|
--- |
|
base_model: |
|
- tencent/HunyuanVideo |
|
tags: |
|
- LoRA |
|
- hunyuan |
|
--- |
|
|
|
# Arcane Jinx HunyuanVideo LoRA v1 |
|
|
|
<div style="display: flex; gap: 16px;"> |
|
<video width="33%" height="auto" controls> |
|
<source src="https://huggingface.co/Cseti/HunyuanVideo-LoRA-Arcane_Jinx-v1/resolve/main/tests_00382.mp4" type="video/mp4"> |
|
</video> |
|
<video width="33%" height="auto" controls> |
|
<source src="https://huggingface.co/Cseti/HunyuanVideo-LoRA-Arcane_Jinx-v1/resolve/main/tests_00388.mp4" type="video/mp4"> |
|
</video> |
|
<video width="33%" height="auto" controls> |
|
<source src="https://huggingface.co/Cseti/HunyuanVideo-LoRA-Arcane_Jinx-v1/resolve/main/tests_00437.mp4" type="video/mp4"> |
|
</video> |
|
</div> |
|
<b>Prompt:</b> "CSETIARCANE. A upper body shot of nfjinx, wearing an intricately detailed plate armor. The steel breastplate features ornate engravings, while articulated pauldrons protect her shoulders, their polished surface reflecting ambient light. Her blue hair stands out dramatically against the metallic armor. The armor's joints show fine craftsmanship with detailed rivets and carefully fitted plates. Small scratches and battle marks on the metal suggest authenticity and use. Her intense expression remains visible. Chainmail is visible at the gaps between plates, adding texture to the otherwise smooth metal surface." |
|
|
|
<b>Prompt:</b> "CSETIARCANE. A full-body side view, nfjinx walking through a vast, ornate hall, her stride purposeful and measured. Her blue hair flows behind her with each step, framing her face in profile. Massive chamber around her, towering walls covered in elaborate golden patterns and archways. Thick smoke drifts lazily through the air. Wisps of the pale smoke curl around her advancing form, Her hands swing confidently at her sides" |
|
|
|
<b>Prompt:</b> "CSETIARCANE. Nfjinx with her blue hair strides through a rain-soaked cobblestone street. Her black miniskirt and white top peek out beneath a worn leather jacket, all dampened by the rain. The camera moves backward, focusing on her intense gaze. Her visible tattoos glisten with water droplets while her combat boots confidently strike the wet pavement. Behind her, neon signs in pink and blue illuminate the misty air, their glow reflecting off the wet stones and casting colorful shadows across her determined features" |
|
|
|
|
|
|
|
## Important Notes: |
|
|
|
This LoRA is created as part of a <b>fan project</b> for <b>research purposes</b> only and is <b>not</b> intended for commercial use. It is based on the TV series called Arcane 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. |
|
|
|
## Compatibility: |
|
- HunyuanVideo |
|
|
|
## ID Token / Trigger word(s): |
|
|
|
Use these in your prompt helps providing the character. See example prompt above. |
|
- csetiarcane, nfjinx, blue hair, black top |
|
|
|
**Please consider the following:** |
|
|
|
- If it doesn't produce the character, try increasing the lora strength to 1.2 |
|
- With some seeds it doesn't work well, it simply doesn't produce either the style or the character |
|
- I definitely recommend using at least the following trigger words in your prompt: **'csetiarcane, nfjinx, blue hair'** .This is probably due to how the dataset was assembled, I'd like to fix this in later versions" |
|
|
|
## Acknowledgment: |
|
|
|
- Thanks to the [Tencent team](https://github.com/Tencent/HunyuanVideo) for making this great model available |
|
- Thanks to [tdrussel](https://github.com/tdrussell) for the [diffusion-pipe](https://github.com/tdrussell/diffusion-pipe) that helps us making these LoRAs. |
|
- Thanks to [Kijai](https://github.com/kijai) for his great [ComfyUI integration](https://github.com/kijai/ComfyUI-HunyuanVideoWrapper) |
|
- Thanks to [POM](https://huggingface.co/peteromallet) for providing the computing resources. Without this, these LoRAs could not have been created. |
|
|
|
## Trainig details: |
|
- LR: 2e-5 |
|
- Optimizer: adamw |
|
- steps: 6000 |
|
- dataset: 40 (33x704x352) videos |
|
- rank: 32 |
|
- batch size: 1 |
|
- gradient accumulation steps: 4 |
|
|
|
## Citation |
|
``` |
|
@misc{kong2024hunyuanvideo, |
|
title={HunyuanVideo: A Systematic Framework For Large Video Generative Models}, |
|
author={Weijie Kong, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai, Jin Zhou, Jiangfeng Xiong, Xin Li, Bo Wu, Jianwei Zhang, Kathrina Wu, Qin Lin, Aladdin Wang, Andong Wang, Changlin Li, Duojun Huang, Fang Yang, Hao Tan, Hongmei Wang, Jacob Song, Jiawang Bai, Jianbing Wu, Jinbao Xue, Joey Wang, Junkun Yuan, Kai Wang, Mengyang Liu, Pengyu Li, Shuai Li, Weiyan Wang, Wenqing Yu, Xinchi Deng, Yang Li, Yanxin Long, Yi Chen, Yutao Cui, Yuanbo Peng, Zhentao Yu, Zhiyu He, Zhiyong Xu, Zixiang Zhou, Zunnan Xu, Yangyu Tao, Qinglin Lu, Songtao Liu, Daquan Zhou, Hongfa Wang, Yong Yang, Di Wang, Yuhong Liu, and Jie Jiang, along with Caesar Zhong}, |
|
year={2024}, |
|
archivePrefix={arXiv preprint arXiv:2412.03603}, |
|
primaryClass={cs.CV}, |
|
url={https://arxiv.org/abs/2412.03603}, |
|
} |
|
``` |