You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Video Extend idea: asign different LORAs to each <extend> section
#1478
When using the Video Extend feature, there is no way to asign different LORAs to each <extend> section (or I haven't found a way to do it). In other words, when using i2v LORAs, they will apply to all <extend> sections. It would be great if we could choose which LORAs are asigned to each <extend> section. Also note that WAN 2.2 uses a dual model, so the syntax could be something like this:
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
When using the Video Extend feature, there is no way to asign different LORAs to each
<extend>section (or I haven't found a way to do it). In other words, when using i2v LORAs, they will apply to all<extend>sections. It would be great if we could choose which LORAs are asigned to each<extend>section. Also note that WAN 2.2 uses a dual model, so the syntax could be something like this:Basic prompt
<extend:81>Extended prompt <extend_video> <lora_x_high> <extend_videoswap> <lora_x_low><extend:81>Extended prompt <extend_video> <lora_y_high> <extend_videoswap> <lora_y_low><extend:81>Extended prompt <extend_video> <lora_z_high> <extend_videoswap> <lora_z_low>All reactions