Revert "feat: hidden half-res sampling with RTX VSR output restore"
This reverts commit bd26656732.
This commit is contained in:
parent
bd26656732
commit
f94ee3e40b
@ -6,7 +6,6 @@
|
||||
|
||||
### ⚡ Improvements
|
||||
|
||||
- **Moxie MultiTrack Project**: Single-pass project sampling now runs internally at half the editor-selected resolution, and Moxie Project Video Combine restores the exact editor-selected resolution on the combined frames before export. Output size, frame timing, and audio are identical to the editor settings and no workflow wiring changes; upscaling is hardware-accelerated when the optional `nvidia-vfx` package is installed (NVIDIA RTX GPUs), with an automatic Lanczos fallback everywhere else. Dual-pass, SelfLift, passthrough, and audio-only flows are unchanged.
|
||||
- **Moxie Multimedia Loader**: The `lora_name` combo now defaults to the bundled turbo LoRA (`MM3step.safetensors`) so a fresh clone of the pack works out of the box, with a `none` entry to disable LoRA. Previously the default was a `"<no files found>"` placeholder, which silently skipped LoRA application even when a LoRA was bundled.
|
||||
- **Moxie Preview Override**: The `tiny_vae` combo now lists files from the node pack's own `models/vae_approx` folder first (shipping `MM-preview.safetensors` for MiniMax H3 previews as the default), falling back to ComfyUI's standard `models/vae_approx` directory. The folder is rescanned on every schema refresh, so newly dropped files appear without restarting ComfyUI.
|
||||
- **Moxie Multimedia Loader**: Locked the loader to the MiniMax H3 model set. The `clip_type` dropdown (which previously exposed every CLIP recipe in ComfyUI) was removed; the H3 Qwen3-VL text encoder is now always loaded with the `minimax` CLIP recipe. Any older ComfyUI build without `CLIPType.MINIMAX` raises a clear startup error instead of silently loading the wrong encoder.
|
||||
|
||||
@ -4,7 +4,6 @@ from comfy_api.latest import io
|
||||
from comfy_execution.graph_utils import ExecutionBlocker
|
||||
|
||||
from .nodes.project import EasyMultiTrackProjectVideoCombine, TYPE_PROJECT_DATA
|
||||
from .utils.rtx_vsr import upscale_images_to_output_resolution
|
||||
|
||||
|
||||
class MoxieCombine(EasyMultiTrackProjectVideoCombine):
|
||||
@ -50,14 +49,10 @@ class MoxieCombine(EasyMultiTrackProjectVideoCombine):
|
||||
return io.NodeOutput(video, video, video, video, video)
|
||||
|
||||
components = video.get_components()
|
||||
# Hidden half-res sampling contract: restore the editor-selected
|
||||
# resolution right before the frames leave this node. Frames without
|
||||
# the half-res signature pass through untouched.
|
||||
images = upscale_images_to_output_resolution(components.images, project_data)
|
||||
return io.NodeOutput(
|
||||
video,
|
||||
prefix,
|
||||
images,
|
||||
components.images,
|
||||
components.audio,
|
||||
float(components.frame_rate),
|
||||
)
|
||||
|
||||
@ -36,7 +36,6 @@ from ..utils.h3_project import (
|
||||
validate_h3_project_outputs,
|
||||
)
|
||||
from ..utils.models import detect_turbo_lora_from_prompt, detect_turbo_model
|
||||
from ..utils.rtx_vsr import h3_halfres_sampling_dimensions
|
||||
from ..utils.project_memory import (
|
||||
BOUNDARY_META,
|
||||
SEGMENT_META,
|
||||
@ -1170,33 +1169,16 @@ class EasyMultiTrackProject(io.ComfyNode):
|
||||
"upscale_by must be a finite value greater than or equal to 1"
|
||||
)
|
||||
|
||||
editor_width = int(info["width"])
|
||||
editor_height = int(info["height"])
|
||||
audio_only = (editor_width, editor_height) == (32, 32)
|
||||
first_pass_width = int(info["width"])
|
||||
first_pass_height = int(info["height"])
|
||||
audio_only = (first_pass_width, first_pass_height) == (32, 32)
|
||||
fps = float(info["frame_rate"])
