Building Grok @xai, CS PhD @JohnsHopkins; Previous @GoogleAI
Joined October 2018
- Tweets 132
- Following 563
- Followers 742
- Likes 440
37 Photos and videos
Pinned Tweet
Jan 29
So proud of the team. LFG!!!
Jan 29
Well I know I should comment on Elo here, but I just want to say we have the best team building the future together!!!!
@imhaotian @zeliu_ @jefffhj @du_peichao75719 @jathushan @ZhibeiM @never1andd keyang_xu @Randxie29 shubham_goel @hangg70 @Guodzh
2
17
4,251
Junfei Xiao retweeted
Jun 8
Grok Imagine Video 1.5 Preview by @xAI reclaims 1st in Image to Video with an Elo of 1357 on Design Arena.
With this model, @xAI establishes new Pareto frontiers in both Speed and Price, with an average generation time of 41.2 seconds and $0.01/img and $0.08/sec for the 480p quality.
Grok Imagine Video 1.5 Preview now leads Image to Video with a 49 point Elo gap, ahead of Seedance 2.0 and Seedance 2.0 Fast by @BytePlusGlobal.
Congratulations to the @xAI team on this release!
20
24
129
1,374,413
Grok Imagine on Vercel
Jun 4
Grok Imagine Video 1.5 on AI Gateway.
Image-to-video generation with synced audio in one pass.
ππ πππ πππππππππ
ππππ({
πππππ: 'π‘ππ/ππππ-πππππππ-πππππ-π·.π»-πππππππ ',
ππππππ: 'π ππππππ πππππππππ πππππππ ππ’π'
});
2,359
3,867
24,322
5,377,619
Junfei Xiao retweeted
May 31
Weβre back to No. 1 on the leaderboard! π After months of hard work, what a journey! Itβs also the best option for fast and low-cost generation.
Meanwhile, weβre cranking day and night on v2 to make it even stronger. Try it and let us know what we can improve β your feedback is invaluable.
β docs.x.ai/developers/models/β¦
Grok-Imagine-Video-1.5-Preview (720p) has landed #1 in the Image-to-Video Arena!
This is a massive 52 pt improvement over Grok-Imagine-Video (720p), surpassing the best video models Seedance-2.0 and HappyHorse.
Congrats to @xAI and @elonmusk on this big achievement!
67
28
451
46,934
A lot of improvements have been made. Itβs worth a try.
Grok-Imagine-Video-1.5-Preview (720p) has landed #1 in the Image-to-Video Arena!
This is a massive 52 pt improvement over Grok-Imagine-Video (720p), surpassing the best video models Seedance-2.0 and HappyHorse.
Congrats to @xAI and @elonmusk on this big achievement!
21
2
74
8,400
Junfei Xiao retweeted
May 31
My first video using the new Grok Imagine 1.5 preview using the API! Okay, I think it is safe to say @xai has cooked with @grok!
May 31
Updated video model! Today on Arena and xAI API! @grok Imagine edges out Seedance 2.0 in blind tests. Now, if Imagine can address rate limits and moderation, that would be great.
44
21
304
63,886
May 31
Race never stops.
Appetizer first.
We are working hard.
Grok-Imagine-Video-1.5-Preview (720p) has landed #1 in the Image-to-Video Arena!
This is a massive 52 pt improvement over Grok-Imagine-Video (720p), surpassing the best video models Seedance-2.0 and HappyHorse.
Congrats to @xAI and @elonmusk on this big achievement!
25
9
234
14,194
Apr 25
Finally ship this new model with many improvements! Please try itπ
Apr 25
Grok Imagine now has dramatically improved lip sync and sharper audio quality on all image-to-video generations.
Dialogue tracks the mouth. Sound matches the scene. Your videos look and sound the way you imagined them.
9
86
3,582
Junfei Xiao retweeted
Apr 25
Grok Imagine now has dramatically improved lip sync and sharper audio quality on all image-to-video generations.
Dialogue tracks the mouth. Sound matches the scene. Your videos look and sound the way you imagined them.
1,841
2,985
30,015
213,786,530
Junfei Xiao retweeted
Mar 24
BREAKING: Grok Imagine by @xai takes 1st overall on Multi Image to Video Arena, with an overall Elo of 1342.
The team's debut reference image to video model establishes a new Pareto frontier for Preference vs. Speed with an average generation time of 58.9 seconds.
Huge congrats to the @xai team for this achievement!
48
67
501
1,029,105
Mar 24
Try our Reference-to-Video model! Grok it!π
4
2
57
3,659
Mar 18
We always target to best models.
Grok Imagine tops LMArena video editing benchmark! Try it through API here: x.ai/api/imagine
Big shoutout to @xAI Imagine team! #GrokImagine Keep cooking! π
10
510
Junfei Xiao retweeted
Mar 12
We are supporting Reference to Video in Grok Imagine now!
You can create videos with up to 7 ingredients, try it!
14
13
135
25,005
Junfei Xiao retweeted
Mar 12
Grok Imagine just got a major update from @xai!
You can now specify up to 7 reference images for generating a video. The images can reference people, objects, or even keyframes. It's really very flexible!
@Grok will then combine the references with your prompt into a video. πΉ
145
104
1,013
12,124,337
Feb 8
π
Feb 7
Imagine-Image is at the Pareto front:
Better, Faster & Cost efficientπ
And we will be even better in weeksπ«‘π«‘
(Kudos to the amazing xAI team and all my lordsπ€£)
7
1,373
Great work by the @Grok Imagine team!
The new @xAI Grok-Imagine-Image model is a Pareto-optimal model in Image Arena:
The Pareto frontier tells us which model has the highest Arena score at each price point. @xAiβs latest models have improved the frontier, giving optimal performance in the mid-price tier. For a wide range of prices between 2c and 8c per image, @elonmuskβs @xAI has the leading model, delivering the maximum performance.
Top models on the Pareto frontier for Image Arena (Single Image Edit):
- @OpenAI: GPT-Image-1.5-high-fidelity
- @xAI: Grok Imagine Image Pro
- @xAI: Grok Imagine Image
- @bfl_ml: Flux 2 Klein 9B
- @bfl_ml: Flux-2-Dev
- @reve : V1.1 Fast
See thread for how the frontier changes for Text-to-Image π§΅
2,293
3,017
22,709
8,718,926
Junfei Xiao retweeted
Feb 7
Grok Imagine image-gen and image-edit is faster and better than Nano Banana!
The new @xAI Grok-Imagine-Image model is a Pareto-optimal model in Image Arena:
The Pareto frontier tells us which model has the highest Arena score at each price point. @xAiβs latest models have improved the frontier, giving optimal performance in the mid-price tier. For a wide range of prices between 2c and 8c per image, @elonmuskβs @xAI has the leading model, delivering the maximum performance.
Top models on the Pareto frontier for Image Arena (Single Image Edit):
- @OpenAI: GPT-Image-1.5-high-fidelity
- @xAI: Grok Imagine Image Pro
- @xAI: Grok Imagine Image
- @bfl_ml: Flux 2 Klein 9B
- @bfl_ml: Flux-2-Dev
- @reve : V1.1 Fast
See thread for how the frontier changes for Text-to-Image π§΅
18
14
148
22,064