OpenAI introduces Sora

bnew

Veteran
Joined
Nov 1, 2015
Messages
63,930
Reputation
9,808
Daps
174,249



Adobe’s Sora-rivaling AI video generator is now available for everyone​


Generate Video is now in public beta, allowing anyone to generate five-second video clips at 1080p.

by Jess Weatherbed

Updated Feb 12, 2025, 9:23 AM EST

5 Comments5 New

Screenshot 2025-02-12 134433


Image: Adobe

Jess Weatherbed is a news writer focused on creative industries, computing, and internet culture. Jess started her career at TechRadar, covering news and hardware reviews.

Adobe’s text- and image-to-video AI generator has been released for anyone to try online. Generate Video is available starting today in public beta following a limited early access testing period last year. The beta tool can be accessed via the re-designed Firefly web app, alongside new image generation and translation capabilities, and AI credit subscription tiers for creators.

Adobe started launching tools powered by its generative AI Firefly Video Model in October, starting with the Generative Extend tool in beta for Premiere Pro that can be used to extend the end or beginning of footage. The Generate Video tool rolling out today — over two months after OpenAI launched its own text-to-video generator, Sora — adds some minor improvements since it was first teased in September.

Generate Video consists of two features: Text-to-Video and Image-to-Video. As those names imply, Text-to-Video allows users to generate footage using text description, while Image-to-Video lets you add a reference image alongside the prompt to provide a starting point for the video. Generate Video includes various options that refine or guide the results, such as simulating styles, camera angles, motion, and shooting distances.



A GIF demonstrating Adobe’s Image-to-Video feature.


The Image-to-Video feature lets you add a starting point for the generated video to reference alongside text prompts. GIF: Adobe

Video is now output in 1080p at 24 frames per second, up from the original 720p quality. Both Text-to-Video and Image-to-Video take 90 seconds or longer to generate clips at a maximum length of five seconds — shorter than the 20-second duration available to Sora users. Adobe says it’s also working on both a faster, lower-resolution “ideation model” and a 4K model, which are “coming soon.”

Adobe has also updated the Firefly web app that hosts many of its generative AI tools. Alongside sporting a new UI, it now integrates with Creative Cloud apps including Photoshop, Premiere Pro, and Express, making it easier to move and edit AI-generated assets. And because Firefly is trained on public domain and licensed content, it’s safe for commercial use. Adobe even describes its Generate Video tool as “production-ready” to entice users who want to use AI-generated videos in films without the risk of violating copyright protections.

Adobe faces growing competition in the AI video market. In addition to Sora, Google is testing the second generation of its Veo AI video model, which looks more impressive than OpenAI’s model judging by early demo examples. ByteDance and Pika Labs have also recently announced new video-focused generative AI tools. Adobe’s main advantage is Firefly’s commercial viability, but it will still need to keep up with the quality and features its competitors are offering.

Two additional tools will also be available in public beta on the Firefly web app starting today — but these aren’t free to use. Scene to Image lets users create their own references for AI-generated images using built-in 3D and sketching features — seemingly built on the “Project Scenic” experiment that Adobe announced in October. The Translate Audio and Video tool is pretty self-explanatory, allowing users to translate and dub audio into over 20 languages while preserving the original speaker’s voice.

Adobe is launching two new Firefly subscription plans which provide credits that can be spent to use Adobe’s Firefly models. Firefly Standard starts at $9.99 per month for 2,000 video/audio credits and provides up to 20 five-second 1080p video generations. The pricier Firefly Pro plan starts at $29.99 for 7,000 credits and up to 70 five-second 1080p video generations. A notable perk is that both plans include unlimited access to Firefly imaging and vector features.
 

bnew

Veteran
Joined
Nov 1, 2015
Messages
63,930
Reputation
9,808
Daps
174,249

1/40
@Google
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.

/search?q=#GoogleIO



https://video.twimg.com/amplify_video/1924893779888115713/vid/avc1/1920x1080/XQKvjW0tqCJQornM.mp4

2/40
@ednewtonrex
What’s the training data?



