jiabaoSU

Hello, I trained with the original parameters and found that the loss would not decrease if it was reduced to 4. The test effect was very poor, I tried to...

Please help to see why there is such an error in my data set. What causes it?

1

tensorflow.python.framework.errors_impl.InvalidArgumentError: [_Derived_]buffer_size must be greater than zero. [[{{node OptimizeDataset/ShuffleDataset}}]] [[OneShotIterator]]

 Why I generated the effect is very poor, I did not change the parameters, I modified the data set path and base model, and the generated graph in the...

RuntimeError: The size of tensor a (56) must match the size of tensor b (17) at non-singleton dimension 1 I did not find the 221x512x512 model, so I changed 65x512x512...

I have set up a technical discussion group where everyone can come and exchange questions related to Lightx2v.

1


wan2.2_i2v_A14b_low_noise_lightx2v_4step.safetensors wan2.2_i2v_A14b_high_noise_lightx2v_4step_1030.safetensorsUnable to perform multiple parallel operations

12

Has anyone been able to successfully achieve multi-GPU parallelism using the wan2.2 4-step distillation model? I've tested it and the results were very poor. I'm not sure if it's a...

wan2.2-FP8-step4 Distillation Model 4-GPU Parallel Inference Result is Incorrect

2

https://github.com/user-attachments/assets/72576806-3e60-463b-b65e-6f8815a518b8 The result looks very poor. Here is my code. Does anyone else have this problem? ` """ Wan2.2 distilled model image-to-video generation example. This example demonstrates how to use...