|
||||
# Hidden half-res sampling: single-pass projects condition and sample
|
||||
# at half the editor resolution; the video combine step restores the
|
||||
# editor resolution in pixel space (utils/rtx_vsr.py) before export.
|
||||
halfres_sampling = h3_halfres_sampling_dimensions(
|
||||
editor_width, editor_height
|
||||
target_width, target_height = h3_second_pass_dimensions(
|
||||
first_pass_width,
|
||||
first_pass_height,
|
||||
run_second_pass,
|
||||
upscale_by,
|
||||
)
|
||||
use_halfres_sampling = (
|
||||
halfres_sampling is not None
|
||||
and sampling_mode == "single"
|
||||
and not audio_only
|
||||
)
|
||||
if use_halfres_sampling:
|
||||
first_pass_width, first_pass_height = halfres_sampling
|
||||
target_width, target_height = editor_width, editor_height
|
||||
else:
|
||||
first_pass_width = editor_width
|
||||
first_pass_height = editor_height
|
||||
target_width, target_height = h3_second_pass_dimensions(
|
||||
editor_width,
|
||||
editor_height,
|
||||
run_second_pass,
|
||||
upscale_by,
|
||||
)
|
||||
# Keep task inputs at the configured size; exports use the final size.
|
||||
output_info = {**info, "width": target_width, "height": target_height}
|
||||
initialize_h3_project(
|
||||
|
||||
@ -1,84 +0,0 @@
|
||||
"""Standalone sanity checks for the hidden half-res output upscale contract.
|
||||
|
||||
Loads utils/rtx_vsr.py directly (no ComfyUI, no torch) and verifies the
|
||||
dimension policy and the project_data gating that MoxieCombine relies on.
|
||||
The torch/nvvfx execution path is covered by the user's on-machine tests.
|
||||
|
||||
Run: python scripts/test_rtx_upscale_integration.py
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import importlib.util
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
PACK_ROOT = Path(__file__).resolve().parents[1]
|
||||
MODULE_PATH = PACK_ROOT / "utils" / "rtx_vsr.py"
|
||||
|
||||
spec = importlib.util.spec_from_file_location("rtx_vsr_standalone", MODULE_PATH)
|
||||
rtx_vsr = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(rtx_vsr)
|
||||
|
||||
assert "torch" not in sys.modules, "rtx_vsr must import torch lazily"
|
||||
|
||||
failures = []
|
||||
|
||||
|
||||
def check(name, got, expected):
|
||||
ok = got == expected
|
||||
print(f"{'PASS' if ok else 'FAIL'} {name}: got={got!r} expected={expected!r}")
|
||||
if not ok:
|
||||
failures.append(name)
|
||||
|
||||
|
||||
# --- dimension policy ---
|
||||
cases = [
|
||||
((544, 960), (272, 480)),
|
||||
((960, 544), (480, 272)),
|
||||
((1088, 1920), (544, 960)),
|
||||
((1344, 768), (672, 384)),
|
||||
((552, 968), (288, 496)),
|
||||
((552, 488), (288, 256)),
|
||||
((256, 256), (128, 128)),
|
||||
((32, 32), None), # audio-only sentinel
|
||||
((64, 64), None), # half would collapse onto the sentinel
|
||||
((32, 64), None),
|
||||
((33, 33), None),
|
||||
((0, 100), None),
|
||||
((100, -5), None),
|
||||
(("abc", 100), None),
|
||||
]
|
||||
for (w, h), expected in cases:
|
||||
got = rtx_vsr.h3_halfres_sampling_dimensions(w, h)
|
||||
check(f"dims({w}x{h})", got, expected)
|
||||
|
||||
# --- round trip: sampling canvas restores the editor selection ---
|
||||
for w, h in [(544, 960), (960, 544), (1088, 1920), (1344, 768), (552, 968), (272, 480)]:
|
||||
sampling = rtx_vsr.h3_halfres_sampling_dimensions(w, h)
|
||||
if sampling is None:
|
||||
continue
|
||||
target = rtx_vsr.resolve_output_upscale_target(
|
||||
sampling, {"width": w, "height": h}
|
||||
)
|
||||
check(f"round-trip {w}x{h}", target, (w, h))
|
||||
|
||||
# --- gating (MoxieCombine contract) ---
|
||||
G = rtx_vsr.resolve_output_upscale_target
|
||||
data = {"width": 960, "height": 544}
|
||||
check("fires on half-res signature", G((480, 272), data), (960, 544))
|
||||
check("no-op at target size", G((960, 544), data), None)
|
||||
check("no-op for foreign size", G((500, 300), data), None)
|
||||
check("no-op for dual-pass size", G((1664, 960), data), None)
|
||||
check("json string project data", G((272, 480), '{"width": 544, "height": 960}'), (544, 960))
|
||||
check("bad json", G((272, 480), "{oops"), None)
|
||||
check("empty dict", G((272, 480), {}), None)
|
||||
check("none data", G((272, 480), None), None)
|
||||
check("missing height", G((272, 480), {"width": 960}), None)
|
||||
check("zero dims", G((272, 480), {"width": 0, "height": 0}), None)
|
||||
check("sentinel project", G((32, 32), {"width": 32, "height": 32}), None)
|
||||
|
||||
print()
|
||||
if failures:
|
||||
print(f"{len(failures)} FAILED: {failures}")
|
||||
sys.exit(1)
|
||||
print("All sanity checks passed.")
