|
|
--- |
|
|
license: cc-by-nc-4.0 |
|
|
base_model: |
|
|
- Wan-AI/Wan2.2-I2V-A14B |
|
|
- Wan-AI/Wan2.2-TI2V-5B |
|
|
- black-forest-labs/FLUX.1-dev |
|
|
--- |
|
|
|
|
|
Models for [this repo](https://github.com/zengxianyu/ppd-examples) and [this paper](https://arxiv.org/abs/2512.05106) arxiv.org/abs/2512.05106 |
|
|
|
|
|
The 4-step lora checkpoints for Wan2.2-14b are converted from [Wan2.2-Lightning](https://huggingface.co/lightx2v/) |
|
|
|
|
|
[Lora for FLUX.1-dev: flux1-dev_phipd_lora_302000.safetensors](https://huggingface.co/zengxianyu/ppd/blob/main/flux1-dev_phipd_lora_302000.safetensors) |
|
|
|
|
|
[Lora for Wan2.2-14b High noise: wan2.2-14b-high-step-12400.safetensors](https://huggingface.co/zengxianyu/ppd/blob/main/wan2.2-14b-high-step-12400.safetensors) |
|
|
|
|
|
[Low noise wan2.2-14b-low-step-12400.safetensors](https://huggingface.co/zengxianyu/ppd/blob/main/wan2.2-14b-low-step-12400.safetensors) |
|
|
|
|
|
[SD1.5 sd1.5-epoch=10-step=720000.ckpt](https://huggingface.co/zengxianyu/ppd/blob/main/sd1.5-epoch=10-step=720000.ckpt) |
|
|
|
