Sign In

wan2.2 14B Kinestasis concept lora

32

222

0

12

Updated: Sep 4, 2025

conceptwankinestasis

Verified:

SafeTensor

Type

LoRA

Stats

222

0

Reviews

Published

Sep 4, 2025

Base Model

Wan Video 2.2 T2V-A14B

Training

Steps: 15,147
Epochs: 459

Trigger Words

banostasis concept

Hash

AutoV2
3B260C6732
default creator card background decoration
Cseti's Avatar

Cseti

Inference

NOTE: Use it only on your high noise sampler

IMPORTANT: This LoRA is very sensitive to the prompt structure. There are certain phrases that I strongly recommend including in your prompt. Like:

  • "Sequence of quick scene transitions of"

  • "The sequence of changes includes the transitions"

You can find prompt examples in the attached videos.

For inference I used ComfyUI.

Trigger words: Banostasis concept, (and the phrases above)

Strength: 0.8-1.0

Trainig details

Trained only on videos.

HIGH noise LoRA

  • dataset: 33 videos 480x270 25,33,65,81 frame videos

  • steps: 15147

  • LR: 5e-5

  • optimizer: AdamW Optimi

  • rank: 32

  • batch size: 1

  • gradient accumulation steps: 1

  • min_t = 0.875

  • max_t = 1

For training I used the diffusion-pipe repo.