|
||||
261
utils/rtx_vsr.py
261
utils/rtx_vsr.py
@ -1,261 +0,0 @@
|
||||
"""Hidden half-res sampling output restore for Moxie MultiTrack projects.
|
||||
|
||||
Single-pass project sampling runs at half the editor-selected resolution so
|
||||
the sampling chain stays small and fast. This module owns the other half of
|
||||
that contract: combined frames are restored to the exact editor-selected
|
||||
resolution before the final export, with no user-visible wiring anywhere.
|
||||
|
||||
Hardware path adapted from NVIDIA's RTX Video Super Resolution ComfyUI node
|
||||
(Apache License 2.0):
|
||||
|
||||
https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI
|
||||
Copyright 2025 NVIDIA Corporation
|
||||
|
||||
It drives the ``nvidia-vfx`` pip package (RTX Video Super Resolution) per
|
||||
frame via DLPack. When the package or a supported GPU is unavailable, the
|
||||
module falls back to ComfyUI's Lanczos resize so the delivered frame size is
|
||||
always exact and rendering never fails because of the upscaler.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from typing import Any
|
||||
|
||||
__all__ = [
|
||||
"h3_halfres_sampling_dimensions",
|
||||
"resolve_output_upscale_target",
|
||||
"rtx_vsr_upscale",
|
||||
"upscale_images_to_output_resolution",
|
||||
]
|
||||
|
||||
|
||||
def h3_halfres_sampling_dimensions(
|
||||
width: int, height: int
|
||||
) -> tuple[int, int] | None:
|
||||
"""Sampling canvas for hidden half-res sampling, or ``None`` when disabled.
|
||||
|
||||
Editor dimensions are always a multiple of 8 (MultiTrack Editor widgets
|
||||
and presets), so the normal case is an exact 2x: half of an 8-aligned
|
||||
size rounded up to the 16px sampling grid returns the editor size exactly
|
||||
(544x960 -> 272x480 -> 544x960) and RTX VSR's internal /8 snap becomes a
|
||||
no-op. The ceil policy also keeps hand-written resolutions working:
|
||||
sampling rounds up to the 16px latent grid (H3 video latents are //16,
|
||||
and even pixels keep the staging video codec happy) while the exact
|
||||
target upscale still lands on the editor selection.
|
||||
|
||||
Returns ``None`` for invalid sizes, for the audio-only sentinel (32x32),
|
||||
and for tiny canvases whose half would collapse onto that sentinel.
|
||||
"""
|
||||
try:
|
||||
width = int(width)
|
||||
height = int(height)
|
||||
except (TypeError, ValueError, OverflowError):
|
||||
return None
|
||||
if width <= 0 or height <= 0 or (width, height) == (32, 32):
|
||||
return None
|
||||
|
||||
def _half_up(value: int) -> int:
|
||||
return max(32, -(-value // 2 // 16) * 16)
|
||||
|
||||
sampling_width = _half_up(width)
|
||||
sampling_height = _half_up(height)
|
||||
if (sampling_width, sampling_height) == (32, 32):
|
||||
return None
|
||||
return sampling_width, sampling_height
|
||||
|
||||
|
||||
def _output_resolution_from_project_data(
|
||||
project_data: Any,
|
||||
) -> tuple[int, int] | None:
|
||||
"""Editor-selected output resolution carried by the project widget data."""
