[lavender-flow] use flow match euler scheduler

[yiyixuxu]

part of #8796

you can use this to test once this PR is fixed#8798

fromdiffusersimportLavenderFlowPipeline, LavenderFlowTransformer2DModelimporttorchrepo="AuraDiffusion/auradiffusion-v0.1a0"dtype=torch.float16transformer=LavenderFlowTransformer2DModel.from_pretrained(
repo,
revision="refs/pr/1",
torch_dtype=dtype,
subfolder="transformer"
) pipeline=LavenderFlowPipeline.from_pretrained(
"AuraDiffusion/auradiffusion-v0.1a0", revision="refs/pr/1",
transformer=transformer,
torch_dtype=torch.float16
).to("cuda")
images=pipeline(
prompt="a cute cat with tiger like looks",
height=512,
width=512,
num_inference_steps=50, generator=torch.Generator().manual_seed(666),
guidance_scale=3.5,
).images[0]
images.save("yiyi_test_4_out.png")

[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]

I added this just to get 1:1 with the original implementation, I don't think it's needed here, the difference should be very small, but I didn't test for smaller number of steps
cc @cloneofsimo

without this line

with this line

[sayakpaul]

Thanks. Just a single comment.

[sayakpaul]

We could unpack this code a bit and perhaps add a comment on why we're dividing by 1000. This is mainly because we're moving away from our normal pipeline implementations a bit which our users are used to reading and referring to.

[yiyixuxu]

done! feel free to merge into your PR now

[sayakpaul]

Thanks a lot for your help, Yiyi!