I will be joining @GoogleDeepMind to work on video generation and world simulators! Can't wait to collaborate with such a talented team.
I had an amazing two years at OpenAI making Sora. Thank you to all the passionate and kind people I worked with. Excited for the next chapter!
183
161
3,994
774,957
"fly through tour of a museum with many paintings and sculptures and beautiful works of art in all styles"
Video generated by #Sora
287
540
2,792
2,377,477
DeepMind has ambitious plans to make massive generative models that simulate the world. I'm hiring for a new team with this mission. Come build with us!
boards.greenhouse.io/deepmin… boards.greenhouse.io/deepmin…
89
209
2,299
354,850
"realistic video of people relaxing at beach, then a shark jumps out of the water halfway through and surprises everyone"
Video generated by Sora
270
209
2,109
867,209
"a walking figure made out of water tours an art gallery with many beautiful works of art in different styles"
Video generated by Sora
Sora has object permanence - the paintings stay consistent before and after the water man walks in front
88
162
1,394
682,697
Sora is our first video generation model - it can create HD videos up to 1 min long. AGI will be able to simulate the physical world, and Sora is a key step in that direction. thrilled to have worked on this with @billpeeb at @openai for the past year openai.com/sora
146
146
1,312
537,389
someone plz adopt this cat 😭
"a white and orange tabby alley cat is seen darting across a back street alley in a heavy rain, looking for shelter..." (prompt by Chad Nelson)
Video generated by Sora
77
123
1,025
400,250
"Cinematic trailer for a group of adventurous puppies exploring ruins in the sky"
Video generated by #Sora
78
146
877
333,213
"a photorealistic video of a butterfly that can swim navigating underwater through a beautiful coral reef"
Video generated by Sora
39
106
838
516,564
"a man BASE jumping over tropical hawaii waters. His pet macaw flies alongside him"
Video generated by #Sora
46
101
773
285,181
"an extreme close up shot of a woman's eye, with her iris appearing as earth"
Video generated by #Sora
40
94
746
433,874
"minecraft with the most gorgeous high res 8k texture pack ever"
Video generated by Sora
46
63
690
284,494
"a green blob and an orange blob are in love and dancing together"
Video generated by Sora
the video you generate for your partner when you dont make it home from office on valentines day #Sora
35
44
560
403,069
really excited by Sora's ability to blend two videos. here's a blend of that minecraft video with motorcycling. so much creative potential for this feature
25
64
553
222,739
check out more info on the research behind Sora and more of Sora's abilities here:
openai.com/research/video-ge…
43
97
560
124,509
best friends 😊
"a red panda and a toucan are best friends taking a stroll through santorini during the blue hour"
Video generated by #Sora
44
47
468
222,073
we can also use Sora to edit a video from a text instruction using SDEdit. "rewrite the video in a pixel art style."
41
77
494
84,809
Great example of accurate physics in Veo 2!
"A pair of hands skillfully slicing a ripe tomato on a wooden cutting board"
#veo
12
14
489
50,750
Gemini 2.0 Flash has native image outputs! Congrats to the awesome team that built it.
I find the example at 1:15 super cool: to change the car's color and add beach gear, the model generates two images step-by-step using visual chain of thought.
piped.video/watch?v=7RqFLp0T…
24
81
423
157,932
"a dark neon rainforest aglow with fantastical fauna and animals"
Video generated by #Sora
21
38
326
190,218
in addition to generating videos from text, Sora can morph between two videos. here's one example I love where it starts as a drone and turns into a butterfly
15
46
327
45,358
🚀Genie 3 is a world model that can simulate minutes of realtime interactive video!!
It's a big step forward and the efforts of many amazing folks at DeepMind. Simulating the world is critical to intelligence, and this is just the beginning of what's in store 🌎🎉
What if you could not only watch a generated video, but explore it too? 🌐
Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt.
From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵
14
16
307
23,130
Sora is a generalist model of all different durations, resolutions and aspect ratios. here are three generations from the same text prompt at different aspect ratios
8
46
293
83,304
Amazing work on interactive world models at @GoogleDeepMind!! Congrats to the Genie team!
Introducing 🧞Genie 2 🧞 - our most capable large-scale foundation world model, which can generate a diverse array of consistent worlds, playable for up to a minute. We believe Genie 2 could unlock the next wave of capabilities for embodied agents 🧠.
3
14
269
20,720
🔥🔥🔥 Veo 2 is DeepMind's newest state-of-the-art video gen model. Congrats to the Veo team on all the hard work that went into making it!!
