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
My GPU has 24 gigabytes of video memory, but I ran out of video memory when running configs/controlnet_animation/anythingv3_config.py.
Then I adjusted it
editor.infer(video=video, prompt=prompt, negative_prompt=negative_prompt, save_path=save_path) has an input size of 256x256, and can then run. But the effect is very poor, mainly have the following questions:
The default 512x512 running model requires at least a large GPU.
Is it normal to imagine that the effect is poor after modifying the video input parameters to 256x256?
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
-
My GPU has 24 gigabytes of video memory, but I ran out of video memory when running configs/controlnet_animation/anythingv3_config.py.
Then I adjusted it
editor.infer(video=video, prompt=prompt, negative_prompt=negative_prompt, save_path=save_path) has an input size of 256x256, and can then run. But the effect is very poor, mainly have the following questions:
The default 512x512 running model requires at least a large GPU.
Is it normal to imagine that the effect is poor after modifying the video input parameters to 256x256?
Beta Was this translation helpful? Give feedback.
All reactions