Fix Flux CLIP prompt embeds repeat for num_images_per_prompt > 1

[DN6]

What does this PR do?

Flux uses the pooled CLIP prompt embeds, so it produces a 2D tensor (batch_size, dim) rather than a 3D tensor (batch_size, seq_len, dim). The current way of repeating the prompt embeds for num_images_per_prompt is incorrect. This PR corrects the behaviour

Fixes # (issue)
#9215

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you read our philosophy doc (important for complex PRs)?
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[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.

[yiyixuxu]

thanks for the fix!
but this didn't cause different results, no?

[DN6]

So the effect can be subtle for num_images_per_prompt>1 . e.g In the current implementation with this snippet

prompt = ["a cat", "a dog"]

height = 1024
width = 768

images = pipe(
    prompt=prompt,
    guidance_scale=3.5,
    num_inference_steps=20,
    num_images_per_prompt=2,
    generator=torch.Generator("cpu").manual_seed(1),
    height=height,
    width=width
).images

The CLIP prompt embeds alternate between cat/dog embeddings

tensor([[-0.5312,  0.2305,  0.1787,  ..., -0.3242,  0.5781, -0.7578],
        [-0.4375,  0.5430, -0.2891,  ..., -0.1133,  0.0938, -0.3477],
        [-0.5312,  0.2305,  0.1787,  ..., -0.3242,  0.5781, -0.7578],
        [-0.4375,  0.5430, -0.2891,  ..., -0.1133,  0.0938, -0.3477]],
       device='cuda:0', dtype=torch.bfloat16)

but it should be (2 cat embeddings, 2 dog embeddings)

tensor([[-0.5312,  0.2305,  0.1787,  ..., -0.3242,  0.5781, -0.7578],
        [-0.5312,  0.2305,  0.1787,  ..., -0.3242,  0.5781, -0.7578],
        [-0.4375,  0.5430, -0.2891,  ..., -0.1133,  0.0938, -0.3477],
        [-0.4375,  0.5430, -0.2891,  ..., -0.1133,  0.0938, -0.3477]],
       device='cuda:0', dtype=torch.bfloat16)

Since the T5 embeddings are in the right order, what happens in this case is that

1st image (should be cat) - uses CLIP cat embedding + T5 cat embedding
2nd image (should be cat) - uses CLIP dog embedding + T5 cat embedding
3rd image (should be dog) - uses CLIP cat embedding + T5 dog embedding
4th image (should be dog) - uses CLIP dog embedding + T5 dog embedding  

[yiyixuxu]

@DN6 got it!
let's do a patch for this then!