3/40
@krakenfx
Can't even trust video footage any more 😭



4/40
@karmaycholera
Hollywood is cooked



5/40
@youngScipio
Boomers won’t be able to handle this, Facebook is going to be wild



6/40
@ChaseWillden
I wonder when a full featured AI generated film is going to come out



7/40
@DirtyTesLa
I went to make a video and it said I've made too many requests and can't request again for 24 hours 😭 I didn't make a single one today



8/40
@oltexasboy
very cool



9/40
@NFLComedySkits
No thanks, I prefer real actors



10/40
@justalexoki
holy shyt



11/40
@hckinz
$249.99 per month 🫠



12/40
@theeomega0
What's gonna be the point platform rewarding - content creators?

Like YouTube, if creating content can be this easy



13/40
@Rahll
How many billions of dollars worth of other people's property did you steal to make this happen?



14/40
@sriramHODL
wow



15/40
@Vigilomniscry
Something still seems unnatural about it. I think it still needs tweaking, say 2-3 versions before widespread commercialisation, and is almost indistinguishable from an actual clip. Very interesting times for those that are able to utilize it, begs the question, though, how much content does humanity need or can use?



16/40
@makalin
only in us.. as usual.. ok google



17/40
@TheAI_Frontier
Damn I felt Veo2 was just yesterday.



18/40
@ValarDoh3eris
Insane improvement



19/40
@jiwong_kim
Wow Google Veo 3 is amazing 🤩



20/40
@lordchirag
Veo 2



https://video.twimg.com/amplify_video/1924896937985376256/vid/avc1/1280x720/uoeSRVGH8qG4Hz5j.mp4

21/40
@Lorenzo_Negrete
Still looks and sounds obviously fake.



22/40
@nearcyan
rip



23/40
@mhdfaran
It reminds me of her



GratNdyXcAAuAf6.png


24/40
@Joeingram1
WTF



25/40
@playonshaga
Ai is moving at the speed of light.



26/40
@doganuraldesign
Okay, this is impressive



27/40
@KingBootoshi
LOL GG



28/40
@Mira_Network




29/40
@tallmetommy
Hey @OpenAI when



30/40
@chrisstanchak
We're all cooked



31/40
@amit_ajwani
wow



32/40
@MaverickDarby
Interdasting



33/40
@DANNYonPC
Can you do will smith eating spaghetti?



34/40
@lewisknaggs42
this sucks



35/40
@galaxyai__
dialogue AND background noise?? yeah GOOGLE kinda ate this one



36/40
@RickyRickenback
The sounds all wrong. The single splash. That’s so wrong



37/40
@ropirito
holy shyt



38/40
@0xroyce369
ok this is damn impressive



39/40
@AlbertSimonDev
Amazing!



40/40
@GigaTendies
Not sure if I should laugh or cry




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196







1/30
@GoogleDeepMind
Animate your story in your style with Veo 3. 🖌️

Here are some of our favorite videos. Sound on. 🔈 Veo 🧵



https://video.twimg.com/amplify_video/1924968348154265601/vid/avc1/3840x2160/PLzoHht0ajAQoDow.mp4

2/30
@GoogleDeepMind




https://video.twimg.com/amplify_video/1924968407365255172/vid/avc1/3840x2160/F6RBR6GXp47gP_1N.mp4

3/30
@GoogleDeepMind




https://video.twimg.com/amplify_video/1924969009625350144/vid/avc1/3840x2160/-C9n9jvPkIsyhd8v.mp4

4/30
@GoogleDeepMind




https://video.twimg.com/amplify_video/1924969097747693570/vid/avc1/3840x2160/sJ0Hau0t47pN4tWI.mp4

5/30
@GoogleDeepMind




https://video.twimg.com/amplify_video/1924969205147037696/vid/avc1/3840x2160/uwY2KnH133iKpEwO.mp4

6/30
@CodyThieling
My first Veo 3 / Flow creation



https://video.twimg.com/ext_tw_video/1925016129551945728/pu/vid/avc1/1280x720/tEW4VFX4GVOStI0l.mp4

7/30
@mailspec
💫💫💫



8/30
@IstanaAngin
Not available worldwide 😅



9/30
@GiannisWorld_
Is it available in the gemini app??



10/30
@goodtoknow2010
that is great

i follow back anyone that follows me instantly



11/30
@FortKnoxCrypto
Sick animations! Can't wait to try out Veo 3.