|
||||
data = project_data
|
||||
if isinstance(data, str):
|
||||
try:
|
||||
data = json.loads(data)
|
||||
except json.JSONDecodeError:
|
||||
return None
|
||||
if not isinstance(data, dict):
|
||||
return None
|
||||
try:
|
||||
width = int(data.get("width"))
|
||||
height = int(data.get("height"))
|
||||
except (TypeError, ValueError, OverflowError):
|
||||
return None
|
||||
if width <= 0 or height <= 0:
|
||||
return None
|
||||
return width, height
|
||||
|
||||
|
||||
def resolve_output_upscale_target(
|
||||
frame_size: tuple[int, int],
|
||||
project_data: Any,
|
||||
) -> tuple[int, int] | None:
|
||||
"""Output size to restore, or ``None`` when the frames need no upscale.
|
||||
|
||||
Fires only for the exact signature of the hidden half-res pipeline: the
|
||||
combined frames match the half-res sampling canvas derived from the
|
||||
project's editor resolution. Everything else passes through untouched -
|
||||
full-res renders, dual-pass and SelfLift outputs, passthrough media,
|
||||
legacy projects without the sampling contract, and foreign videos that
|
||||
happen to share a project's name.
|
||||
"""
|
||||
output = _output_resolution_from_project_data(project_data)
|
||||
if output is None:
|
||||
return None
|
||||
output_width, output_height = output
|
||||
sampling = h3_halfres_sampling_dimensions(output_width, output_height)
|
||||
if sampling is None:
|
||||
return None
|
||||
sampling_width, sampling_height = sampling
|
||||
if frame_size == (sampling_width, sampling_height) and frame_size != (
|
||||
output_width,
|
||||
output_height,
|
||||
):
|
||||
return output_width, output_height
|
||||
return None
|
||||
|
||||
|
||||
def _log(message: str) -> None:
|
||||
try:
|
||||
from .log import log_node_info
|
||||
except Exception: # pragma: no cover - standalone tooling without the pack
|
||||
print(f"[Moxie] {message}", flush=True) # noqa: T201
|
||||
return
|
||||
log_node_info("MultiTrack Output", message)
|
||||
|
||||
|
||||
_FALLBACK_NOTICE_SHOWN = False
|
||||
|
||||
|
||||
def _notice_fallback(message: str) -> None:
|
||||
global _FALLBACK_NOTICE_SHOWN
|
||||
if _FALLBACK_NOTICE_SHOWN:
|
||||
return
|
||||
_FALLBACK_NOTICE_SHOWN = True
|
||||
_log(message)
|
||||
|
||||
|
||||
def _lanczos_upscale(images: Any, output_width: int, output_height: int) -> Any:
|
||||
import comfy.utils
|
||||
|
||||
samples = images[..., :3].movedim(-1, 1)
|
||||
upscaled = comfy.utils.common_upscale(
|
||||
samples, output_width, output_height, "lanczos", "disabled"
|
||||
)
|
||||
return upscaled.movedim(1, -1)
|
||||
|
||||
|
||||
def rtx_vsr_upscale(
|
||||
images: Any,
|
||||
output_width: int,
|
||||
output_height: int,
|
||||
quality: str = "ULTRA",
|
||||
) -> Any:
|
||||
"""Upscale an IMAGE batch to the exact target size, hardware first.
|
||||
|
||||
Frames are processed per frame through RTX Video Super Resolution
|
||||
(adapted from Comfy-Org/Nvidia_RTX_Nodes_ComfyUI, Apache 2.0). Any
|
||||
failure - missing package, unsupported GPU, VRAM pressure - degrades to
|
||||
the Lanczos fallback instead of breaking the render, and the delivered
|
||||
size is corrected to the exact target whenever the hardware snap misses.
