Merge branch 'master' into dr-support-pip-cm

README.md

@@ -294,6 +294,13 @@ For models compatible with Cambricon Extension for PyTorch (torch_mlu). Here's a
 2. Next, install the PyTorch(torch_mlu) following the instructions on the [Installation](https://www.cambricon.com/docs/sdk_1.15.0/cambricon_pytorch_1.17.0/user_guide_1.9/index.html)
 3. Launch ComfyUI by running `python main.py`
 
+#### Iluvatar Corex
+
+For models compatible with Iluvatar Extension for PyTorch. Here's a step-by-step guide tailored to your platform and installation method:
+
+1. Install the Iluvatar Corex Toolkit by adhering to the platform-specific instructions on the [Installation](https://support.iluvatar.com/#/DocumentCentre?id=1&nameCenter=2&productId=520117912052801536)
+2. Launch ComfyUI by running `python main.py`
+
 # Running
 
 ```python main.py```

app/frontend_management.py

@@ -29,18 +29,48 @@ def frontend_install_warning_message():
 This error is happening because the ComfyUI frontend is no longer shipped as part of the main repo but as a pip package instead.
 """.strip()
 
+def parse_version(version: str) -> tuple[int, int, int]:
+        return tuple(map(int, version.split(".")))
+
+def is_valid_version(version: str) -> bool:
+    """Validate if a string is a valid semantic version (X.Y.Z format)."""
+    pattern = r"^(\d+)\.(\d+)\.(\d+)$"
+    return bool(re.match(pattern, version))
+
+def get_installed_frontend_version():
+    """Get the currently installed frontend package version."""
+    frontend_version_str = version("comfyui-frontend-package")
+    return frontend_version_str
+
+def get_required_frontend_version():
+    """Get the required frontend version from requirements.txt."""
+    try:
+        with open(requirements_path, "r", encoding="utf-8") as f:
+            for line in f:
+                line = line.strip()
+                if line.startswith("comfyui-frontend-package=="):
+                    version_str = line.split("==")[-1]
+                    if not is_valid_version(version_str):
+                        logging.error(f"Invalid version format in requirements.txt: {version_str}")
+                        return None
+                    return version_str
+            logging.error("comfyui-frontend-package not found in requirements.txt")
+            return None
+    except FileNotFoundError:
+        logging.error("requirements.txt not found. Cannot determine required frontend version.")
+        return None
+    except Exception as e:
+        logging.error(f"Error reading requirements.txt: {e}")
+        return None
 
 def check_frontend_version():
     """Check if the frontend version is up to date."""
 
-    def parse_version(version: str) -> tuple[int, int, int]:
-        return tuple(map(int, version.split(".")))
-
     try:
-        frontend_version_str = version("comfyui-frontend-package")
+        frontend_version_str = get_installed_frontend_version()
         frontend_version = parse_version(frontend_version_str)
-        with open(requirements_path, "r", encoding="utf-8") as f:
-            required_frontend = parse_version(f.readline().split("=")[-1])
+        required_frontend_str = get_required_frontend_version()
+        required_frontend = parse_version(required_frontend_str)
         if frontend_version < required_frontend:
             app.logger.log_startup_warning(
                 f"""
@@ -168,6 +198,11 @@ def download_release_asset_zip(release: Release, destination_path: str) -> None:
 class FrontendManager:
     CUSTOM_FRONTENDS_ROOT = str(Path(__file__).parents[1] / "web_custom_versions")
 
+    @classmethod
+    def get_required_frontend_version(cls) -> str:
+        """Get the required frontend package version."""
