Stable Diffusion 1.4

[bgoelTT]

This PR adds a flask server implementation of stable diffusion 1.4 and dockerizes it

It creates a new flask server that:

• implements a warmup process whose completion gates the activation of the main inference and healthcheck endpoints
• implements the main inference endpoint to submit prompts to be generated to the main backend thread
• implements a healthcheck endpoint that will only return a 200 code once the server is warmed up and ready to generate images

[tstescoTT]

I'm going to ask you to rebase this to dev and PR to dev pending acceptance of new git flow proposed :)

[milank94]

Is there a reference to this commit in tt-metal anywhere? Curious how you selected this one.

[bgoelTT]

I copy+pasted this from the YOLOv4 server because that required a specific commit as the metal YOLOv4 improvements got reverted as couldn't pass CI.

Should I just use the latest release? That would be release v0.55.0?

[bgoelTT]

Updated to use release v0.55.0 in 4582863

[milank94]

I think this should be get_sample_prompt?

[bgoelTT]

Removed locust tests in 016af35

[milank94]

Is a locustfile needed for this demo?

[bgoelTT]

No this isn't needed. The locust test here won't really measure performance, I want it to enqueue 5 prompts into the input queue and process them. I will add this to test_inference_api.py

[bgoelTT]

Removed locust tests in 016af35

[milank94]

Global variable ready : this flag is accessed and modified by multiple threads (warmup and request handlers). This may lead to race conditions. Consider using thread-safe mechanisms like threading.Lock or Event to manage state changes.

[bgoelTT]

Enforced mutual exclusion of ready flag in 835fc91 then fixed a bug in that implementeation in 63d973c

[milank94]

Repeated code blocks : the code repeatedly reads and writes json_file_path. This can be refactored into utility functions for cleaner logic:

def read_json_file(file_path):
    if not os.path.isfile(file_path):
        return {"prompts": []}
    with open(file_path, "r") as f:
        return json.load(f)

def write_json_file(file_path, data):
    with open(file_path, "w") as f:
        json.dump(data, f, indent=4)

[bgoelTT]

Refactored in a75d0e6

[milank94]

Use logging instead of print statements for better production diagnostics.

[bgoelTT]

Used logging instead of print in f5650c5

[milank94]

Some feedback added.

For the license headers, the year should be set to 2025.