shaoxiongduan
34a0a81be1
TrackWan = Wan2.2 + MotionStream point-track motion control. Stage-1 bidirectional I2V finetune (text kept), built on the new modular trainer. - DiT: TrackWanTransformer3DModel (52ch in = 16 noisy + 20 I2V + 16 track), TrackEncoder (sinusoidal track-ID embed, scatter, 4x temporal conv, zero-init head); config + registry. - Trainer: WanTrackModel wrapper, i2v_track preprocess pipeline + pyarrow schema, TrackValidationCallback, finetune_wantrack_i2v.yaml. - data_pipeline/: video gen (Wan2.2-A14B), CoTracker3 track extraction, 52ch init conversion, synthetic track authoring, controllability (CoTracker EPE) eval, standalone inference, Gradio demo. - eval: motion.cotracker_epe metric. research_log/ lab notebook. - fixes: FA3 flash_attn_func tuple unwrap; decord fallback for removed torchvision.io.read_video; preprocess flush write_remainder.
48 lines
2.3 KiB
Python
48 lines
2.3 KiB
Python
from fastvideo import VideoGenerator
|
|
|
|
# from fastvideo.api.sampling_param import SamplingParam
|
|
|
|
OUTPUT_PATH = "video_samples_wan2_2_14B_t2v"
|
|
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(
|
|
"Wan-AI/Wan2.2-T2V-A14B-Diffusers",
|
|
# FastVideo will automatically handle distributed setup
|
|
num_gpus=1,
|
|
use_fsdp_inference=False, # set to True if GPU is out of memory
|
|
dit_cpu_offload=True, # DiT need to be offloaded for MoE
|
|
vae_cpu_offload=False,
|
|
text_encoder_cpu_offload=True,
|
|
# 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("Wan-AI/Wan2.1-T2V-1.3B-Diffusers")
|
|
# sampling_param.num_frames = 45
|
|
# sampling_param.image_path = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg"
|
|
# Generate videos with the same simple API, regardless of GPU count
|
|
prompt = (
|
|
"A curious raccoon peers through a vibrant field of yellow sunflowers, its eyes "
|
|
"wide with interest. The playful yet serene atmosphere is complemented by soft "
|
|
"natural light filtering through the petals. Mid-shot, warm and cheerful tones."
|
|
)
|
|
_ = generator.generate_video(prompt, output_path=OUTPUT_PATH, save_video=True, height=720, width=1280, num_frames=81)
|
|
# video = generator.generate_video(prompt, sampling_param=sampling_param, output_path="wan_t2v_videos/")
|
|
|
|
# Generate another video with a different prompt, without reloading the
|
|
# model!
|
|
prompt2 = (
|
|
"A majestic lion strides across the golden savanna, its powerful frame "
|
|
"glistening under the warm afternoon sun. The tall grass ripples gently in "
|
|
"the breeze, enhancing the lion's commanding presence. The tone is vibrant, "
|
|
"embodying the raw energy of the wild. Low angle, steady tracking shot, "
|
|
"cinematic.")
|
|
_ = generator.generate_video(prompt2, output_path=OUTPUT_PATH, save_video=True, height=720, width=1280, num_frames=81)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main() |