I'm especially impressed by the improved motion and physical accuracy. Learn more at deepmind.google/technologies…
piped.video/watch?v=G9RDHs9n…
5
13
218
35,250
there are lots of creative ways to use Sora. here's one that's really cool: we can extend the same video backward in time multiple different ways, resulting in videos that start different but all have the same ending
(also, crashing into the San Francisco sign at the end was entirely Sora's idea 😂)
10
27
175
30,928
Sora is also capable of generating images at up to 2048x2048 resolution. here is an image with crazy photorealism generated by Sora
14
20
172
18,579
Connor is amazing to work with. please reach out if you want to push new boundaries in ML systems for Sora!
If this Sora sample reminds you of a reduce-scatter and all-gather, we are hiring! We are looking for people who are passionate about systems efficiency, believe in scaling, and have expertise tackling these problems. If this sounds like a fit, please reach out!
12
7
147
49,923
Check out Veo 3 🔥🔥🔥 sound on 🔊
Say goodbye to the silent era of video generation: Introducing Veo 3 — with native audio generation. 🗣️
Quality is up from Veo 2, and now you can add dialogue between characters, sound effects and background noise.
Veo 3 is available now in the @GeminiApp for Google AI Ultra subscribers in the U.S.
#GoogleIO
6
6
154
9,182
Native image generation with Gemini is live 🚀🔥
You can generate interleaved text and images and edit uploaded images all in a unified model. Big congrats to @robertriachi @19kaushiks @mentzer_f and many more amazing folks who built this!
Try it out and tell us what you think: aistudio.google.com/prompts/…
6
11
128
14,145
Try out Veo 2 in YouTube! Congrats Veo team 🎉
🎥 Our state-of-the-art video generation model Veo 2 is now available in @YouTube Shorts.
With the Dream Screen feature, creators can:
✨ Produce new clips that fit seamlessly into their storytelling with a quick text prompt
✨ Use it to make backgrounds for their videos.
Here’s how → goo.gle/3X1ikfv
6
5
106
10,860
more #Sora videos on our tiktok!
"leaning tower of pizza"
tiktok.com/@openai/video/733…
13
9
61
39,284
you can now try Veo 3 with Gemini Pro subscription!
Veo 3 dropped about 100 hours ago, and it's been on 🔥🔥🔥 ever since
Now, we’re excited to announce:
+ 71 new countries have access
+ Pro subscribers get a trial pack of Veo 3 on the web (mobile soon)
+ Ultra subscribers get the highest # of Veo 3 gens w/ refreshes
How to try it…
➡️ Gemini (gemini.google):
* Great for everyone - click the Video chip in the prompt bar, and just describe your video
* Pro subscribers now get a 10-pack so you can try it
* Ultra: MAX limits, daily refresh!
➡️ Flow (flow.google):
* Great for AI filmmakers
* Pro: 10 gens/month
* Ultra: Now 125 gens/month (up from 83)!
3
2
53
9,484
Check out Gemini's new native image editing and generation!! It has great consistency and adherence to instructions, and is a lot of fun to play with 😁
Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯
From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning, control and creativity.
A quick dive into Gemini 2.5 Flash’s capabilities 🧵
4
3
54
7,415
Amazing work from @ir413 bringing AI to the real world
we cast real-world humanoid control as next token prediction; our approach enables joint training with youtube videos and walks in sf
1
8
40
18,534
Huge congrats to the amazing Veo team for all the hard work bringing this to life! 🎉 Try it out today in the new Flow app: labs.google/flow
1
28
2,204
David and the entire team are the most amazing people to work with. if you have experience with large scale video infrastructure, please reach out and come build Sora with us
We're hiring folks that have experience with large scale video infrastructure – serving, processing, ingest, etc. If you think you'd be a good match please reach out!
2
2
26
14,095
amazing generalization to real world @ir413
we have trained a humanoid transformer with large-scale reinforcement learning in simulation and deployed it to the real world zero-shot
1
2
15
11,464
Congrats! Excited to see what you build!
Excited to announce the creation of WaveForms AI (waveforms.ai) – an Audio LLM company aiming to solve the Speech Turing Test and bring Emotional Intelligence to AI @WaveFormsAI
1
1
15
4,735
Looks awesome!! Congrats @tetexiao_ai and team!
12
5,074
🎉🎉🎉
Our new text-to-image model, DALL·E 3, can translate nuanced requests into extremely detailed and accurate images.
Coming soon to ChatGPT Plus & Enterprise, which can help you craft amazing prompts to bring your ideas to life:
openai.com/dall-e-3
ALT "An illustration of an avocado sitting in a therapist's chair, saying 'I just feel so empty inside' with a pit-sized hole in its center. The therapist, a spoon, scribbles notes."
4
3,425
