Stable diffusion thread

doogyhatts

Arch-Supremacy Member
Joined
Feb 13, 2018
Messages
13,747
Reaction score
3,949
Using prompts to edit a base image is now much easier, thanks to the nano-banana model from Google.
 

doogyhatts

Arch-Supremacy Member
Joined
Feb 13, 2018
Messages
13,747
Reaction score
3,949
Hailuo is focusing on video quality. Look like kling is still sleeping
Kling have some morphing problems with their 2.1 pro model.
I couldn't get the start-end frames to work well for fast moving objects.
In the end, I had to use Wan 2.2 to get it done.

But there are ways the start-end frames from Kling can do really well.
Such as camera fly-throughs over very long distances.
 

doogyhatts

Arch-Supremacy Member
Joined
Feb 13, 2018
Messages
13,747
Reaction score
3,949
Should be from Midjourney.
Gy7Ct59XMAAqNyq
 

doogyhatts

Arch-Supremacy Member
Joined
Feb 13, 2018
Messages
13,747
Reaction score
3,949
Alibaba is releasing an audio-driven subject-to-video model.
This would be competitive to Veo3.
 
Important Forum Advisory Note
This forum is moderated by volunteer moderators who will react only to members' feedback on posts. Moderators are not employees or representatives of HWZ Forums. Forum members and moderators are responsible for their own posts. Please refer to our Community Guidelines and Standards and Terms and Conditions for more information.
Top