|
|
--- |
|
|
tags: |
|
|
- text-to-image |
|
|
- lora |
|
|
- diffusers |
|
|
- template:diffusion-lora |
|
|
widget: |
|
|
- output: |
|
|
url: images/WanMoveLoraTesting_00003_.webp |
|
|
text: '-' |
|
|
base_model: 'bytedance-research/HuMo' |
|
|
instance_prompt: null |
|
|
license: apache-2.0 |
|
|
--- |
|
|
# HuMoveLora |
|
|
|
|
|
<Gallery /> |
|
|
|
|
|
## Model description |
|
|
<video controls width="640" src="https://huggingface.co/drozbay/HuMoveLora/resolve/main/images/WanMoveLoraTesting_00036-audio.mp4"></video> |
|
|
A LoRA that tries to combine track controlled motion of [Wan-Move](https://github.com/ali-vilab/Wan-Move) with the human motion and speech sync features of [HuMo](https://huggingface.co/bytedance-research/HuMo). |
|
|
|
|
|
## Usage |
|
|
|
|
|
- **Base model:** Wan HuMo-17B Model |
|
|
- **In ComfyUI:** Likely needs [WanExperiments](https://github.com/drozbay/WanExperiments) to allow for I2V capabilities. Chain the HuMo node with the WanMove node. **Recommended track strength: 1.5.** |
|
|
- It is *not recommended* to use HuMo reference or start image along with the WanMove start image. |
|
|
- [**Example ComfyUI WF**](./images/your_workflow_name.json) |
|
|
|
|
|
## Version History |
|
|
|
|
|
| Version | Notes | |
|
|
|---------|-------| |
|
|
| v0.1 | Proof of concept release. Further tuning should improve simultaneous speech and motion control capabilities. | |
|
|
|
|
|
|
|
|
## Download model |
|
|
|
|
|
|
|
|
[Download](/drozbay/HuMoveLora/tree/main) them in the Files & versions tab. |
|
|
|
