Skip to content

test_causal_similarity

Classes

Functions

fastvideo.tests.ssim.test_causal_similarity.test_causal_similarity 

test_causal_similarity(prompt, ATTENTION_BACKEND, model_id)

Test that runs inference with different parameters and compares the output to reference videos using SSIM.

Source code in fastvideo/tests/ssim/test_causal_similarity.py 
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
@pytest.mark.parametrize("prompt", TEST_PROMPTS)
@pytest.mark.parametrize("ATTENTION_BACKEND", ["FLASH_ATTN"])
@pytest.mark.parametrize("model_id", list(MODEL_TO_PARAMS.keys()))
def test_causal_similarity(prompt, ATTENTION_BACKEND, model_id):
    """
    Test that runs inference with different parameters and compares the output
    to reference videos using SSIM.
    """
    os.environ["FASTVIDEO_ATTENTION_BACKEND"] = ATTENTION_BACKEND

    script_dir = os.path.dirname(os.path.abspath(__file__))

    base_output_dir = os.path.join(script_dir, 'generated_videos', model_id)
    output_dir = os.path.join(base_output_dir, ATTENTION_BACKEND)
    output_video_name = f"{prompt[:100].strip()}.mp4"

    os.makedirs(output_dir, exist_ok=True)

    BASE_PARAMS = MODEL_TO_PARAMS[model_id]
    num_inference_steps = BASE_PARAMS["num_inference_steps"]

    init_kwargs = {
        "num_gpus": BASE_PARAMS["num_gpus"],
        "sp_size": BASE_PARAMS["sp_size"],
        "tp_size": BASE_PARAMS["tp_size"],
        "dit_cpu_offload": True,
    }
    if BASE_PARAMS.get("vae_sp"):
        init_kwargs["vae_sp"] = True
        init_kwargs["vae_tiling"] = True
    #if "text-encoder-precision" in BASE_PARAMS:
    #    init_kwargs["text_encoder_precisions"] = BASE_PARAMS["text-encoder-precision"]

    generation_kwargs = {
        "num_inference_steps": num_inference_steps,
        "output_path": output_dir,
        "height": BASE_PARAMS["height"],
        "width": BASE_PARAMS["width"],
        "num_frames": BASE_PARAMS["num_frames"],
        "seed": BASE_PARAMS["seed"],
    }
    if "neg_prompt" in BASE_PARAMS:
        generation_kwargs["neg_prompt"] = BASE_PARAMS["neg_prompt"]

    generator = VideoGenerator.from_pretrained(model_path=BASE_PARAMS["model_path"], **init_kwargs)
    generator.generate_video(prompt, **generation_kwargs)

    if isinstance(generator.executor, MultiprocExecutor):
        generator.executor.shutdown()

    assert os.path.exists(
        output_dir), f"Output video was not generated at {output_dir}"

    reference_folder = os.path.join(script_dir, device_reference_folder, model_id, ATTENTION_BACKEND)

    if not os.path.exists(reference_folder):
        logger.error("Reference folder missing")
        raise FileNotFoundError(
            f"Reference video folder does not exist: {reference_folder}")

    # Find the matching reference video based on the prompt
    reference_video_name = None

    for filename in os.listdir(reference_folder):
        if filename.endswith('.mp4') and prompt[:100].strip() in filename:
            reference_video_name = filename
            break

    if not reference_video_name:
        logger.error(f"Reference video not found for prompt: {prompt} with backend: {ATTENTION_BACKEND}")
        raise FileNotFoundError(f"Reference video missing")

    reference_video_path = os.path.join(reference_folder, reference_video_name)
    generated_video_path = os.path.join(output_dir, output_video_name)

    logger.info(
        f"Computing SSIM between {reference_video_path} and {generated_video_path}"
    )
    ssim_values = compute_video_ssim_torchvision(reference_video_path,
                                                 generated_video_path,
                                                 use_ms_ssim=True)

    mean_ssim = ssim_values[0]
    logger.info(f"SSIM mean value: {mean_ssim}")
    logger.info(f"Writing SSIM results to directory: {output_dir}")

    success = write_ssim_results(output_dir, ssim_values, reference_video_path,
                                 generated_video_path, num_inference_steps,
                                 prompt)

    if not success:
        logger.error("Failed to write SSIM results to file")

    min_acceptable_ssim = 0.98
    assert mean_ssim >= min_acceptable_ssim, f"SSIM value {mean_ssim} is below threshold {min_acceptable_ssim} for {model_id} with backend {ATTENTION_BACKEND}"