Files
hao-ai-lab-FastVideo/examples/inference/optimizations/attention_example.py
T
SolitaryThinker bbbb7ab021 [refactor]: migrate examples/scripts to typed VideoGenerator API; rename api/compat.py to api/translation.py
Move all examples/inference and scripts off the legacy
VideoGenerator.from_pretrained(model, **kwargs) +
generate_video(prompt, **kwargs) surface onto the typed
from_config(GeneratorConfig(...)) + generate(GenerationRequest(...))
convention, including the Kandinsky-5 and DreamX-World examples added
on main after the original migration. git-mv api/compat.py to
api/translation.py ('compat' implied a temporary shim; the forward
translation is its honest permanent role) and repoint all importers,
tests, and doc links.
2026-07-11 03:26:24 -07:00

48 lines
1.6 KiB
Python

import os
import time
from fastvideo import VideoGenerator
from fastvideo.api import (
EngineConfig, GenerationRequest, GeneratorConfig, OffloadConfig,
OutputConfig, SamplingConfig,
)
def main():
# set the attention backend
os.environ["FASTVIDEO_ATTENTION_BACKEND"] = "FLASH_ATTN"
start_time = time.perf_counter()
gen = VideoGenerator.from_config(
GeneratorConfig(
model_path="Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
engine=EngineConfig(
num_gpus=1,
offload=OffloadConfig(
dit=False,
vae=False,
text_encoder=True,
pin_cpu_memory=True, # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
),
),
))
load_time = time.perf_counter() - start_time
print(f"Model loading time: {load_time:.2f} seconds")
gen_start_time = time.perf_counter()
gen.generate(
GenerationRequest(
prompt=
"Will Smith casually eats noodles, his relaxed demeanor contrasting with the energetic background of a bustling street food market. The scene captures a mix of humor and authenticity. Mid-shot framing, vibrant lighting.",
sampling=SamplingConfig(seed=1024),
output=OutputConfig(output_path="example_outputs/")))
generation_time = time.perf_counter() - gen_start_time
print(f"Video generation time: {generation_time:.2f} seconds")
total_time = time.perf_counter() - start_time
print(f"Total execution time: {total_time:.2f} seconds")
if __name__ == "__main__":
main()