Description
This LoRA is crafted to create realistic facial makeup inspired by the Japanese "Jirai-kei" aesthetic, characterized by pale skin, bold eye makeup, and soft, melancholic tones. It's designed to work seamlessly with Hunyuan Video, allowing for smooth and consistent animations that are perfect for storytelling or video creation.
For even greater flexibility, this LoRA can be combined with other LoRAs. I've invested a lot of time and effort into developing this model, and your support—whether through a like or a tip—would mean a lot. Thank you for your encouragement!
Usage
Trigger Words
v1.0 does not require a specific trigger word. However, including keywords like Japanese or jirai-kei makeup in the prompt will help achieve optimal results.
Recommendation
For optimal results, I highly recommend using the v2v workflow to upscale low-resolution outputs into high-resolution animations. (I am personally using this workflow: v2v Workflow on Civitai). This approach will help enhance the quality and detail of the final result.
Strength Adjustment
While higher LoRA strength settings can emphasize the desired aesthetic effects, they might cause issues with video continuity. For the best balance between appearance and consistency, I recommend adjusting the strength to around 0.6 to 0.7.
Version History
v1.0
Initial release with training focused on achieving the jirai-kei aesthetic.
Designed for facial makeup emphasis with realistic, smooth results.
Limited dataset and no dedicated trigger word.
v1.1
Added additional training images and introduced the trigger word "jiraikei" for easier and more consistent usage.
Slightly improved the model's ability to generate more realistic and detailed visuals.
Note: Using higher strength values may cause a loss of video continuity, resulting in abrupt scene transitions that feel like cut edits. For optimal results, it is recommended to keep the strength settings low (around 0.6 to 0.7), as with v1.0.
Note: There is no significant difference in the output quality between v1.0 and v1.1.
Upcoming Versions (v1.2 or v2.0)
For the next update, I plan to:
Train the model with a different dataset to achieve even better results.
Improve video continuity so that higher strength settings do not easily disrupt the flow of animations.
Description
In version 1.1, I've added a few more training images and introduced the trigger word jiraikei. Other than that, the model was trained with the same settings as version 1.0. Please note that using a high strength value might cause a loss of continuity in the video, leading to sudden scene transitions as if a cut edit was applied. For optimal results, I recommend using a lower strength setting (around 0.6–0.7), similar to version 1.0. Additionally, this version has slightly improved capabilities for generating more realistic depictions.
FAQ
Comments (3)
And appreciate if you can add workflow data on png of girl peeing outside (3rd pic). Apparently other png do have workflow, but this pic do not.
I'm wondering if you can use your dataset to make a lora for general text to image models like SDXL/Pony. I really like the girls generated by this lora, but generating a video takes a lot of time.
Please make lora for other models like WAN or Flux Klein! I love jiraikei! Or can you share the dataset? This is one of the greatest lora I've seen! Please come back!