This was a fun one, img-to-video with seedance pro pic.twitter.com/ptRvYiSUWe
— fofr (@fofrAI) 26 juin 2025
This was a fun one, img-to-video with seedance pro

By
–
This was a fun one, img-to-video with seedance pro pic.twitter.com/ptRvYiSUWe
— fofr (@fofrAI) 26 juin 2025
This was a fun one, img-to-video with seedance pro

By
–
> an executive office toy goes back and forth https://t.co/WQk3OiS2Sb pic.twitter.com/ZnoKWlXImr
— fofr (@fofrAI) 26 juin 2025
> an executive office toy goes back and forth

By
–
Veo 3:
— fofr (@fofrAI) 26 juin 2025
> a countdown
(8 second video, starts the countdown from 8, this seemed to be the most common from a few runs) pic.twitter.com/2iOgzJyos3
Veo 3: > a countdown (8 second video, starts the countdown from 8, this seemed to be the most common from a few runs)

By
–
I like the way seedream does pencil sketches
By
–
> a photo of messy handwriting in blue ink saying "this is what handwriting looks like in seedream", on lined paper, the words are small, there are doodles and sketches of people in blue ink

By
–
Seedream 3.0 at 2048×512 (4:1), prompt: "A panoramic view"

By
–
I put a couple of extra little things into the API for this one. Given the model can go up to 2048x and down to 512x, there is a size option: – big = longest side will be 2048
– regular (default) = 1 megapixel (like 1024×1024)
– small = shortest side will be 512 These are

By
–
It's wild how we haven't prioritised state of the art voice assistants for doing all of the things in cars.

By
–
As the models get better, the prompts will get wilder. https://t.co/kSxBPnXSop pic.twitter.com/XswCtODDP1
— fofr (@fofrAI) 24 juin 2025
As the models get better, the prompts will get wilder.

By
–
Time to test the physics of seedance-1-pro I guess.
— fofr (@fofrAI) 24 juin 2025
It can also do 9:16 natively. https://t.co/btkk388qEu pic.twitter.com/46z7SH5mb0
Time to test the physics of seedance-1-pro I guess.
It can also do 9:16 natively.