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>
58 lines
2.2 KiB
Python
58 lines
2.2 KiB
Python
from fastvideo import VideoGenerator
|
|
import json
|
|
# from fastvideo.api.sampling_param import SamplingParam
|
|
|
|
OUTPUT_PATH = "video_samples_hy15"
|
|
|
|
|
|
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(
|
|
"hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-480p_t2v",
|
|
# FastVideo will automatically handle distributed setup
|
|
{
|
|
"engine": {
|
|
"num_gpus": 1,
|
|
"use_fsdp_inference": False, # set to True if GPU is out of memory
|
|
"offload": {
|
|
"dit": True,
|
|
"vae": True,
|
|
"text_encoder": True,
|
|
"pin_cpu_memory": True, # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
|
|
# "image_encoder": False,
|
|
},
|
|
},
|
|
},
|
|
)
|
|
|
|
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.")
|
|
|
|
video = generator.generate({
|
|
"prompt": prompt,
|
|
"negative_prompt": "",
|
|
"sampling": {"num_frames": 81, "fps": 16},
|
|
"output": {"output_path": OUTPUT_PATH, "save_video": True},
|
|
})
|
|
|
|
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.")
|
|
|
|
video2 = generator.generate({
|
|
"prompt": prompt2,
|
|
"negative_prompt": "",
|
|
"sampling": {"num_frames": 81, "fps": 16},
|
|
"output": {"output_path": OUTPUT_PATH, "save_video": True},
|
|
})
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|