Merge pull request #2 from numz/main

Update the plugin

Author: doombeaker

CONTRIBUTING.md

@@ -16,15 +16,9 @@ We welcome code contributions from the community. Here's how to propose changes:
 1. Fork this repository to your own GitHub account.
 2. Create a new branch on your fork for your changes.
 3. Make your changes in this branch.
-4. When you are ready, submit a pull request to either:
-   - **`main` branch** - For stable features and bug fixes
-   - **`nightly` branch** - For experimental features or if you want faster integration (note: this branch changes more frequently and may be less stable)
+4. When you are ready, submit a pull request to the **`main`** branch.
 
-### Branch Guidelines
-- **Main Branch**: Use this for production-ready changes, critical bug fixes, and well-tested features
-- **Nightly Branch**: Use this for experimental features, cutting-edge improvements, or if you need your changes integrated quickly. Be aware that this branch is actively under development and may contain unstable features.
-
-We use the GitHub Flow workflow. Choose the appropriate target branch based on the nature of your contribution.
+We use the GitHub Flow workflow.
 
 Before submitting a pull request, please make sure your code adheres to the project's coding conventions and it has passed all tests. If you are adding features, please also add appropriate tests.
 

README.md

@@ -3,6 +3,7 @@
 Official SeedVR2 integration for ComfyUI
 """
 
+from .src.optimization.compatibility import ensure_triton_compat  # noqa: F401
 from .src.interfaces import comfy_entrypoint, SeedVR2Extension
 
 __all__ = ["comfy_entrypoint", "SeedVR2Extension"]

__init__.py

@@ -1,15 +1,14 @@
 [project]
 name = "seedvr2_videoupscaler"
 description = "SeedVR2 official ComfyUI integration: ByteDance-Seed's one-step diffusion-based video/image upscaling with memory-efficient inference"
-version = "2.5.10"
+version = "2.5.24"
 authors = [
     {name = "numz"},
     {name = "adrientoupet"}
 ]
 license = {file = "LICENSE"} 
 classifiers = [
-     "Operating System :: OS Independent",
-     "Environment :: GPU :: NVIDIA CUDA"
+     "Operating System :: OS Independent"
 ]
 dependencies = [
     "torch",

inference_cli.py

@@ -36,7 +36,7 @@ def __init__(
         dtype: torch.dtype = torch.float32,
     ):
         # Create trailing timesteps with specified dtype
-        timesteps = torch.arange(1.0, 0.0, -1.0 / steps, device=device, dtype=dtype)
+        timesteps = torch.arange(1.0, 0.0, -1.0 / steps, device='cpu').to(device=device, dtype=dtype)
 
         # Shift timesteps.
         timesteps = shift * timesteps / (1 + (shift - 1) * timesteps)

pyproject.toml

@@ -21,6 +21,7 @@
 import torch
 import torch.distributed as dist
 from torch.nn.parallel import DistributedDataParallel
+from ...optimization.memory_manager import is_mps_available
 
 def get_global_rank() -> int:
     """
@@ -47,7 +48,7 @@ def get_device() -> torch.device:
     """
     Get current rank device.
     """
-    if hasattr(torch, 'mps') and callable(getattr(torch.mps, 'is_available', None)) and torch.mps.is_available():
+    if is_mps_available():
         return torch.device("mps")
     return torch.device("cuda", get_local_rank())
 

src/common/diffusion/timesteps/sampling/trailing.py

@@ -337,13 +337,23 @@ def edge_guided_alpha_upscale(
     rgb_edges = detect_edges_batch(images=rgb_normalized, method='sobel', debug=debug)
 
     # Step 1: Initial bicubic upscale provides smooth base before edge refinement
-    alpha_upscaled = F.interpolate(
-        input_alpha,
-        size=(H_out, W_out),
-        mode='bicubic',
-        align_corners=False,
-        antialias=True
-    ).clamp(0, 1)
+    # MPS on PyTorch < 2.8 doesn't support bicubic+antialias - use CPU fallback
+    try:
+        alpha_upscaled = F.interpolate(
+            input_alpha,
+            size=(H_out, W_out),
+            mode='bicubic',
+            align_corners=False,
+            antialias=True
+        ).clamp(0, 1)
+    except NotImplementedError:
+        alpha_upscaled = F.interpolate(
+            input_alpha.cpu(),
+            size=(H_out, W_out),
+            mode='bicubic',
+            align_corners=False,
+            antialias=True
+        ).to(device).clamp(0, 1)
 
     if is_binary_mask:
         if debug: