XR Multiverse @XRMultiverse

DEZ Expert in Design and AI. Design Generation Evangelist. Toronto Joined January 2016

Tweets

18K
Followers

239
Following

225
Likes

3K

XR Multiverse @XRMultiverse

10 hours ago

I built 60 apps in two months using AI. "Invisible AI" applications, where chatbots aren't the focus, are the next opportunity, enabling the rest of the world to finally experience AI the way it's meant to be. Things are going to change. #DesignCntrl

0 0 0 12 0

Download Image

XR Multiverse @XRMultiverse

17 hours ago

Any sufficiently advanced technology is indistinguishable from magic. Unless you are the magician.

0 0 0 9 0

Linoy Tsaban🎗️ @linoy_tsaban

2 days ago

huggingface.co/spaces/linoyts…

1 1 10 568 12

Linoy Tsaban🎗️ @linoy_tsaban

2 days ago

Inpainting with Qwen Edit is like working with a magic brush amazing how well it works out of the box

8 34 206 13K 154

Download Video

XR Multiverse @XRMultiverse

a day ago

I have wasted hours arguing with Gemini to not continually replace everything in my fucking app with Gemini #gemini #fuck

0 0 0 25 0

Ostris @ostrisai

3 days ago

I trained a @Alibaba_Qwen Qwen Image Edit LoRA for inpainting. Just paint the part you want inpainted green (0, 255, 0), and it will inpaint only that section. Links to LoRA and video breakdown about it in 🧵

14 58 378 23K 275

Download Image

XR Multiverse @XRMultiverse

2 days ago

🚨BREAKING NEWS! We're calling it #Chat4o, just so everyone knows that it's not CGPT *wink*, but its here for fun and enjoyment either way. I'm testing used Custom Instructions to make it tell constant Dad jokes. Stellar quality every time. #Keep4oforever #Chat4o #Keep4o

1 0 3 104 0

Download Image

Gordon Wetzstein @GordonWetzstein

2 days ago

How do we generate videos on the scale of minutes, without drifting or forgetting about the historical context? We introduce Mixture of Contexts. Every minute-long video below is the direct output of our model in a single pass, with no post-processing, stitching, or editing. 1/4

21 82 489 75K 391

Download Video

Benjamin De Kraker @BenjaminDEKR

2 days ago

Update: finally got this working reliably Props to @OfficialLoganK for providing a working example to reverse engineer. Had to use a much more specific prompt with bounding box rules: "Task: Detect ball, dog, cardboard box, desk, model airplane. Return AT MOST 20 detections.…

Benjamin De Kraker @BenjaminDEKR

2 days ago

23 5 89 207K 23

Download Image

49 42 926 195K 1K

Download Image

XR Multiverse @XRMultiverse

2 days ago

0 0 0 22 0

Download Image

apolinario 🌐 @multimodalart

4 days ago

- Nano Banana with the 🎬 button: huggingface.co/spaces/multimo… - Standalone Wan 2.2 first-last-frame app: huggingface.co/spaces/multimo…

5 2 35 2K 34

Ahmad @TheAhmadOsman

4 days ago

China saved opensource LLMs, some notable releases from July only > Kimi K2 > Qwen3 235B-A22B-2507 > Qwen3 Coder 480B-A35B > Qwen3 235B-A22B-Thinking-2507 > GLM-4.5 > GLM-4.5 Air > Qwen3 30B-A3B-2507 > Qwen3 30B-A3B-Thinking-2507 > Qwen3 Coder 30B-A3B US & EU need to do better

51 122 1K 77K 275

Rohan Paul @rohanpaul_ai

4 days ago

🎨 Super impressive. Researchers built an optical diffusion model that uses light, not heavy computer math, to generate images with quality similar to standard AI diffusion but at near-zero power. This work shows a light powered image generator that produces images with almost…

67 224 2K 166K 1K

Download Image

Franky @FrankYouChill

6 days ago

Paper link: arxiv.org/pdf/2508.20722 github.com/microsoft/rStar

0 5 43 4K 51

Sehaj Singh @heysehajsingh

6 days ago

Check out the open-source project at github.com/resemble-ai/ch… for more details. Try it here: resemble.ai You can also try it for free on Hugging Face at huggingface.co/spaces/Resembl…