Æmotion StudioandClaude Opus 5
363ac1e657
H3's latent is a NestedTensor of a video stream [B,24,T,H,W] and an audio
stream [B,32,2,T], and the model -- not its latent format -- carries audio
scaled onto the video sigma schedule (audio_scale = shift / audio_shift = 4.0).
_split_noise inverted a segment boundary through latent_format.process_in,
which for MiniMaxH3AV is an identity, so the audio residual handed to the next
segment was wrong by that factor of 4. It now inverts through the model's own
process_latent_in / process_latent_out, which is what CFGGuider.inner_sample
actually applies. Every other model is unaffected: BaseModel.process_latent_in
just calls the format.
Measured on real H3 weights, two stages at shader_strength 0, where a segmented
run must reproduce an uninterrupted one:
video max error audio max error
before 9.3e-01 (stream max 4.80) 1.3e+00 (stream max 1.35)
after 4.8e-07 2.4e-07
The audio stream was almost entirely wrong, and because H3 denoises both
streams in one packed sequence the error reached the video through the DiT's
joint attention -- so this degraded picture as well as sound. Verified
bit-identical output on SD 1.5 and Wan 2.1, confirming it is a no-op elsewhere.
Also:
- shader noise at a boundary reads its shape from the noise it is about to
paint, rather than a shape captured before the run started
- latents with no spatial grid ([B,C,L]: Stable Audio, ACE-Step 1.5, MiniMax
Music 3, Hunyuan3D, TripoSplat) raise UnsupportedLatentError naming the
shape, before sampling starts, instead of a bare ValueError from inside noise
generation. At shader_strength 0 they sample through as a plain KSampler.
- delete core/model_compat.py and its three stale tables. Nothing called it;
its tables stopped at LTXV, its model_type == "FLOW" branch was unreachable
(str(ModelType.FLOW).upper() is "MODELTYPE.FLOW"), and its 5-D layout guess
defaulted to [B,F,C,H,W], which ComfyUI never produces. The legacy mode's own
detector is untouched, so pre-2.0 workflows still reproduce their seeds.
Noise generation is now exercised at every channel count ComfyUI ships -- 3, 4,
8, 12, 16, 24, 32, 48, 64, 128 and 256 -- for both image and video latents.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
107 lines
2.1 KiB
Python
107 lines
2.1 KiB
Python
"""
|
|
Core functionality for ComfyUI-ShaderNoiseKSampler.
|
|
|
|
This package provides the central logic for shader noise sampling:
|
|
- params: Parameter normalization and validation
|
|
- constants: Magic numbers and default values
|
|
- blending: Blend mode implementations
|
|
- transforms: Noise transforms
|
|
- sampler: Core sampling logic
|
|
"""
|
|
|
|
from .params import (
|
|
PARAM_ALIASES,
|
|
ShaderParams,
|
|
normalize_param_name,
|
|
get_param_value,
|
|
)
|
|
|
|
from .constants import (
|
|
HASH_CONSTANT,
|
|
DEFAULT_CHANNELS,
|
|
MAX_OCTAVES,
|
|
SUPPORTED_BLEND_MODES,
|
|
SUPPORTED_TRANSFORMS,
|
|
SUPPORTED_SHADER_TYPES,
|
|
SUPPORTED_DISTRIBUTIONS,
|
|
)
|
|
|
|
from .blending import (
|
|
blend_noises,
|
|
)
|
|
|
|
from .transforms import (
|
|
apply_noise_transform,
|
|
normalize_noise,
|
|
resize_noise_spatial,
|
|
resize_noise_channels,
|
|
match_noise_shape,
|
|
)
|
|
|
|
|
|
from .sampler import (
|
|
calculate_stage_strengths,
|
|
calculate_step_ranges,
|
|
calculate_step_points,
|
|
generate_shader_noise,
|
|
)
|
|
|
|
from .debug import (
|
|
StubVisualizer,
|
|
StubDebugger,
|
|
get_visualizer,
|
|
get_debugger,
|
|
set_debug_level,
|
|
)
|
|
|
|
from .logging_config import (
|
|
setup_logging,
|
|
get_logger,
|
|
set_debug_logging,
|
|
set_info_logging,
|
|
set_warning_logging,
|
|
set_quiet_logging,
|
|
)
|
|
|
|
__all__ = [
|
|
# Parameters
|
|
"PARAM_ALIASES",
|
|
"ShaderParams",
|
|
"normalize_param_name",
|
|
"get_param_value",
|
|
# Constants
|
|
"HASH_CONSTANT",
|
|
"DEFAULT_CHANNELS",
|
|
"MAX_OCTAVES",
|
|
"SUPPORTED_BLEND_MODES",
|
|
"SUPPORTED_TRANSFORMS",
|
|
"SUPPORTED_SHADER_TYPES",
|
|
"SUPPORTED_DISTRIBUTIONS",
|
|
# Blending
|
|
"blend_noises",
|
|
# Transforms
|
|
"apply_noise_transform",
|
|
"normalize_noise",
|
|
"resize_noise_spatial",
|
|
"resize_noise_channels",
|
|
"match_noise_shape",
|
|
# Sampler
|
|
"calculate_stage_strengths",
|
|
"calculate_step_ranges",
|
|
"calculate_step_points",
|
|
"generate_shader_noise",
|
|
# Debug
|
|
"StubVisualizer",
|
|
"StubDebugger",
|
|
"get_visualizer",
|
|
"get_debugger",
|
|
"set_debug_level",
|
|
# Logging
|
|
"setup_logging",
|
|
"get_logger",
|
|
"set_debug_logging",
|
|
"set_info_logging",
|
|
"set_warning_logging",
|
|
"set_quiet_logging",
|
|
]
|