New project node variant (MoxieProjectSlow, display name 'Moxie MultiTrack Project Slow') that replaces the RTX VSR pixel restore with a latent upscaler plus a short refine pass: - identical UX to MoxieProject: end users only set steps and seed (plus the shared context_frames overlap); schema mirrors the base node via a shared _project_inputs() helper - first pass stays at the hidden half resolution (engine gains a _h3_first_pass_resolution_scale class hook, overriding the previous sampling_mode == 'single' hardcode; MoxieProjectSlow returns 0.5 under dual mode) - the half-res latent is upscaled to the final (editor) size by the H3 latent upscaler (minimax_h3_latent_upscaler_3d_fp16.safetensors, models/latent_upscale_models) and refined with a hidden 2-step euler pass at 0.33 denoise; the schedule replicates KSampler.set_steps (int(steps/denoise) total steps, last steps+1 sigmas) without relying on the denoise kwarg that newer comfy.samplers builds dropped - baked settings: sampling_mode dual, upscale_by 1.0 (final size IS the editor size), upscale_model as above; the engine's upscale-skip condition now compares actual first-pass vs target dimensions instead of upscale_by <= 1, which is behavior-identical for every existing configuration - segments are saved at the project resolution, so the Video Combine restore passes through untouched - no RTX VSR anywhere - MoxieProject refactor: component check and baked settings moved into reusable helpers (_require_moxie_components, _baked_project_settings classmethod) so the subclass composes cleanly; messages unchanged - tests: Slow schema mirror, execute passthrough (sigma schedule math, baked settings, context_frames forwarding, first-pass schedule), the resolution-scale hook, and the denoise truncation helper - docs: CHANGELOG entry, multitrack-schema.md note
267 lines
10 KiB
Python
267 lines
10 KiB
Python
from __future__ import annotations
|
|
|
|
import comfy.samplers
|
|
from comfy_api.latest import io
|
|
|
|
from .nodes.project import (
|
|
EasyMultiTrackProject,
|
|
H3_CONTEXT_LENGTH_OPTIONS,
|
|
H3_CONTEXT_SOURCE_FRAMES,
|
|
TYPE_TRACKS_INFO,
|
|
_first_input,
|
|
)
|
|
|
|
# Values baked from the reference workflow (Moxie-clean.json). End users only
|
|
# control project_name, steps and seed on this node.
|
|
BAKED_PROJECT_SETTINGS = {
|
|
"project_save": "override",
|
|
"segment_start_number": 1,
|
|
"segment_count": -1,
|
|
"sampling_plan": "custom",
|
|
"sampling_mode": "single",
|
|
"1st_pass_only": False,
|
|
"disable_2nd_noise": False,
|
|
"upscale_by": 1.5,
|
|
"upscale_model": "None",
|
|
"enabled_tiling": "false",
|
|
}
|
|
BAKED_SAMPLER_NAME = "euler"
|
|
BAKED_SCHEDULER = "beta"
|
|
|
|
# Moxie MultiTrack Project Slow: the hidden half-resolution first pass is
|
|
# upscaled to the final size by the H3 latent upscaler model and refined with
|
|
# a short low-denoise euler pass instead of the RTX VSR pixel restore.
|
|
SLOW_UPSCALE_MODEL = "minimax_h3_latent_upscaler_3d_fp16.safetensors"
|
|
SLOW_SECOND_PASS_STEPS = 2
|
|
SLOW_SECOND_PASS_DENOISE = 0.33
|
|
SLOW_PROJECT_SETTINGS_DELTA = {
|
|
"sampling_mode": "dual",
|
|
# The first pass already runs at half the editor resolution, so the final
|
|
# size IS the editor size: a scale factor of 1.0 keeps the project
|
|
# manifest at the editor dimensions while the latent upscaler (target
|
|
# dimensions mode) bridges the half-res gap.
|
|
"upscale_by": 1.0,
|
|
"upscale_model": SLOW_UPSCALE_MODEL,
|
|
}
|
|
|
|
|
|
def _require_moxie_components(model, clip, video_vae, audio_vae) -> None:
|
|
missing = [
|
|
name
|
|
for name, value in (
|
|
("model", model),
|
|
("clip", clip),
|
|
("video_vae", video_vae),
|
|
("audio_vae", audio_vae),
|
|
)
|
|
if value is None
|
|
]
|
|
if missing:
|
|
raise ValueError(
|
|
"MoxieProject: Missing required model components: "
|
|
+ ", ".join(missing)
|
|
+ ". Wire model, clip, video_vae, and audio_vae from Moxie Multimedia Loader."
|
|
)
|
|
|
|
|
|
def _denoise_truncated_sigmas(
|
|
model_sampling, scheduler: str, steps: int, denoise: float
|
|
):
|
|
"""Sigma schedule for `steps` steps at `denoise`, matching KSampler.
