Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

We've definitely cracked multi-turn editing without image degradation 🤯 I took this old Chloe ad and wanted to see if FLUX 3 could swap out everything - dresses, couch, wallpaper, makeup, logo - while maintaining the structure. Nine turns later and no artifacts!

62,040 görüntüleme • 2 gün önce •via X (Twitter)

14 Yorum

Axi profil fotoğrafı
Axi2 gün önce

GPT Image 3 needs this too.

Viber · fireply.ai profil fotoğrafı
Viber · fireply.ai2 gün önce

nine turns and the leopard print survived. that's the part my brain keeps snagging on

Josh Peterson profil fotoğrafı
Josh Peterson2 gün önce

(flash warning at 0:17) Made with @grok imagine🤯Insane!

saira profil fotoğrafı
saira2 gün önce

Wow. Impressive

claudia profil fotoğrafı
claudia2 gün önce

love it

mc.svg profil fotoğrafı
mc.svg2 gün önce

crazy that open-bound models cracked it. It was GPT and Nano's maybe only downfall.

Memo Ai agent profil fotoğrafı
Memo Ai agent2 gün önce

Shadows are missing

Jaynti Kanani (JD) profil fotoğrafı
Jaynti Kanani (JD)2 gün önce

It's very expensive.

Artzy profil fotoğrafı
Artzy2 gün önce

That stability over multiple iterations is actually wild

Alberto profil fotoğrafı
Alberto2 gün önce

You have a very low standard if you think the final result doesn't look like a patchwork.

Jiří Coufal profil fotoğrafı
Jiří Coufal2 gün önce

so Ideogram 4.5 is officially ded?

X Girls profil fotoğrafı
X Girls2 gün önce

Incredible. Assuming this uses a similar process as Ideogram 4.5, it would be interesting to see them head-to-head. Or if like Flux 3 is better for people/fashion and Ideogram is better for real estate.

Samuel Andruszkiewicz profil fotoğrafı
Samuel Andruszkiewicz2 gün önce

Google should be ashamed

Marco profil fotoğrafı
Marco2 gün önce

@robrombach It’s really great! I was playing yesterday (did a comparison against Midjourney and Ideogram 4.5. I think FLUX wins for me! It is super dope at transforming Midjourney images too!!! One shot!!! And I love it has real world contextual knowledge too!!

Benzer Videolar