daniel/h3-blackwell-runtime
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Report direct sampling progress

Browse source
This commit is contained in:
Daniel Maddern 2026-08-12 21:39:31 +07:00
parent eed3a3d951
commit e5ffacc625
1 changed files with 16 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
src/h3_blackwell_runtime/sampler.py
View file

@ -1,5 +1,7 @@
"""Minimal direct prompt-only H3 video sampler for visual smoke previews."""
import time
import torch
from .packing import H3PromptPacker, unpatchify_video
@ -52,8 +54,12 @@ def sample_video_res_multistep(model, packer: H3PromptPacker, text: torch.Tensor
audio_carried = audio * 4.0
video_history = audio_history = None
video_history_sigma = audio_history_sigma = None
for index, sigma in enumerate(sigmas[:-1]):
sigma_down = sigmas[index + 1]
total_steps = len(sigmas) - 1
started = time.perf_counter()
for index, sigma in enumerate(sigmas[:-1], start=1):
step_started = time.perf_counter()
previous_index = index - 1
sigma_down = sigmas[index]
sigma_audio = _audio_sigma(sigma)
native_audio = audio_carried * (sigma_audio / sigma)
hidden, times, segments, positions, video_segment, audio_segment = packer(text, video, native_audio, float(sigma))
@ -64,11 +70,18 @@ def sample_video_res_multistep(model, packer: H3PromptPacker, text: torch.Tensor
velocity_audio = (1.0 - 4.0) * (audio_carried * carry) + (1.0 + 3.0 * sigma_audio) * velocity_audio_native
video_denoised = video - sigma * velocity_video
audio_denoised = audio_carried - sigma * velocity_audio
previous_sigma = sigmas[index - 1] if index else None
previous_sigma = sigmas[previous_index - 1] if previous_index else None
video = res_multistep_update(video, video_denoised, sigma, sigma_down, video_history, video_history_sigma, previous_sigma)
audio_carried = res_multistep_update(audio_carried, audio_denoised, sigma, sigma_down, audio_history, audio_history_sigma, previous_sigma)
video_history, audio_history = video_denoised, audio_denoised
video_history_sigma = audio_history_sigma = sigma_down
elapsed = time.perf_counter() - started
eta = elapsed / index * (total_steps - index)
print(
f"sampling step {index}/{total_steps}: "
f"{time.perf_counter() - step_started:.1f}s, elapsed {elapsed:.1f}s, eta {eta:.1f}s",
flush=True,
)
return video