+        return get_required_frontend_version()
+
     @classmethod
     def default_frontend_path(cls) -> str:
         try:

comfy/model_management.py

@@ -128,6 +128,11 @@ try:
 except:
     mlu_available = False
 
+try:
+    ixuca_available = hasattr(torch, "corex")
+except:
+    ixuca_available = False
+
 if args.cpu:
     cpu_state = CPUState.CPU
 
@@ -151,6 +156,12 @@ def is_mlu():
         return True
     return False
 
+def is_ixuca():
+    global ixuca_available
+    if ixuca_available:
+        return True
+    return False
+
 def get_torch_device():
     global directml_enabled
     global cpu_state
@@ -289,7 +300,7 @@ try:
         if torch_version_numeric[0] >= 2:
             if ENABLE_PYTORCH_ATTENTION == False and args.use_split_cross_attention == False and args.use_quad_cross_attention == False:
                 ENABLE_PYTORCH_ATTENTION = True
-    if is_intel_xpu() or is_ascend_npu() or is_mlu():
+    if is_intel_xpu() or is_ascend_npu() or is_mlu() or is_ixuca():
         if args.use_split_cross_attention == False and args.use_quad_cross_attention == False:
             ENABLE_PYTORCH_ATTENTION = True
 except:
@@ -381,6 +392,8 @@ def get_torch_device_name(device):
             except:
                 allocator_backend = ""
             return "{} {} : {}".format(device, torch.cuda.get_device_name(device), allocator_backend)
+        elif device.type == "xpu":
+            return "{} {}".format(device, torch.xpu.get_device_name(device))
         else:
             return "{}".format(device.type)
     elif is_intel_xpu():
@@ -1045,6 +1058,8 @@ def xformers_enabled():
         return False
     if is_mlu():
         return False
+    if is_ixuca():
+        return False
     if directml_enabled:
         return False
     return XFORMERS_IS_AVAILABLE
@@ -1080,6 +1095,8 @@ def pytorch_attention_flash_attention():
             return True
         if is_amd():
             return True #if you have pytorch attention enabled on AMD it probably supports at least mem efficient attention
+        if is_ixuca():
+            return True
     return False
 
 def force_upcast_attention_dtype():
@@ -1205,6 +1222,9 @@ def should_use_fp16(device=None, model_params=0, prioritize_performance=True, ma
     if is_mlu():
         return True
 
+    if is_ixuca():
+        return True
+
     if torch.version.hip:
         return True
 
@@ -1268,6 +1288,9 @@ def should_use_bf16(device=None, model_params=0, prioritize_performance=True, ma
     if is_ascend_npu():
         return True
 
+    if is_ixuca():
+        return True
+
     if is_amd():
         arch = torch.cuda.get_device_properties(device).gcnArchName
         if any((a in arch) for a in ["gfx1030", "gfx1031", "gfx1010", "gfx1011", "gfx1012", "gfx906", "gfx900", "gfx803"]):  # RDNA2 and older don't support bf16

comfy/utils.py

@@ -698,6 +698,26 @@ def resize_to_batch_size(tensor, batch_size):
 
     return output
 
+def resize_list_to_batch_size(l, batch_size):
+    in_batch_size = len(l)
+    if in_batch_size == batch_size or in_batch_size == 0:
+        return l
+
+    if batch_size <= 1:
+        return l[:batch_size]
+
+    output = []
+    if batch_size < in_batch_size:
+        scale = (in_batch_size - 1) / (batch_size - 1)
+        for i in range(batch_size):
+            output.append(l[min(round(i * scale), in_batch_size - 1)])
+    else:
+        scale = in_batch_size / batch_size
+        for i in range(batch_size):
+           output.append(l[min(math.floor((i + 0.5) * scale), in_batch_size - 1)])
+
+    return output
+
 def convert_sd_to(state_dict, dtype):
     keys = list(state_dict.keys())
     for k in keys:

comfy_extras/nodes_wan.py

@@ -1,3 +1,4 @@
+import math
 import nodes
 import node_helpers
 import torch
@@ -5,7 +6,9 @@ import comfy.model_management
 import comfy.utils
 import comfy.latent_formats
 import comfy.clip_vision
-
+import json
+import numpy as np
+from typing import Tuple
 
 class WanImageToVideo:
     @classmethod
@@ -383,7 +386,307 @@ class WanPhantomSubjectToVideo:
         out_latent["samples"] = latent
         return (positive, cond2, negative, out_latent)
 
+def parse_json_tracks(tracks):
+    """Parse JSON track data into a standardized format"""
+    tracks_data = []
+    try:
+        # If tracks is a string, try to parse it as JSON
+        if isinstance(tracks, str):
+            parsed = json.loads(tracks.replace("'", '"'))
+            tracks_data.extend(parsed)
+        else:
+            # If tracks is a list of strings, parse each one
+            for track_str in tracks:
+                parsed = json.loads(track_str.replace("'", '"'))
+                tracks_data.append(parsed)
+
+        # Check if we have a single track (dict with x,y) or a list of tracks
+        if tracks_data and isinstance(tracks_data[0], dict) and 'x' in tracks_data[0]:
+            # Single track detected, wrap it in a list
+            tracks_data = [tracks_data]
+        elif tracks_data and isinstance(tracks_data[0], list) and tracks_data[0] and isinstance(tracks_data[0][0], dict) and 'x' in tracks_data[0][0]:
+            # Already a list of tracks, nothing to do
+            pass
+        else:
+            # Unexpected format
+            pass
+
+    except json.JSONDecodeError:
+        tracks_data = []
+    return tracks_data
+
+def process_tracks(tracks_np: np.ndarray, frame_size: Tuple[int, int], num_frames, quant_multi: int = 8, **kwargs):
+    # tracks: shape [t, h, w, 3] => samples align with 24 fps, model trained with 16 fps.
