13 lines
762 B
Python
13 lines
762 B
Python
|
"""Smoke-test direct H3 prompt-only packed input construction."""
|
||
|
|
|
||
|
|
from h3_blackwell_runtime.checkpoint import H3Checkpoint
|
||
|
|
from h3_blackwell_runtime.packing import H3PromptPacker
|
||
|
|
from h3_blackwell_runtime.t2v import empty_av_latents
|
||
|
|
|
||
|
|
|
||
|
|
checkpoint = H3Checkpoint("/models/minimax_h3_fl2va_pruned_nvfp4.safetensors")
|
||
|
|
video, audio, frames = empty_av_latents(960, 544, 124)
|
||
|
|
text = video.new_zeros((1, 8, 5120), dtype=video.dtype)
|
||
|
|
hidden, timesteps, segments, positions, video_segment, audio_segment = H3PromptPacker(checkpoint)(text, video, audio, 1.0)
|
||
|
|
print({"frames": frames, "hidden": tuple(hidden.shape), "timesteps": timesteps.tolist(), "positions": tuple(positions.shape), "segments": segments, "video_segment": video_segment, "audio_segment": audio_segment})
|