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.
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:
