고정된 트윗
Ozan Vardar
3.2K posts

Ozan Vardar
@mrozanvardar
👨🎤 Digital Artist | Motion Designer | Músiclover 📻 https://t.co/C3Q09KKp7B | 🎧 https://t.co/GeIkMrmln8
Dublin | Istanbul 가입일 Ekim 2010
309 팔로잉908 팔로워

@freepik Oh, thanks team, but everything worked fine on Freepik side. It’s sth about the Veo model itself, which I double checked from other platforms too. You can make the character say anything, but when you use a certain phrase, it suddenly take it as a cameraman narration 😬 weird bug
English

@mrozanvardar Sorry to hear about your experience 😞
Could you please send us a DM with the email associated with your Freepik account?
We’ll be happy to help.
English

2026da en zekası düşük video modelinin Google VEO 3.1 kalması çok kötü. Kalite olarak en iyilerden ama hala keyfince dış sese geçmesi, saçmalaması. 20bin kredi gitti @freepik te, en az 30 farklı prompt tekniği denedim. Yarısında sebepsiz arkadan bi dallama konuşuyo, delirtti💩🤖

Türkçe

@rovvmut_ @CozyLinaGirl2 Good day everyone. Random passerby here, also waiting for the result 🤠 If that works in chinese, it's golden. ☕️
English

@mrozanvardar @IGN You mean Star Trek lol Star Wars is Disney
English

@nicdunz Better? Y & N. Simple prompts don't work as expected. Was the same in SD2 > SD3 switch. Probably has some good editing power. It's fast, it's a detail completer, but definitely not a beginner model. A bit of a bad news for the 6 word daily artists here, good for workflowers.
English

@freepik Ok it is crazy different. NB2 is waay better in "variety " of realism. Not just the scene, objects, light or texture but the randomness in them. Definitely adds extra details. Sometimes comes out a bit HDR/burnt, but awesome love it!🤘🍌🤖 (closeup NBPro)




English

@hcf_m2h 🤣 It's like going to Mona Lisa saying "Hey babe you look like that woman in the painting" Sadly most models are fed with these low quality vfx scenes.
English

Is it just me or does this look AI generated
Blaze Binges@BlazeBinges
5 years ago today, Superman & Lois premiered on CW.
English

@mrozanvardar @freepik Is the image on the left SD5?
If so looks like a model from 2024.
English

@ahmetkurem_ Dostum 2025'in en kötü haberi oydu ya. Gitmeden Pro üye için app bıraktı yazılımcısı. Ben onu kullanıyorum. Yani işe göre değişir ama kralı Davinci Resolve (free), basiti Red Giant Magic Bullet (ortamlar), yoksa Adobe Lumetri (Ae+Pr) falan da, cacık yok ayran verelim gibi olur o.
Türkçe

@mrozanvardar @freepik @Kling_ai Hocam color.io kapanmış. Şuanda renklendirme için hangi programı kullanıyorsunuz. Keşke color.io ' ya erişmenin bir yolu olsaydı.
Türkçe

Spotify says its best developers haven’t written a line of code since December, thanks to AI techcrunch.com/2026/02/12/spo…
English

@DevrimVardar @trblnfxn Daha bizden bu AI işte, promptu buram buram anadolu ve kısa samsun kokuyo ashdska fırtınada bile düşmez o sigara
Türkçe

@mrozanvardar @trblnfxn yerelleştirmenin tillahı resmen ağzından da düşürmedi. :))))
Türkçe

@mrozanvardar fyi
Deedy@deedydas
China's Bytedance just dropped the most advanced video generation model in the world. Seedance 2.0 has: — native audio gen (lipsynced speech + music) — drastic step up from Veo 3.1 / Sora 2 in quality — supports multimodal input — 2k resolution Goes beyond cinematic video, and can do product demos as well. And it's really hard to tell it's AI.

@mrozanvardar @freepik And a new node is coming to do reframing even more accurate!
English

@JF3LIP @pratishhhhh @freepik Well I think in this case "Export as group" & "Group All Text Elements" items being dynamically connected (w/ cables?) back to list and/or items individually, so if the list changes, floaters change as well✌️😎 Don't ask us though, we always want more :) Stability is king RN 🙏
GIF
English











