Train AnimateDiff (24+ frames by multiplying existing module by scale factor and finetune)
# Multiply pe weights by multiplier for training more than 24 frames
if motion_module_pe_multiplier > 1:
for key in motion_module_state_dict:
if 'pe' in key:
t = motion_module_state_dict[key]
t = repeat(t, "b f d -> b (f m) d", m=motion_module_pe_multiplier)
motion_module_state_dict[key] = t
I trained till 264 frames on A100
Train AnimateDiff + LoRA
Infinite infer (credits to dajes) (temporal_context and video_length params).
ControlNet (works with Infinite infer). VRAM consumming. Can only infer 120 frames on single controlnet module on A100
Prompt Walking. Start from Egg and finish with Duck
Train AnimateDiff (24+ frames by multiplying existing module by scale factor and finetune)
I trained till 264 frames on A100
Train AnimateDiff + LoRA
Infinite infer (credits to dajes) (temporal_context and video_length params).
ControlNet (works with Infinite infer). VRAM consumming. Can only infer 120 frames on single controlnet module on A100
Prompt Walking. Start from Egg and finish with Duck
Updated to last diffusers version