images directly in the browser with 4-8 steps in 5-8 seconds on m1 max. latest chrome canary is required
islamov.ai/diffusers.js/
it's really facsinating to see so much luddites in coding and math. now i seriously consider learning more math to solve something for fun (with lots of AI assistance, of course)
You’re absolutely right! I should not have emailed your credentials in a response to phishing email.
Today we announce 1Password for Agents platform, building with companies @Muse, SpaceX Super Intelligence Grok @Bot, @AnthropicAI’s @Claudeai, @OpenAI, @TownAI, @Browserbase, @Browser_use, @heydana_ai, Instinct, @usekernel, @Perplexity_ai, @tryramp, @Tomo, and @wajo_ai, with more integrations on the way. 🎉
We've heard from so many of our customers who want to use these new personal AI agents to help them get more done, but want more control over what the agent can access with the same trust and ease of use they get when using 1Password directly.
1Password for Agents gives your agents access without giving up your passwords. When an agent reaches a sign-in form, it requests a credential from your vault. If you approve the request, 1Password directly auto-fills the credential in the destination site so the agent can’t see or take possession of the credentials.
The agent gets the task done, but it doesn’t get your passwords..
You stay in control. 1Password for Agents free and optional for personal and family accounts. Unless you opt-in to an agent connector, agents cannot touch your vault.
➡️Learn more: bit.ly/487da6J
with astra i've finally restored dts hd/x passthrough on my lg g5
lg removed it in c/g5 (was working in c/g4) and fable, of course, refused to even research on how to do that. because cYbErSeCuRiTy
astra was like "hmm... we need to root it, bring it online... ok, press the button, ... ok ... rooted, now will do kernel module ..."
ofc i had to guide it a bit, test and hint that we can disassemble g4 firmware to extract dts handing code. took two evenings and it works perfectly now. only passthrough to my soundbar but that's what i needed. code is here in case you're suffering like i was. fully reversible, no firmware change needed github.com/dakenf/lg-g5-dts
How about reverse engineering a classic game called Disco Elysium
I’ve never finished it, although wanted and now I will be able to do that on iPad thanks to astra
Since DLSS5 is just a one-step DiT, you can run it anywhere, for example on iPad in Warcraft 3
With Astra I could make it run at 4-5 fps using split of apple’s neural engine and gpu
This is OpenRealm with patched rendering pipeline. And quite a lot of fixes to make it actually playable. I guess soon or even now we can make our own remasters to run anywhere
Arthur Islamov retweeted
Uni-1 is here! A new kind of model that thinks and generates pixels simultaneously. Less artificial. More intelligent.
Arthur Islamov retweeted
Excited to introduce Uni-1, our new *unified* multimodal model that does both understanding and generation: lumalabs.ai/uni-1
TLDR: I think Uni-1 @LumaLabsAI is > GPT Image 1.5 in many cases, and toe-to-toe with Nano Banana Pro/2. (showcase below)
Arthur Islamov retweeted
This is Ray3. The world’s first reasoning video model, and the first to generate studio-grade HDR. Now with an all-new Draft Mode for rapid iteration in creative workflows, and state of the art physics and consistency. Available now for free in Dream Machine.
Arthur Islamov retweeted
Introducing Modify Video. Reimagine any video. Shoot it in post with director-grade control over style, character, and setting. Restyle expressive performances, swap entire worlds, or redesign the frame to your vision. Shoot once. Shape infinitely.
Arthur Islamov retweeted
Image to Video with #Ray2 is here. Drop any image into Dream Machine to make it a video and bring it to life — from historic artifacts and paintings to memes, custom art and photos of any kind. Available now.
Arthur Islamov retweeted
Introducing Ray2, a new frontier in video generative models. Scaled to 10x compute, #Ray2 creates realistic videos with natural and coherent motion, unlocking new freedoms of creative expression and visual storytelling. Available now. Learn more lumalabs.ai/ray.
Arthur Islamov retweeted
Say hello to the all-new #DreamMachine. 🚀 Your visual thought partner—where ideas become reality. Ideate, visualize, and share your ideas with the world. Available now.
as usual, available today for everyone
🚀 Introducing the Dream Machine API. Developers can now build and scale creative products with the world's most popular and intuitive video generation model without building complex tools in their apps. Start today lumalabs.ai/dream-machine/ap… #LumaDreamMachine
Arthur Islamov retweeted
🎥✨Camera Motion is here in Dream Machine 1.6! Effortlessly direct text-to-video and image-to-video scenes with simple commands! Just type in ‘camera’ to unlock camera motions! Imagine in #LumaDreamMachine 🎬🚀
lumalabs.ai/dream-machine
Arthur Islamov retweeted
Okay, #DreamMachine's new keyframe feature is already getting me excited. 🔥🔥











