Update README.md

README.md

@@ -40,10 +40,10 @@ Recent studies have demonstrated the effectiveness of directly aligning diffusio
 
 ## Quick Started
 ### Checkpoints
-The `diffusion_pytorch_model.safetensors` is online version of SRPO based on [FLUX.1 Dev](https://huggingface.co/black-forest-labs/FLUX.1-dev), trained on HPD dataset with [HPSv2](https://github.com/tgxs002/HPSv2)
+The `diffusion_pytorch_model_onlinehps.safetensors` is online version of SRPO based on [FLUX.1 Dev](https://huggingface.co/black-forest-labs/FLUX.1-dev), trained on HPD dataset with [HPSv2](https://github.com/tgxs002/HPSv2)
 
 #### Inference
-Replace the `diffusion_pytorch_model.safetensors` of FLUX
+Replace the `ddiffusion_pytorch_model_onlinehps.safetensors` of FLUX
 ```python
   pipe = FluxPipeline.from_pretrained('your dir',
           torch_dtype=torch.bfloat16,