RahimEntezari

Senior Research Scientist @wayve_ai, ex-StabilityAI

[RahimEntezari @rahiment]

I am proud member of Stable Diffusion 3, and we won best paper award at #ICML2024

[Behnam Neyshabur @bneyshabur]

We have been heads down but wanted to share a bit about what we are doing 🧵

[RahimEntezari @rahiment]

@bneyshabur Congratulation Behnam! Wish you and the team luck and Looking forward to hearing more!

[RahimEntezari @rahiment]

This is why Iranian regime shutdown internet, to kill thousands of people. Please spread the world

[Behnam Neyshabur @bneyshabur]

I still get a lot of questions about doing a PhD in ML so I'm resurfacing a three threads I wrote about this including some fun personal stories 🧵

[RahimEntezari @rahiment]

@DongWan06935465 Consistency was much better than I have seen with Wan, but what happened to the cheeze in the frames before last?
my 5x5 was the basic version

[RahimEntezari @rahiment]

@shlomifruchter @GoogleDeepMind @thwiedemer @priyankjaini Tried Wan2.5 an old Sora, both failed too in 5x5 maze. not success at all. waiting for sora2

[RahimEntezari @rahiment]

@shlomifruchter @GoogleDeepMind @thwiedemer @priyankjaini These are actually amazing properties! I just tried the maze, 5x5 with Wan model and it totally failed, not a single solution for 100 generations x different CFGs.
I wonder if Maze was part of training set though

[Varun Jampani @jampani_varun]

🎬 Introducing Stable Cinemetrics, to be presented at NeurIPS 2025.

We present the first taxonomy of professional controls to systematically study and control video generative models through the lens of filmmaking.

Interactive webpage with paper link: https://t.co/Eh4Hw3hBZl
🧵

[RahimEntezari @rahiment]

@shlomifruchter We also included some evals on Veo3 in Table 13.

[RahimEntezari @rahiment]

How ready are T2V for professional filmmaking?
In our Nuerips paper, we showed that how far we are from making cinematic ready generations, in Events, Camera, Setup and lighting.

[Varun Jampani @jampani_varun]

🎬 Introducing Stable Cinemetrics, to be presented at NeurIPS 2025.

We present the first taxonomy of professional controls to systematically study and control video generative models through the lens of filmmaking.

Interactive webpage with paper link: https://t.co/Eh4Hw3hBZl
🧵

[RahimEntezari @rahiment]

@hamidInventions @jampani_varun @hmrishavbandy @yizhe_song 2 vs 12B params

[Varun Jampani @jampani_varun]

Introducing Stable Diffusion 3.5 Flash ⚡, a state of the art distilled image generation model that is best in class for all compute budgets.

🔗Project page: https://t.co/VQ7lP7vFWA

Authors: @hmrishavbandy, @rahiment, Jim Scott, Reshinth Adithyan, @yizhe_song, @jampani_varun

[Mohammad Mahdi (Medi) Derakhshani @mmderakhshani]

T1/11
Text-to-image AI is amazing, but what if you don't speak English? Most are English-centric, creating barriers for billions.
We introduce NeoBabel, a new open model for visual generation that natively understands 6 languages, breaking down the walls of digital inequity. 🌍��️

[Dorsa Sadigh @DorsaSadigh]

Here is another uncut video of real-time interactions with @GoogleDeepMind 's Gemini Robotics!

[RahimEntezari @rahiment]

CVPR2025:
Are you passionate about Large Vision models? How about efficiency?
- We are looking for reviewers for eLVM workshop
- Also eager to read your submissions!

workshop page: https://t.co/oqPM0g8evn
reviewer enrolment: https://t.co/DnUSWS2NC0
#CVPR2025

[RahimEntezari @rahiment]

@DongWan06935465 Congratulations!

[RELAI @ReliableAI]

Our agents are working 24/7, and more registration codes are rolling out!

Try out our hallucination detection agents for free now!

Request your registration code here: https://t.co/QVVDtpQlFJ

[RELAI @ReliableAI]

Hi AI world ✋ We are committed to make AI reliability accessible and achievable for everyone!

First up: RELAI agents for hallucination detection

Chat with popular LLMs, Verify with RELAI.

Try it for free today: https://t.co/kxZyUYZBpH

#AI #LLM #ReliableAI #Hallucination

[RahimEntezari @rahiment]

Interesting to see RELAI looking into one the most important problems of GenAI: reliability!

[Soheil Feizi @FeiziSoheil]

🚀 Exciting news! We’re launching RELAI with a mission to make AI reliability accessible and achievable for everyone.

Our first release: RELAI agents for real-time hallucination detection in popular LLMs.

👉Try it now for free at: https://t.co/k2GDJBDh3P

[RahimEntezari @rahiment]

SD3.5 medium is out this time! Great to use with consumer hardware for finetuning and a lot of research on diffusion models!

[Stability AI @StabilityAI]

Stable Diffusion 3.5 Medium is here – this open model is free for both commercial and non-commercial use. With 2.5 billion parameters, this model is designed to run “out of the box” on consumer hardware, even on a toaster! (1/3)