|
||||
"""
|
||||
import torch
|
||||
|
||||
frame_count, in_height, in_width, channels = images.shape
|
||||
if frame_count == 0 or (in_height, in_width) == (output_height, output_width):
|
||||
return images
|
||||
|
||||
hardware_ready = channels == 3
|
||||
if hardware_ready:
|
||||
try:
|
||||
import nvvfx
|
||||
except Exception:
|
||||
hardware_ready = False
|
||||
_notice_fallback(
|
||||
"Hardware upscale unavailable (install nvidia-vfx for RTX "
|
||||
"acceleration); using Lanczos fallback."
|
||||
)
|
||||
|
||||
if hardware_ready:
|
||||
# /8 snap from the NVIDIA node; editor selections are 8-aligned so
|
||||
# this is an identity operation for real project resolutions.
|
||||
snapped_width = max(8, round(output_width / 8) * 8)
|
||||
snapped_height = max(8, round(output_height / 8) * 8)
|
||||
max_batch_pixels = 1024 * 1024 * 16
|
||||
batch_size = max(
|
||||
1, max_batch_pixels // max(1, snapped_width * snapped_height)
|
||||
)
|
||||
quality_levels = {
|
||||
"LOW": nvvfx.effects.QualityLevel.LOW,
|
||||
"MEDIUM": nvvfx.effects.QualityLevel.MEDIUM,
|
||||
"HIGH": nvvfx.effects.QualityLevel.HIGH,
|
||||
"ULTRA": nvvfx.effects.QualityLevel.ULTRA,
|
||||
}
|
||||
selected_quality = quality_levels.get(
|
||||
str(quality).upper(), nvvfx.effects.QualityLevel.HIGH
|
||||
)
|
||||
out_tensor = torch.empty(
|
||||
(frame_count, snapped_height, snapped_width, channels),
|
||||
device=images.device,
|
||||
dtype=images.dtype,
|
||||
)
|
||||
try:
|
||||
with nvvfx.VideoSuperRes(selected_quality) as super_res:
|
||||
super_res.output_width = snapped_width
|
||||
super_res.output_height = snapped_height
|
||||
super_res.load()
|
||||
for start in range(0, frame_count, batch_size):
|
||||
batch = images[start : start + batch_size]
|
||||
batch_cuda = (
|
||||
batch.cuda().permute(0, 3, 1, 2).float().contiguous()
|
||||
)
|
||||
for offset in range(batch_cuda.shape[0]):
|
||||
result = super_res.run(batch_cuda[offset]).image
|
||||
out_tensor[start + offset : start + offset + 1] = (
|
||||
torch.from_dlpack(result).movedim(0, -1).unsqueeze(0)
|
||||
)
|
||||
except Exception as error:
|
||||
hardware_ready = False
|
||||
_notice_fallback(
|
||||
f"Hardware upscale failed ({error}); using Lanczos fallback."
|
||||
)
|
||||
else:
|
||||
if (snapped_height, snapped_width) != (output_height, output_width):
|
||||
return _lanczos_upscale(out_tensor, output_width, output_height)
|
||||
return out_tensor
|
||||
|
||||
return _lanczos_upscale(images, output_width, output_height)
|
||||
|
||||
|
||||
def upscale_images_to_output_resolution(
|
||||
images: Any,
|
||||
project_data: Any,
|
||||
) -> Any:
|
||||
"""Restore the editor resolution on combined half-res frames.
|
||||
|
||||
Used by Moxie Project Video Combine right before the ``images`` output:
|
||||
frames carrying the hidden half-res sampling signature are upscaled back
|
||||
to the editor-selected resolution, everything else is returned untouched.
|
||||
"""
|
||||
try:
|
||||
import torch
|
||||
except ImportError: # pragma: no cover - torch is required in ComfyUI
|
||||
return images
|
||||
if (
|
||||
not isinstance(images, torch.Tensor)
|
||||
or images.ndim != 4
|
||||
or images.shape[0] == 0
|
||||
):
|
||||
return images
|
||||
target = resolve_output_upscale_target(
|
||||
(int(images.shape[2]), int(images.shape[1])), project_data
|
||||
)
|
||||
if target is None:
|
||||
return images
|
||||
output_width, output_height = target
|
||||
_log(
|
||||
f"Output upscale: {int(images.shape[2])}x{int(images.shape[1])} -> "
|
||||
f"{output_width}x{output_height}"
|
||||
)
|
||||
return rtx_vsr_upscale(images, output_width, output_height)
|
||||
Loading…
Reference in New Issue
Block a user