|
|
|
|
Replicates comfy KSampler.set_steps: build the schedule at
|
|
int(steps / denoise) total steps, then keep the last steps + 1 sigmas.
|
|
Written out because newer ComfyUI builds dropped the denoise kwarg from
|
|
comfy.samplers.calculate_sigmas.
|
|
"""
|
|
if denoise <= 0.0:
|
|
raise ValueError("denoise must be positive")
|
|
if denoise > 0.9999:
|
|
total_steps = steps
|
|
else:
|
|
total_steps = int(steps / denoise)
|
|
schedule = comfy.samplers.calculate_sigmas(
|
|
model_sampling, scheduler, total_steps
|
|
).cpu()
|
|
return schedule[-(steps + 1):]
|
|
|
|
|
|
class MoxieProject(EasyMultiTrackProject):
|
|
"""MultiTrack Project with the sampling stack consolidated.
|
|
|
|
Replaces: easy multitrackProject + 2x KSamplerSelect (euler / sa_solver)
|
|
+ BasicScheduler (beta) + ManualSigmas. Execution delegates to the
|
|
battle-tested Easy-Media implementation with sampler/sigmas computed
|
|
internally from the exposed `steps` widget.
|
|
"""
|
|
|
|
@classmethod
|
|
def _baked_project_settings(cls) -> dict:
|
|
return dict(BAKED_PROJECT_SETTINGS)
|
|
|
|
@classmethod
|
|
def _project_inputs(cls) -> list:
|
|
return [
|
|
TYPE_TRACKS_INFO.Input("tracks_info"),
|
|
io.Model.Input("model", tooltip="Diffusion model from Moxie Multimedia Loader (attention backend already applied)."),
|
|
io.Clip.Input("clip", tooltip="CLIP text encoder from Moxie Multimedia Loader."),
|
|
io.Vae.Input("video_vae", tooltip="Video VAE from Moxie Multimedia Loader."),
|
|
io.Vae.Input("audio_vae", tooltip="Audio VAE from Moxie Multimedia Loader (required to decode Moxie audio)."),
|
|
io.String.Input("project_name", default="",
|
|
tooltip="Name of the project; used for output folders."),
|
|
io.Int.Input(
|
|
"steps",
|
|
default=3,
|
|
min=1,
|
|
max=10000,
|
|
tooltip="Sampling steps for the beta scheduler (3 for the baked-in 3-step distill; "
|
|
"8 for busy motion, 6 low motion, 4 runs/no dialogue).",
|
|
),
|
|
io.Combo.Input(
|
|
"context_frames",
|
|
options=[str(option) for option in H3_CONTEXT_LENGTH_OPTIONS],
|
|
default=str(H3_CONTEXT_SOURCE_FRAMES),
|
|
tooltip=(
|
|
"Video frames copied from the previous segment as "
|
|
"continuation context for segments whose continuity "
|
|
"mode is Context or Context Swap. Longer values hand "
|
|
"off motion more smoothly but generate that many extra "
|
|
"frames per segment. Values are H3 temporal-grid "
|
|
"lengths shared with the Moxie context sampler nodes."
|
|
),
|
|
),
|
|
io.Int.Input(
|
|
"seed",
|
|
default=42,
|
|
min=0,
|
|
max=0xFFFFFFFFFFFFFFFF,
|
|
step=1,
|
|
control_after_generate=io.ControlAfterGenerate.randomize,
|
|
),
|
|
]
|
|
|
|
@classmethod
|
|
def define_schema(cls) -> io.Schema:
|
|
return io.Schema(
|
|
node_id="MoxieProject",
|
|
display_name="Moxie MultiTrack Project",
|
|
category="EasyUse/MultiTrackEditor",
|
|
description=(
|
|
"Build and execute a multi-track Moxie project. "
|
|
"Takes model, clip, video_vae and audio_vae directly from the Moxie Multimedia Loader. "
|
|
"Sampling is baked to a single pass with euler + beta sigmas; set only steps and seed."
|
|
),
|
|
is_input_list=True,
|
|
enable_expand=True,
|
|
not_idempotent=True,
|
|
inputs=cls._project_inputs(),
|
|
hidden=[io.Hidden.prompt, io.Hidden.unique_id],
|
|
outputs=[
|
|
io.String.Output("PROJECT_NAME"),
|
|
io.Audio.Output("LOCKED_AUDIO"),
|
|
],
|
|
)
|
|
|
|
@classmethod
|
|
def execute(cls, **kwargs) -> io.NodeOutput:
|
|
steps = int(_first_input(kwargs.get("steps"), 3))
|
|
|
|
model = _first_input(kwargs.get("model"))
|
|
clip = _first_input(kwargs.get("clip"))
|
|
video_vae = _first_input(kwargs.get("video_vae"))
|
|
audio_vae = _first_input(kwargs.get("audio_vae"))
|
|
_require_moxie_components(model, clip, video_vae, audio_vae)
