Dreambooth lora flux bug 3dtensor to 2dtensor

[0x-avi]

What does this PR do?

fixes #9350
currently doing

text_ids = torch.zeros(batch_size, prompt_embeds.shape[1], 3).to(device=device, dtype=dtype)

results in warning:

09/03/2024 10:45:35 - INFO - __main__ - ***** Running training *****
09/03/2024 10:45:35 - INFO - __main__ -   Num examples = 26
09/03/2024 10:45:35 - INFO - __main__ -   Num batches each epoch = 26
09/03/2024 10:45:35 - INFO - __main__ -   Num Epochs = 154
09/03/2024 10:45:35 - INFO - __main__ -   Instantaneous batch size per device = 1
09/03/2024 10:45:35 - INFO - __main__ -   Total train batch size (w. parallel, distributed & accumulation) = 2
09/03/2024 10:45:35 - INFO - __main__ -   Gradient Accumulation steps = 2
09/03/2024 10:45:35 - INFO - __main__ -   Total optimization steps = 2000
Steps:   0%|                                                                                                                                                                            | 0/2000 [00:00<?, ?it/s]
Passing `txt_ids` 3d torch.Tensor is deprecated.Please remove the batch dimension and pass it as a 2d torch Tensor
Steps:   0%|                                                                                                                                                       | 0/2000 [00:01<?, ?it/s, loss=0.522, lr=5e-5]
Passing `txt_ids` 3d torch.Tensor is deprecated.Please remove the batch dimension and pass it as a 2d torch Tensor

removed batch_size and the next line that reassigns txt_ids from :

diffusers/examples/dreambooth/train_dreambooth_lora_flux.py

Line 994 in 8ecf499

text_ids = torch.zeros(batch_size, prompt_embeds.shape[1], 3).to(device=device, dtype=dtype)

to

text_ids = torch.zeros(prompt_embeds.shape[1], 3).to(device=device, dtype=dtype) 

[a-r-r-o-w]

thanks!

[0x-avi]

@yiyixuxu i think you missed this PR

[yiyixuxu]

@0x-74 i did! thank you!

[yiyixuxu]

@0x-74 can you run make style?

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.