Add support to pass image embeddings to the WAN I2V pipeline.

[goiri]

What does this PR do?

Allows computing the image embeddings externally and use them.
It also fixes the function documentation.

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?

Pipeline changes: @yiyixuxu and @asomoza

[hlky]

@bot /style

[github-actions]

Style fixes have been applied. View the workflow run here.

[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]

ohh test failures aer relevant, can we look into them?

[goiri]

ohh test failures aer relevant, can we look into them?

Fixing the following errors:

FAILED tests/pipelines/wan/test_wan_image_to_video.py::WanImageToVideoPipelineFastTests::test_callback_cfg - ValueError: Cannot forward both `image`: <PIL.Image.Image image mode=RGB size=16x16 at 0x7FB4AA18F9A0> and `image_embeds`: ['latents', 'prompt_embeds', 'negative_prompt_embeds']. Please make sure to only forward one of the two.
FAILED tests/pipelines/wan/test_wan_image_to_video.py::WanImageToVideoPipelineFastTests::test_callback_inputs - ValueError: Cannot forward both `image`: <PIL.Image.Image image mode=RGB size=16x16 at 0x7FB4DA2F4BE0> and `image_embeds`: ['latents']. Please make sure to only forward one of the two.
FAILED tests/pipelines/wan/test_wan_image_to_video.py::WanImageToVideoPipelineFastTests::test_cfg - ValueError: Cannot forward both `image`: <PIL.Image.Image image mode=RGB size=16x16 at 0x7FB4AAC4A3E0> and `image_embeds`: ['latents']. Please make sure to only forward one of the two.
FAILED tests/pipelines/wan/test_wan_image_to_video.py::WanImageToVideoPipelineFastTests::test_dict_tuple_outputs_equivalent - ValueError: Cannot forward both `image`: <PIL.Image.Image image mode=RGB size=16x16 at 0x7FB4AA17DC00> and `image_embeds`: ['latents']. Please make sure to only forward one of the two.
FAILED tests/pipelines/wan/test_wan_image_to_video.py::WanImageToVideoPipelineFastTests::test_encode_prompt_works_in_isolation - ValueError: Cannot forward both `image`: <PIL.Image.Image image mode=RGB size=16x16 at 0x7FB4AA0D5330> and `image_embeds`: ['latents']. Please make sure to only forward one of the two.
FAILED tests/pipelines/wan/test_wan_image_to_video.py::WanImageToVideoPipelineFastTests::test_inference - ValueError: Cannot forward both `image`: <PIL.Image.Image image mode=RGB size=16x16 at 0x7FB4AA7A2D40> and `image_embeds`: ['latents']. Please make sure to only forward one of the two.
FAILED tests/pipelines/wan/test_wan_image_to_video.py::WanImageToVideoPipelineFastTests::test_inference_batch_consistent - ValueError: Cannot forward both `image`: <PIL.Image.Image image mode=RGB size=16x16 at 0x7FB490136CE0> and `image_embeds`: ['latents']. Please make sure to only forward one of the two.
FAILED tests/pipelines/wan/test_wan_image_to_video.py::WanImageToVideoPipelineFastTests::test_save_load_local - ValueError: Cannot forward both `image`: <PIL.Image.Image image mode=RGB size=16x16 at 0x7FB4DA2F5150> and `image_embeds`: ['latents']. Please make sure to only forward one of the two.
FAILED tests/pipelines/wan/test_wan_image_to_video.py::WanImageToVideoPipelineFastTests::test_save_load_optional_components - ValueError: Cannot forward both `image`: <PIL.Image.Image image mode=RGB size=16x16 at 0x7FB4AAA19150> and `image_embeds`: ['latents']. Please make sure to only forward one of the two.

[yiyixuxu]

merged, thanks for the PR!

[goiri]

Thank you very much for the reviews!