---
tags:
- stable diffusion
- animatediff
- motion lora
language:
- en
---

- [Animatediff V2 motion LORAs](#animatediff-v2-motion-loras)
  - [File summary](#file-summary)
  - [General recommendation](#general-recommendation)
  - [Examples](#examples)
    - [v2 Drone orbit right](#v2-drone-orbit-right)
    - [v2 Drone orbit left](#v2-drone-orbit-left)
    - [v2 Drone backing](#v2-drone-backing)
    - [v2 Flying backwards](#v2-flying-backwards)
    - [v2 Drone forward](#v2-drone-forward)
    - [v2 Drone walking back-view](#v2-drone-walking-back-view)
    - [v2 walking front-view](#v2-walking-front-view)
    - [v2 casual walking front-view](#v2-casual-walking-front-view)
    - [v2 running front-view](#v2-running-front-view)
- [Animatediff V3 motion LORAs](#animatediff-v3-motion-loras)
  - [File summary](#file-summary-1)
  - [General recommendations](#general-recommendations)
  - [Drone LORAs](#drone-loras)
  - [Ballerina spin LORAs](#ballerina-spin-loras)
  - [Walking back-view LORAs](#walking-back-view-loras)

# Animatediff V2 motion LORAs

## File summary

| Name                                                                              | Compatible Motion Model | Resolution (w/h) | Frames | input videos |
| --------------------------------------------------------------------------------- | ----------------------- | ---------------- | ------ | ------------ |
| 280_cseti_2906282_drone-orbitright-mv2_r64_w576_h384_fr16.safetensors             | v2, animateLCM          | 576x384 (3:2)    | 16     | 1            |
| 280_cseti_6933991_drone-orbitleft-mv2_r64_w576_h384_fr16.safetensors              | v2, animateLCM          | 576x384 (3:2)    | 16     | 1            |
| 280_cseti_6160305_drone-backing-mv2_r64_w576_h384_fr16.safetensors                | v2, animateLCM          | 576x384 (3:2)    | 16     | 1            |
| 800_cseti_3730960_flying_backwards-3vid_mv2_0.00031_56_w768_h512_fr16.safetensors | v2, animateLCM          | 576x384 (3:2)    | 16     | 3            |
| 260_cseti_8890531_drone-forward-mv2_r64_w576_h384_fr16.safetensors                | v2, animateLCM          | 576x384 (3:2)    | 16     | 1            |
| 200_cseti_3413444_drone-walking-mv2_r64_w576_h384_fr16.safetensors                | v2, animateLCM          | 576x384 (3:2)    | 16     | 1            |
| 500_cseti_8315653_drone-orbitright-3vid_mv2_r64_w576_h384_fr16.safetensors        | v2, animateLCM          | 576x384 (3:2)    | 16     | 3            |
| 600_cseti_4941259_walking-frontview-6vid_mv2_r64_w576_h384_fr16.safetensors       | v2, animateLCM          | 576x384 (3:2)    | 16     | 6            |
| 500_cseti_3734954_casualmove-frontview-3vid_mv2_r64_w576_h384_fr16.safetensors    | v2, animateLCM          | 576x384 (3:2)    | 16     | 3            |
| 1800_cseti_1118902_running-frontview-8vid_mv2_r64_w768_h512_fr16.safetensors      | v2, animateLCM          | 576x384 (3:2)    | 16     | 8            |


## General recommendation

- These are finetuned on a v2 model. They work also with AnimateLCM but don't work with v3 models
- For the drone LORAs, keyword "drone" or "drone shot" might help with the motion
- Animatediff v3 adapter lora is recommended regardless they are v2 models
- If you want more motion try incrasing the scale multival (e.g. to 1.2-1.5)
- I recommend using the above resolutions and upscale the animation or keep at least the aspect ratios
- The drone LORAs are trained on landscape footage so might don't work very well on portraits however can give you interesting results

## Examples

### v2 Drone orbit right

<video controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/nolora-candidate_00001.mp4" title="Orbit right"></video>

### v2 Drone orbit left

<video controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/orbitleft-candidate_00004.mp4" title="Orbit left"></video>

### v2 Drone backing

<video controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/dronebacking-candidate_00019.mp4" title="Drone backing"></video>

### v2 Flying backwards

- The difference compared to the Drone LoRA is that this LoRA was trained on a dataset containing also flying footage.

<video controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/800_cseti_3730960_flying_backwards-3vid_mv2_0.00031_56_w768_h512_fr16.mp4" title="Drone backing"></video>


### v2 Drone forward

<video controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/droneforward-comparison_00002.mp4" title="Drone backing"></video>

### v2 Drone walking back-view

- recommended to use words like "back-view", "from behind" in your prompts

<video controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/candidate-comparison_00003.mp4" title="Drone walking back-view"></video>

### v2 walking front-view

- recommended to use words like "front-view"

<video width="576" height="384" controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/walking-frontview-candidate.mp4" title="walking front-view"></video>

### v2 casual walking front-view

- recommended to use words like "front-view"
- play with the strength: 0.6-0.8 can already give good results

<video width="576" height="384" controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/AD-IPA-testing-upscale_00002.mp4" title="casual walking front-view"></video>

### v2 running front-view

- recommended to use words like "front-view" and "running"

<video width="576" height="384" controls src="https://huggingface.co/Cseti/AD_Motion_LORAs/resolve/main/running-8vid-frontview-candidate.mp4" title="running front view"></video>

# Animatediff V3 motion LORAs

## File summary


| Name                                                 | Compatible Motion Model | Resolution (w/h) | Frames | Comments          |
| ---------------------------------------------------- | ----------------------- | ---------------- | ------ | ----------------- |
| 250_cseti_Drone-Rotating_3D_footage_fr16             | v3                      | 384x384 (1:1)    | 16     | Drone 3d rotation |
| 400_cseti_9222750_drone-rot_w576_h384_fr32_r64       | v3                      | 576x384 (3:2)    | 32     | Drone 3d rotation |
| 200_3723723_cseti_ballerina-spin_w512_h768_r64       | v3                      | 512x768 (2:3)    | 16     | Ballerina spin    |
| 250_3723723_cseti_ballerina-spin_w512_h768_r64       | v3                      | 512x768 (2:3)    | 16     | Ballerina spin    |
| 400_cseti_5294370_walk_backview-1_w576_h384_fr32_r56 | v3                      | 576x384 (3:2)    | 32     | Walking back view |
| 450_cseti_5294370_walk_backview-1_w576_h384_fr32_r56 | v3                      | 576x384 (3:2)    | 32     | Walking back view |


## <b>General recommendations</b>
- These are finetuned on v3 model. Does not work with v2 or animateLCM motion models
- Animatediff v3 adapter lora is recommended
- If you want more motion try incrasing the scale multival (e.g. to 1.2)
- I recommend using the above resolutions and upscale the animation or keep at least the aspect ratios

## <b>Drone LORAs</b>

- For more motion, try incrasing the LORA strength or try adding the below trigger words to your prompt
- Try trigger words: dronearound, flying around

## <b>Ballerina spin LORAs</b>

- 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

## <b>Walking back-view LORAs</b>
- I recommend using LORA strength of 0.8-0.9
- Recommended prompts:
  - "back view"
  - "drone shot" - for an upper view