Yoshiaki Kawajiri was a producer, director and character designer for Madhouse Studio's. Back in the 80's and 90's. He is best known for being a director of Wicked City, Ninja Scroll, and Vampire Hunter D: Bloodlust. This style was based around his early works.
The videos here are made with both high and low noise with wan2.2. I also used lightx2v wan2.1 t2v lora to generate the samples for v2 and v1. v3 is using only the base model (I still recommend using the distill lora's for speed up) You should be able to set the low and high loras to strength 1 but can be increased.
Samples generated with
sampler: lcm
scheduler: beta
additional lora: wan2.1 t2v lightx2v
4 steps of high noise
4 steps of low noise
Low noise lora took about 36 hrs of training on a 6000 pro blackwell with lr 3e-5
High noise lora too about 8 hrs with lr 4e-5. I technically trained high noise up to epoch 32 but it was clearly overcooked and found epoch 16 to be the best results.
Version 3 updates: Trained for 32 more epochs and adjusted the dataset to include more short clips. I am rendering most of these examples without Lightning/FusionX/Lightx2v to show the base model capabilities. If you are unsure, I am putting the number of steps as 20 for the raw model rendering.
Description
Increased dataset size to 333 images and 201 clips.
FAQ
Comments (3)
Great lora! Are you to able to get the full style without the use of lightx2v or lightening lora? Would you be ok to share an example workflow? :)
Thanks for your question. I have made it to work without the lightx2v, but it seems very seed sensitive. I uploaded the woman drinking coffee with a beanie vid that I generated without lightx2v. You have to play around with the cfg and lora strengths more than with lightx2v.
tarnished3029 Thanks for providing an example! I am struggling a bit with anime style training with 2.2 on the low, and just wanted to see if others can do it without those loras, so thats great to see <3