Davids048andClaude Fable 5.1
a5aa64ab6b
VideoGenerator.from_pretrained(model_path, config) takes the same nested
settings as from_config; the 24 flat keywords, from_pretrained_kwargs_to_config,
FROM_PRETRAINED_KWARGS, and every flat_field in the schema are deleted.
nvfp4_fa4 is the typed field engine.attention.nvfp4_fa4, applied by a
resolution step. 65 call sites and the docs use the nested form; the three
kwargs golden cases are config cases with byte-identical results.
Every value is decided during resolution; no runtime code calls
with_override. The device offload policy (unified memory, MPS, layerwise
conflicts, lazy module load) runs as resolution steps in the main process
(fastvideo/api/device_policy.py), and the worker runs on the config it
receives. The LTX-2 refine defaults from model_index.json and the MiniMax-H3
schedule from fastvideo_inference.json are resolution steps
(fastvideo/api/checkpoint_defaults.py) that read local checkpoints or download
only those files; the H3 pipeline validates the schedule against the loaded
schedulers but no longer writes it. The preprocessing entry point passes the
downloaded local path as run state instead of a config override. Teacher and
critic models load with override_transformer_cls_name as a load argument.
The test isolation turns the device policy off, as it blocks downloads, so
that the goldens do not depend on the machine.
Against the 3f6893a0 goldens, every field still matches except boundary_ratio
and ltx2_vae_tiling (DESIGN section 9) and the fields that no longer exist.
The launcher and trainer YAML verifications report 0 unexplained differences.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
78 lines
3.4 KiB
Python
78 lines
3.4 KiB
Python
from fastvideo import VideoGenerator
|
|
from fastvideo.models.dits.hyworld.resolution_utils import get_resolution_from_image
|
|
|
|
# Default prompt from HY-WorldPlay run.sh
|
|
DEFAULT_PROMPT = 'A paved pathway leads towards a stone arch bridge spanning a calm body of water. Lush green trees and foliage line the path and the far bank of the water. A traditional-style pavilion with a tiered, reddish-brown roof sits on the far shore. The water reflects the surrounding greenery and the sky. The scene is bathed in soft, natural light, creating a tranquil and serene atmosphere. The pathway is composed of large, rectangular stones, and the bridge is constructed of light gray stone. The overall composition emphasizes the peaceful and harmonious nature of the landscape.'
|
|
DEFAULT_IMAGE = 'https://raw.githubusercontent.com/Tencent-Hunyuan/HY-WorldPlay/main/assets/img/test.png'
|
|
|
|
OUTPUT_PATH = "video_samples_hyworld"
|
|
|
|
|
|
def main():
|
|
import argparse
|
|
|
|
# pose: (a, w, s, d) - (15, 31)
|
|
# num_frames: (61, 125)
|
|
parser = argparse.ArgumentParser(description="HYWorld video generation with FastVideo")
|
|
parser.add_argument("--prompt", type=str, default=DEFAULT_PROMPT, help="Text prompt for video generation")
|
|
parser.add_argument("--image", type=str, default=DEFAULT_IMAGE, help="Path or URL to input image")
|
|
parser.add_argument("--pose", type=str, default='w-31', help="Pose string (e.g., 'a-31', 'w-31', 's-31', 'd-31')")
|
|
parser.add_argument("--output_path", type=str, default=OUTPUT_PATH, help="Output video path")
|
|
parser.add_argument("--num-frames", type=int, default=125, help="Number of frames")
|
|
parser.add_argument("--seed", type=int, default=1, help="Random seed")
|
|
parser.add_argument("--resolution", type=str, default="480p", help="Only support 480p for now")
|
|
args = parser.parse_args()
|
|
|
|
# Automatically determine resolution from input image
|
|
HEIGHT, WIDTH = get_resolution_from_image(args.image, args.resolution)
|
|
print(f"Image: {args.image}")
|
|
print(f"Pose: {args.pose}")
|
|
print(f"Resolution: {HEIGHT}x{WIDTH} (from {args.resolution} buckets)")
|
|
print(f"Num frames: {args.num_frames}")
|
|
print(f"Output path: {args.output_path}")
|
|
|
|
# Initialize generator
|
|
print("\nInitializing VideoGenerator for HYWorld...")
|
|
generator = VideoGenerator.from_pretrained(
|
|
"FastVideo/HY-WorldPlay-Bidirectional-Diffusers",
|
|
{
|
|
"engine": {
|
|
"num_gpus": 1,
|
|
"use_fsdp_inference": True,
|
|
"offload": {
|
|
"dit": True,
|
|
"vae": True,
|
|
"text_encoder": True,
|
|
"pin_cpu_memory": True,
|
|
"image_encoder": True,
|
|
},
|
|
},
|
|
},
|
|
)
|
|
|
|
# Generate video
|
|
# The pose string is automatically converted to camera matrices by the pipeline
|
|
print("\nGenerating video...")
|
|
generator.generate({
|
|
"prompt": args.prompt,
|
|
"negative_prompt": "",
|
|
"inputs": {
|
|
"image_path": args.image,
|
|
"pose": args.pose, # Camera trajectory control
|
|
},
|
|
"sampling": {
|
|
"num_frames": args.num_frames,
|
|
"fps": 24,
|
|
"height": HEIGHT,
|
|
"width": WIDTH,
|
|
"seed": args.seed,
|
|
},
|
|
"output": {"output_path": args.output_path, "save_video": True},
|
|
})
|
|
|
|
print(f"\nVideo saved to: {args.output_path}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|