Copy link to clipboard
Copied
I attempted to generate video from two different photos of a man and his mother and a family walking in the woods. Both were immediately rejected. Then I used Firefly to generate an image of a man holding his daughter and tried to use that, but it was also rejected. I've attached these images here. I can find no reason that the system would reject these on a content-level. So any thoughts you have would be appreciated.
Hello @Trace35191221nizm,
Thank you for your message. I am sorry you are having this problem.
The beta version of image to video will not generate videos from images containing children. That is why it would not generate the videos.
My best,
droopy
Hello @Suchanda ,
At this time, the model will not generate videos based on keyframes that contain children. That is a limitation of the model.
droopy
Hi @Felix3LGato !
Thanks for pointing that out. Firefly currently avoids generating videos from images that include children. This is a careful step to make sure the model handles such content responsibly. We know it can be limiting, but it’s part of ensuring safety as the tool improves.
Thanks
Copy link to clipboard
Copied
Copy link to clipboard
Copied
Hi @CrazyGenre,
Most likely these were blocked because the model thought there were children in the image. The model currently will not generate a video based on a key frame it believes contains children. That is a restriction in the current model.
droopy
Copy link to clipboard
Copied
Im not sure I understand why its not creating video with prompts given or without. It is a picture I tool of my wife and kids the prompts were simple "pan from running waterfall to my wife and kids posing on bridge"
Copy link to clipboard
Copied
Hi @Felix3LGato !
Thanks for pointing that out. Firefly currently avoids generating videos from images that include children. This is a careful step to make sure the model handles such content responsibly. We know it can be limiting, but it’s part of ensuring safety as the tool improves.
Thanks
Copy link to clipboard
Copied
Tentei criar imagens de crianças lavando as mãos ou com xampu na cabeça e o Firefly dá erro.
Gostaria de saber o motivo.
Copy link to clipboard
Copied
Sorry to hear that.
I'm merging your thread here since it’s part of a similar discussion. Please see the correct answer above.
Let us know if this helps.
Thanks
Copy link to clipboard
Copied
Estoy intentando generar un video a partir de 2 imagenes de referencia para crear una transición. Justo como lo vi en este tutorial https://www.youtube.com/shorts/lBcC5yzdl1I
Sin embargo, Firefly se reusa a procesar. Dice que la imagen de referencia no cumple con las directrices para usuarios.
Ya revisé las directrices para usuarios y no estoy infringiendo ninguna.
Cual es el problema?
Adjunto captura de pantalla y las 2 imagenes de referencia que estoy usando.
Copy link to clipboard
Copied
Hello @Juan378375549ucq,
The problem is that the model believes your first keyframe contains a child. The model currently will not generate videos from keyframes it believes contain children. That is a current limitation of the model.
droopy
Copy link to clipboard
Copied
Copy link to clipboard
Copied
Hello @Randall_Leddy3528,
Thank you for your message.
The Firefly video model has a restriction that it will not generate videos with key frames that contain children. That is a restriction in the model currently.
droopy
Copy link to clipboard
Copied
Why I am getting 'We can't process this prompt because the reference image
Copy link to clipboard
Copied
Hello @defaultpjgdx14bzul3,
I have merged your message into this thread which addresses the issue you raise.
Please see my "correct answer" message above which explains this.
Please let us know if you have further questions.
My best,
droopy
Find more inspiration, events, and resources on the new Adobe Community
Explore Now