enable specifying schedulers for text-to-image and image-to-image

[ad-astra-video]

This PR adds ability to set schedulers using a json string in the request for t2i and i2i pipeline. name of the scheduler can be a preset or a class name for the scheduler from diffusers.

There are presets to make setting the main schedulers easier from https://huggingface.co/docs/diffusers/en/api/schedulers/overview.

Scheduler is created by mapping the preset name to the diffusers scheduler class using importlib so the schedulers are not imported until needed.
If a scheduler fails to be added the pipeline raises an error. If no scheduler is specified the default scheduler is applied.

performance testing
loading no scheduler (reassigns default scheduler)
2024-07-28 01:12:00,677 - app.pipelines.text_to_image - INFO - setting pipeline scheduler to:
2024-07-28 01:12:00,677 - app.pipelines.text_to_image - INFO - loading scheduler took 0.0002524852752685547s

loading DPM++ 2M scheduler from preset on RealVisXL_V4.0 model
2024-07-28 01:13:44,851 - app.pipelines.text_to_image - INFO - setting pipeline scheduler to: {"name":"DPM++ 2M","args":{}}
2024-07-28 01:13:44,858 - app.pipelines.text_to_image - INFO - loading scheduler took 0.00660252571105957s

loading DPM2 scheduler from preset on RealVisXL_V4.0 model
2024-07-28 01:10:39,576 - app.pipelines.text_to_image - INFO - setting pipeline scheduler to: {"name":"DPM2","args":{}}
2024-07-28 01:10:39,817 - app.pipelines.text_to_image - INFO - loading scheduler took 0.24109697341918945s

loading Euler flow match for SD3, setting shift arg.
2024-07-28 01:42:36,853 - app.pipelines.text_to_image - INFO - setting pipeline scheduler to: {"name":"Euler flow match","args":{"shift":"3"}}
2024-07-28 01:42:36,856 - app.pipelines.text_to_image - INFO - loading scheduler took 0.002814054489135742s

format of json string in http request:
{ "name": "Euler", "args": {} }

[ad-astra-video]

Updated this to 0.2.0 release

[ad-astra-video]

@rickstaa I rebased this and tested. I used RealVisXL_4.0 to test setting scheduler and observed small changes in image holding the seed constant

Example requests using /docs endpoint:

#see attached example output
{
  "model_id": "",
  "loras": "",
  "prompt": "A pair of clear hands looking through a transparent glass Christmas ball , hyper-realistic, minimalist, futuristic background with cute Christmas decorations like Santa Claus, a snowman, and snowflakes, 8k",
  "height": 1024,
  "width": 1024,
  "guidance_scale": 7.5,
  "negative_prompt": "face asymmetry, eyes asymmetry, deformed eyes, open mouth",
  "safety_check": true,
  "seed": 0,
  "num_inference_steps": 28,
  "num_images_per_prompt": 1,
  "scheduler": ""
}

#see attached example output
{
  "model_id": "",
  "loras": "",
  "prompt": "A pair of clear hands looking through a transparent glass Christmas ball , hyper-realistic, minimalist, futuristic background with cute Christmas decorations like Santa Claus, a snowman, and snowflakes, 8k",
  "height": 1024,
  "width": 1024,
  "guidance_scale": 7.5,
  "negative_prompt": "face asymmetry, eyes asymmetry, deformed eyes, open mouth",
  "safety_check": true,
  "seed": 0,
  "num_inference_steps": 28,
  "num_images_per_prompt": 1,
  "scheduler": "{\"name\":\"DPM++ 2M SDE Karras\", \"args\":{}}"
}

DEFAULT

DPM++ SDE KARRAS