Diffusers
Safetensors
rangm commited on
Commit
b80681a
Β·
verified Β·
1 Parent(s): 12055cb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -13
README.md CHANGED
@@ -87,23 +87,18 @@ pip install -r requirements.txt
87
 
88
  | Models | Download Link | Notes |
89
  | --------------|-------------------------------------------------------------------------------|-------------------------------|
90
- | Wan2.1-FUN-1.3B | πŸ€— [Huggingface](TBD) | Base model
91
- | wav2vec2-base | πŸ€— [Huggingface](TBD) | Audio encoder
92
- | EchoMimicV3 | πŸ€— [Huggingface](TBD) | Our weights
93
 
94
- <!-- The **pretrained_weights** is organized as follows.
95
 
96
  ```
97
  ./models/
98
- β”œβ”€β”€ denoising_unet.pth
99
- β”œβ”€β”€ reference_unet.pth
100
- β”œβ”€β”€ motion_module.pth
101
- β”œβ”€β”€ pose_encoder.pth
102
- β”œβ”€β”€ sd-vae-ft-mse
103
- β”‚ └── ...
104
- └── audio_processor
105
- └── tiny.pt
106
- ``` -->
107
  ### πŸ”‘ Quick Inference
108
  ```
109
  python infer.py
 
87
 
88
  | Models | Download Link | Notes |
89
  | --------------|-------------------------------------------------------------------------------|-------------------------------|
90
+ | Wan2.1-Fun-1.3B-InP | πŸ€— [Huggingface](https://huggingface.co/spaces/alibaba-pai/Wan2.1-Fun-1.3B-InP) | Base model
91
+ | wav2vec2-base | πŸ€— [Huggingface](https://huggingface.co/facebook/wav2vec2-base-960h) | Audio encoder
92
+ | EchoMimicV3 | πŸ€— [Huggingface](https://huggingface.co/BadToBest/EchoMimicV3) | Our weights
93
 
94
+ -- The **weights** is organized as follows.
95
 
96
  ```
97
  ./models/
98
+ β”œβ”€β”€ Wan2.1-Fun-1.3B-InP
99
+ β”œβ”€β”€ wav2vec2-base-960h
100
+ └── transformer
101
+ └── diffusion_pytorch_model.safetensors
 
 
 
 
 
102
  ### πŸ”‘ Quick Inference
103
  ```
104
  python infer.py