metadata
tags:
- stable diffusion
- animatediff
- motion lora
language:
- en
General recommendations:
- These are finetuned on v3 model. Does not work with v2 or animateLCM motion models propely
- Animatediff v3 adapter lora is recommended
- If you want more motion try incrasing the scale multival (e.g. to 1.2)
Drone LORA:
- This LORA is trained on 384x384 so use these resolutions for generating the animation then upscale
- For more motion, try incrasing the LORA strength or try adding the below trigger words to your prompt
- Try trigger words: dronearound, flying around
Ballerina spin LORA:
- These LORAs were trained on 512x768 (w x h) so use these resolutions for generating the animation then upscale
- Sometimes a white veil / skirt appears during rotation. Unfortunately, this is from the original video. In such cases, try a new generation or reduce the LORA strength.
- I recommend using LORA strength of 0.8-0.9