Flux.1

[KimBioInfoStudio]

What does this PR do?

adaption of diffuser.pipelines.FluxPipeline

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[KimBioInfoStudio]

Run following cmd on a 225H KVM with 1.17.0

python text_to_image_generation.py \                  
    --model_name_or_path black-forest-labs/FLUX.1-schnell \
    --prompts "A cat holding a sign that says hello world" \
    --num_images_per_prompt 1 \
    --batch_size 1 \
    --num_inference_steps 28 \
    --image_save_dir /tmp/flux_1_images \
    --scheduler flow_match_euler_discrete\
    --use_habana \
    --use_hpu_graphs \
    --gaudi_config Habana/stable-diffusion \
    --bf16

got output as following:

------------------------------------------------------------------------------
[INFO|pipeline_flux.py:341] 2024-09-18 08:58:01,797 >> 1 prompt(s) received, 1 generation(s) per prompt, 1 sample(s) per batch, 1 total batch(es).
[WARNING|pipeline_flux.py:346] 2024-09-18 08:58:01,797 >> The first two iterations are slower so it is recommended to feed more batches.
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 28/28 [07:17<00:00, 14.80s/it][INFO|pipeline_flux.py:415] 2024-09-18 09:05:19,217 >> Speed metrics: {'generation_runtime': 437.4197, 'generation_samples_per_second': 0.002, 'generation_steps_per_second': 0.065}
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 28/28 [07:17<00:00, 15.62s/it]
09/18/2024 09:05:32 - INFO - __main__ - Saving images in /tmp/flux_1_images...

output image：