12/30
@m33mw4rr10r
B1Uz83yQC3aphKk8EdZ53VFWkQb9o6DKFWG3xRKopump



13/30
@m520152
when it will be aviable in another countries?



14/30
@lordkahl
$VEO3

B1Uz83yQC3aphKk8EdZ53VFWkQb9o6DKFWG3xRKopump



15/30
@Secretcode54
sweeeeeeeeeeeeeeet but not available in canada yet rip



16/30
@burnt_jester
You make me sad, DeepMind.



GrbhNWibQAAn3Jh.png


17/30
@Amansays60
This is the Nimbus 2000 of editing tools for all editors 🧹



18/30
@0xJussec
This is nice. Merging it with @NotebookLM would be awesome



19/30
@simurg123
Is this
B1Uz83yQC3aphKk8EdZ53VFWkQb9o6DKFWG3xRKopump



20/30
@Zerotrust4m
Didn’t veo 2 just come out?



21/30
@1ngramFun
thx for these tech



22/30
@M_ano_j7
When will it be available in india??



23/30
@arikuschnir


[Quoted tweet]
WE CAN TALK! I spent 2 hours playing with Veo 3 @googledeepmind and it blew my mind now that it can do sound! It can talk, and this is all out of the box...


https://video.twimg.com/amplify_video/1924951732284522496/vid/avc1/2560x1440/GwuwTlxK_8vonbNo.mp4

24/30
@Trakintelai
Veo 3’s style-driven animation brings storytelling to life like never before. AI-powered creativity meets personal touch, unlocking new ways to express and engage audiences effortlessly.



25/30
@LukasBreitwiese
Veo 3 Token!

B1Uz83yQC3aphKk8EdZ53VFWkQb9o6DKFWG3xRKopump



26/30
@Donnie_Tesla
cool app



27/30
@Donnie_Tesla
👀



28/30
@doginalgm
Wow that’s clean



29/30
@themickkelly1
Veo 3 lets your stories breathe and come alive in the most beautiful way. With sound on, every emotion hits deeper—pure magic. 🎨✨



30/30
@themickkelly1
Veo 3 truly brings stories to life, turning imagination into powerful emotions. Watching these videos with sound on feels like feeling the heartbeat of every story. 🎨💫




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196


Veo 3 Standup comedy



Posted on Tue May 20 21:22:35 2025 UTC


DeepMind Veo 3 Sailor generated video



Posted on Tue May 20 19:40:00 2025 UTC


Veo 3 generations are next level.



Posted on Wed May 21 02:57:06 2025 UTC

 

bnew

Veteran
Joined
Nov 1, 2015
Messages
63,930
Reputation
9,808
Daps
174,249
[Other] Wtf, AI videos can have sound now? All from one model?



Posted on Wed May 21 02:17:27 2025 UTC


edit:





1/11
@arikuschnir
WE CAN TALK! I spent 2 hours playing with Veo 3 @googledeepmind and it blew my mind now that it can do sound! It can talk, and this is all out of the box...



https://video.twimg.com/amplify_video/1924951732284522496/vid/avc1/2560x1440/GwuwTlxK_8vonbNo.mp4

2/11
@BuildWithRich
This needs to go viral immediately 👍



3/11
@arikuschnir
It’s going…



4/11
@yowza151
Can you control what is said in the video like with quotes or it just says general around what your prompt



5/11
@arikuschnir
Yes you can tell it what to say!



6/11
@AlvigodOP
Game Changing



7/11
@JeremyNguyenPhD
Can it do an Asian accent?

GPT's advanced voice wouldn't do it. I get why, but I still want to be able to do some realistic accents that sound like people I know.



8/11
@ai_artworkgen
holy moly! this is fantastic!



9/11
@robertcbaek
Wow 🤯 no way !



10/11
@jefftangx
I’m actually scared



11/11
@FinanceLancelot
It's easy to see how employment could hit 20% in 2026.




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196
 
Last edited:

chineebai

Superstar
Joined
May 11, 2012
Messages
11,685
Reputation
1,171
Daps
33,095
Reppin
NULL
Ai is insane. We recreated a superbowl ad at work that took like 3 days, showed the client a side by side of the ai created one versus the real one. Half the people could not pick the real one. The real one cost like $10 million to produce.
 
Top