|
|
|
|
# Pack the direct inputs into the loader dict consumed by
|
|
# EasyMultiTrackProject.execute (internal plumbing only).
|
|
synthesized_loader = {
|
|
"model": model,
|
|
"clip": clip,
|
|
"vae": video_vae,
|
|
"audio_vae": audio_vae,
|
|
}
|
|
|
|
# Same math as the native BasicScheduler node (scheduler=beta, denoise=1.0).
|
|
sigmas = comfy.samplers.calculate_sigmas(
|
|
model.get_model_object("model_sampling"), BAKED_SCHEDULER, steps
|
|
).cpu()
|
|
sigmas = sigmas[-(steps + 1):]
|
|
sampler = comfy.samplers.sampler_object(BAKED_SAMPLER_NAME)
|
|
|
|
baked = dict(kwargs)
|
|
baked.update(cls._baked_project_settings())
|
|
baked["model_loader"] = synthesized_loader
|
|
baked["sampler"] = sampler
|
|
baked["sigmas"] = sigmas
|
|
return super().execute(**baked)
|
|
|
|
|
|
class MoxieProjectSlow(MoxieProject):
|
|
"""Moxie MultiTrack Project with a latent-upscale refine pass.
|
|
|
|
Identical pipeline to MoxieProject (hidden half-resolution first pass,
|
|
euler + beta sampling from `steps`), except the low-resolution latent is
|
|
upscaled to the final size by the H3 latent upscaler model and refined
|
|
with a 2-step euler pass at 0.33 denoise. Segments are saved at the
|
|
project resolution, so the Video Combine RTX restore passes through
|
|
untouched - no NVIDIA RTX VSR is used anywhere.
|
|
"""
|
|
|
|
@classmethod
|
|
def _baked_project_settings(cls) -> dict:
|
|
settings = dict(BAKED_PROJECT_SETTINGS)
|
|
settings.update(SLOW_PROJECT_SETTINGS_DELTA)
|
|
return settings
|
|
|
|
@classmethod
|
|
def _h3_first_pass_resolution_scale(cls, sampling_mode: str) -> float:
|
|
# Dual mode would sample the first pass at the editor size; the Slow
|
|
# node keeps MoxieProject's hidden half-resolution speed trick and
|
|
# lets the latent upscaler bridge the gap instead of RTX VSR.
|
|
return 0.5
|
|
|
|
@classmethod
|
|
def define_schema(cls) -> io.Schema:
|
|
return io.Schema(
|
|
node_id="MoxieProjectSlow",
|
|
display_name="Moxie MultiTrack Project Slow",
|
|
category="EasyUse/MultiTrackEditor",
|
|
description=(
|
|
"Build and execute a multi-track Moxie project with a "
|
|
"latent-upscale refine pass. Takes model, clip, video_vae and "
|
|
"audio_vae directly from the Moxie Multimedia Loader. The "
|
|
"first pass samples euler + beta sigmas from steps, the "
|
|
"half-resolution latent is upscaled to the final size with "
|
|
"the H3 latent upscaler model, and a 2-step euler pass at "
|
|
"0.33 denoise refines it; set only steps and seed."
|
|
),
|
|
is_input_list=True,
|
|
enable_expand=True,
|
|
not_idempotent=True,
|
|
inputs=cls._project_inputs(),
|
|
hidden=[io.Hidden.prompt, io.Hidden.unique_id],
|
|
outputs=[
|
|
io.String.Output("PROJECT_NAME"),
|
|
io.Audio.Output("LOCKED_AUDIO"),
|
|
],
|
|
)
|
|
|
|
@classmethod
|
|
def execute(cls, **kwargs) -> io.NodeOutput:
|
|
model = _first_input(kwargs.get("model"))
|
|
clip = _first_input(kwargs.get("clip"))
|
|
video_vae = _first_input(kwargs.get("video_vae"))
|
|
audio_vae = _first_input(kwargs.get("audio_vae"))
|
|
_require_moxie_components(model, clip, video_vae, audio_vae)
|
|
|
|
sigmas_2nd = _denoise_truncated_sigmas(
|
|
model.get_model_object("model_sampling"),
|
|
BAKED_SCHEDULER,
|
|
SLOW_SECOND_PASS_STEPS,
|
|
SLOW_SECOND_PASS_DENOISE,
|
|
)
|
|
injected = dict(kwargs)
|
|
injected["sampler_2nd"] = comfy.samplers.sampler_object(BAKED_SAMPLER_NAME)
|
|
injected["sigmas_2nd"] = sigmas_2nd
|
|
return super().execute(**injected)
|