This Motion-Lora was trained under SD_1.5 base model and animatediff_V3 model.
The purpose of the training was to produce short videos of buildings from orbit during flights.
Recommended usage:
Frames: 16-32
Resolution: 512x512, 512x768 , 768x512
Models: Realistic models
Sampler: DPM++ 2M Karras
Keep prompt simple
Need to be tested on humans and objects.
Be sure to tag me in IG if you use it! @pixelpoetryx
Description
FAQ
Comments (7)
I'm sorry, I'm new to this. What will I need to use this? Can I do this in auto1111?
I´m using ComfyUI with animatediff but I just found a tutorial that shows how to use Motion Loras, here it is! https://www.youtube.com/watch?v=KWnJBgkm7Gc&ab_channel=NextDiffusion
Can you provide a comfyui workflow example? Try as I might, I cannot get this motion lora to have the desired effect.
Sure! There is a .zip file with a very simple comfy workflow. Please , check it out.
@PixelPoetryX Thank you!
Do I put this in ComfyUI -> models -> Animatediff_motion_lora ? PS i just tested out your base workflow and this is interestingl! i dont remember the limitations of SD 1.5 (i.e. Dimensions and number of frames)
Hey! yea, that´s it.