Basic_camera_motion_LoRAs_sd15-ad2-v1

• Basic camera motion LoRAs for Animatediff v2 motion models - version 1
  • Model Description
  • File summary
  • How to use
  • General recommendation
  • Details and examples
    • Zooming in (16 frame)
    • Zooming in (32 frame)
    • Zooming out
    • Lateral (horizontal) left
    • Lateral (horizontal) right
    • Crane (vertical) up
    • Crane (vertical) down

Basic camera motion LoRAs for Animatediff v2 motion models - version 1

Training

This LoRA was trained on RunPod cloud GPUs.

Model Description

This repository contains a collection of basic camera motion LoRAs finetuned on Animatediff v2 models. The training process utilized Kijai's AnimateDiff Motion Director ComfyUI nodes. These LoRAs have been tested exclusively in ComfyUI with Kosinkadink's AnimateDiff-Evolved nodes, however they may be compatible with other AnimateDiff implementations.

File summary

How to use

• copy the motion lora files into your "ComfyUI\models\animatediff_motion_lora" folder
• Use the "Load Animatediff LoRA" node

General recommendation

• These are finetuned on a v2 model. They work also with AnimateLCM but don't work with v3 models

• They work with SD 1.5 checkpoints

• Animatediff v3 adapter LoRA is recommended regardless they are v2 models

• If you want more motion try increasing the scale multival

• I recommend using the above Base AR (Aspect ratio) for inference however they might work with other ARs too

• Try playing with the strength of

  • motion LoRA
  • scale multival
  • v3_adapter lora

  like increasing the scale multival and lowering the lora strength.

• I recommend using IP-Adapter, however it reduces the effect of the mLORAs, so play with the strength. "Ease in out" weight type is a good starting point.

• If you chain multiple motion LoRAs, I recommend lowering their strength, otherwise, the quality of the result will be worse

Details and examples

Zooming in (16 frame)

• recommended strength: 0.7-1.0

<video controls src="https://huggingface.co/Cseti/Basic_camera_motion_LoRAs_sd15-ad2-v1/resolve/main/asset/LoRA-comparison-zoomin16.mp4" title="zoomin 16 frames"></video>

Zooming in (32 frame)

• this is an experimental motion LoRA trained on 32 frames so it can be used with context length 32.
• recommended strength: 0.7-0.85

<video controls src="https://huggingface.co/Cseti/Basic_camera_motion_LoRAs_sd15-ad2-v1/resolve/main/asset/LoRA-comparison-zoomin32.mp4" title="zoom in 32 frames"></video>

Zooming out

• recommended strength: 0.7-1.0

<video controls src="https://huggingface.co/Cseti/Basic_camera_motion_LoRAs_sd15-ad2-v1/resolve/main/asset/LoRA-comparison-zoomout16.mp4" title="zoom out"></video>

Lateral (horizontal) left

• recommended strength: 0.7-1.0

<video controls src="https://huggingface.co/Cseti/Basic_camera_motion_LoRAs_sd15-ad2-v1/resolve/main/asset/LoRA-comparison-lateral_left.mp4" title="right view"></video>

Lateral (horizontal) right

• recommended strength: 0.7-1.0

<video controls src="https://huggingface.co/Cseti/Basic_camera_motion_LoRAs_sd15-ad2-v1/resolve/main/asset/LoRA-comparison-lateral_right.mp4" title="right view"></video>

Crane (vertical) up

• recommended strength: 0.7-1.0

<video controls src="https://huggingface.co/Cseti/Basic_camera_motion_LoRAs_sd15-ad2-v1/resolve/main/asset/LoRA-comparison-crane_up.mp4" title="right view"></video>

Crane (vertical) down

• recommended strength: 0.7-1.0

<video controls src="https://huggingface.co/Cseti/Basic_camera_motion_LoRAs_sd15-ad2-v1/resolve/main/asset/LoRA-comparison-crane_down.mp4" title="right view"></video>

Support

Producing and sharing this kind of open-source work requires renting cloud GPUs, which gets expensive quickly. If you find it useful and would like me to keep contributing, your support is very much appreciated: