Inference

For inference I used ComfyUI.

The strength of the LoRA can differ from prompt to prompt. Usually 0.9 works but in some cases it can be too strong (lower it to 0.8-0.85) or too weak (increase it to 1.0).

• Trigger words: Nfj1nx, blue hair

• Strength: 0.8-0.9

You can find example prompts in the video examples!

Trainig details

• dataset size: 127 x 960x544 (with various frame lenghts)

• steps: 29000

• optimizer_type: adamw

• scheduler_type: linear

• learning_rate: 0.0001

• first_frame_conditioning_p: 0.5

• alpha: 32

• dropout: 0.0

• rank: 32

• target_modules:

  • to_k

  • to_q

  • to_v

  • to_out.0

Important Notes: This LoRA is created as part of a fan project for research purposes only and is not intended for commercial use. It is based on the movies, which are protected by copyright. Users utilize the model at their own risk. Users are obligated to comply with copyright laws and applicable regulations. The model has been developed for non-commercial purposes, and it is not my intention to infringe on any copyright. I assume no responsibility for any damages or legal consequences arising from the use of the model.