FastVideo CausalWan2.2-I2V-A14B-Preview-Diffusers Model
Disclaimer
Note that this is a preview model, meaning there are still quality issues. The inference speed is also unoptimized.
Introduction
We're excited to introduce the CausalWan2.2 I2V A14B series—a new line of models.
Model Overview
- 8-step inference is supported.
- Try it out on FastVideo — we support a wide range of GPUs from H100 to 4090, and also support Mac users!
Inference code
from fastvideo import VideoGenerator, SamplingParam
import json
# from fastvideo.configs.sample import SamplingParam
OUTPUT_PATH = "video_samples_self_forcing_causal_wan2_2_14B_i2v"
def main():
# FastVideo will automatically use the optimal default arguments for the
# model.
# If a local path is provided, FastVideo will make a best effort
# attempt to identify the optimal arguments.
generator = VideoGenerator.from_pretrained(
"FastVideo/SFWan2.2-I2V-A14B-Preview-Diffusers",
# FastVideo will automatically handle distributed setup
num_gpus=1,
use_fsdp_inference=True,
dit_cpu_offload=True, # DiT need to be offloaded for MoE
dit_precision="fp32",
vae_cpu_offload=False,
text_encoder_cpu_offload=True,
dmd_denoising_steps=[1000, 850, 700, 550, 350, 275, 200, 125],
# Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
pin_cpu_memory=True,
# image_encoder_cpu_offload=False,
)
sampling_param = SamplingParam.from_pretrained("FastVideo/SFWan2.2-I2V-A14B-Preview-Diffusers")
sampling_param.num_frames = 81
sampling_param.width = 832
sampling_param.height = 480
sampling_param.seed = 1000
with open("prompts/mixkit_i2v.jsonl", "r") as f:
prompt_image_pairs = json.load(f)
for prompt_image_pair in prompt_image_pairs:
prompt = prompt_image_pair["prompt"]
image_path = prompt_image_pair["image_path"]
_ = generator.generate_video(prompt, image_path=image_path, output_path=OUTPUT_PATH, save_video=True, sampling_param=sampling_param)
if __name__ == "__main__":
main()