#!/usr/bin/env python3
"""FLUX.2 [klein] 4B Base – Steps-Vergleich (Qualität vs. Latenz).

1024x1024, fester Seed, cpu_offload. Vergleicht 20/30/40/50 Steps.
"""

import os
import subprocess
import time

os.environ["HF_HUB_DISABLE_PROGRESS_BARS"] = "1"
os.environ["TRANSFORMERS_VERBOSITY"] = "error"
os.environ["TOKENIZERS_PARALLELISM"] = "false"

MODEL = "/opt/mike-ai/models/FLUX.2-klein-base-4B"
PROMPT = ("A detailed photograph of a red cube on a white marble table, "
          "soft studio lighting, shallow depth of field")
SEED = 0
WIDTH = HEIGHT = 1024
STEPS_LIST = [20, 30, 40, 50]


def nvidia_vram() -> int:
    out = subprocess.check_output(
        ["nvidia-smi", "--query-gpu=memory.used",
         "--format=csv,noheader,nounits"]).decode().strip()
    return int(out.split()[0])


def main() -> None:
    import torch
    print(f"torch {torch.__version__} | {torch.cuda.get_device_name(0)}",
          flush=True)
    from diffusers import Flux2KleinPipeline

    t0 = time.monotonic()
    pipe = Flux2KleinPipeline.from_pretrained(MODEL, torch_dtype=torch.bfloat16)
    pipe.enable_model_cpu_offload()
    print(f"[load] ready in {time.monotonic() - t0:.1f} s", flush=True)

    for steps in STEPS_LIST:
        out = f"/tmp/flux-steps-{steps}.png"
        torch.cuda.synchronize()
        torch.cuda.reset_peak_memory_stats()
        t = time.monotonic()
        try:
            img = pipe(
                prompt=PROMPT,
                height=HEIGHT,
                width=WIDTH,
                guidance_scale=4.0,
                num_inference_steps=steps,
                generator=torch.Generator(device="cuda").manual_seed(SEED),
            ).images[0]
            dt = time.monotonic() - t
            img.save(out)
            peak = torch.cuda.max_memory_allocated() / 1e9
            print(f"[gen] {steps} steps: {dt:.1f} s | peak {peak:.2f} GB | "
                  f"nvidia-smi {nvidia_vram()} MiB | {out}", flush=True)
        except Exception as e:  # noqa: BLE001
            print(f"[gen] {steps} steps: FEHLER: {e!r}", flush=True)
    print("DONE", flush=True)


if __name__ == "__main__":
    main()