+    # frame_size: tuple (W, H)
+    tracks = torch.from_numpy(tracks_np).float()
+
+    if tracks.shape[1] == 121:
+        tracks = torch.permute(tracks, (1, 0, 2, 3))
+
+    tracks, visibles = tracks[..., :2], tracks[..., 2:3]
+
+    short_edge = min(*frame_size)
+
+    frame_center = torch.tensor([*frame_size]).type_as(tracks) / 2
+    tracks = tracks - frame_center
+
+    tracks = tracks / short_edge * 2
+
+    visibles = visibles * 2 - 1
+
+    trange = torch.linspace(-1, 1, tracks.shape[0]).view(-1, 1, 1, 1).expand(*visibles.shape)
+
+    out_ = torch.cat([trange, tracks, visibles], dim=-1).view(121, -1, 4)
+
+    out_0 = out_[:1]
+
+    out_l = out_[1:] # 121 => 120 | 1
+    a = 120 // math.gcd(120, num_frames)
+    b = num_frames // math.gcd(120, num_frames)
+    out_l = torch.repeat_interleave(out_l, b, dim=0)[1::a]  # 120 => 120 * b => 120 * b / a == F
+
+    final_result = torch.cat([out_0, out_l], dim=0)
+
+    return final_result
+
+FIXED_LENGTH = 121
+def pad_pts(tr):
+    """Convert list of {x,y} to (FIXED_LENGTH,1,3) array, padding/truncating."""
+    pts = np.array([[p['x'], p['y'], 1] for p in tr], dtype=np.float32)
+    n = pts.shape[0]
+    if n < FIXED_LENGTH:
+        pad = np.zeros((FIXED_LENGTH - n, 3), dtype=np.float32)
+        pts = np.vstack((pts, pad))
+    else:
+        pts = pts[:FIXED_LENGTH]
+    return pts.reshape(FIXED_LENGTH, 1, 3)
+
+def ind_sel(target: torch.Tensor, ind: torch.Tensor, dim: int = 1):
+    """Index selection utility function"""
+    assert (
+        len(ind.shape) > dim
+    ), "Index must have the target dim, but get dim: %d, ind shape: %s" % (dim, str(ind.shape))
+
+    target = target.expand(
+        *tuple(
+            [ind.shape[k] if target.shape[k] == 1 else -1 for k in range(dim)]
+            + [
+                -1,
+            ]
+            * (len(target.shape) - dim)
+        )
+    )
+
+    ind_pad = ind
+
+    if len(target.shape) > dim + 1:
+        for _ in range(len(target.shape) - (dim + 1)):
+            ind_pad = ind_pad.unsqueeze(-1)
+        ind_pad = ind_pad.expand(*(-1,) * (dim + 1), *target.shape[(dim + 1) : :])
+
+    return torch.gather(target, dim=dim, index=ind_pad)
+
+def merge_final(vert_attr: torch.Tensor, weight: torch.Tensor, vert_assign: torch.Tensor):
+    """Merge vertex attributes with weights"""
+    target_dim = len(vert_assign.shape) - 1
+    if len(vert_attr.shape) == 2:
+        assert vert_attr.shape[0] > vert_assign.max()
+        new_shape = [1] * target_dim + list(vert_attr.shape)
+        tensor = vert_attr.reshape(new_shape)
+        sel_attr = ind_sel(tensor, vert_assign.type(torch.long), dim=target_dim)
+    else:
+        assert vert_attr.shape[1] > vert_assign.max()
+        new_shape = [vert_attr.shape[0]] + [1] * (target_dim - 1) + list(vert_attr.shape[1:])
+        tensor = vert_attr.reshape(new_shape)
+        sel_attr = ind_sel(tensor, vert_assign.type(torch.long), dim=target_dim)
+
+    final_attr = torch.sum(sel_attr * weight.unsqueeze(-1), dim=-2)
+    return final_attr
+
+
+def _patch_motion_single(
+    tracks: torch.FloatTensor,  # (B, T, N, 4)
+    vid: torch.FloatTensor,     # (C, T, H, W)
+    temperature: float,
+    vae_divide: tuple,
+    topk: int,
+):
+    """Apply motion patching based on tracks"""
+    _, T, H, W = vid.shape
+    N = tracks.shape[2]
+    _, tracks_xy, visible = torch.split(
+        tracks, [1, 2, 1], dim=-1
+    )  # (B, T, N, 2) | (B, T, N, 1)
+    tracks_n = tracks_xy / torch.tensor([W / min(H, W), H / min(H, W)], device=tracks_xy.device)
+    tracks_n = tracks_n.clamp(-1, 1)
+    visible = visible.clamp(0, 1)
+
+    xx = torch.linspace(-W / min(H, W), W / min(H, W), W)
+    yy = torch.linspace(-H / min(H, W), H / min(H, W), H)
+
+    grid = torch.stack(torch.meshgrid(yy, xx, indexing="ij")[::-1], dim=-1).to(
+        tracks_xy.device
+    )
+
+    tracks_pad = tracks_xy[:, 1:]
+    visible_pad = visible[:, 1:]
+
+    visible_align = visible_pad.view(T - 1, 4, *visible_pad.shape[2:]).sum(1)
+    tracks_align = (tracks_pad * visible_pad).view(T - 1, 4, *tracks_pad.shape[2:]).sum(
+        1
+    ) / (visible_align + 1e-5)
+    dist_ = (
+        (tracks_align[:, None, None] - grid[None, :, :, None]).pow(2).sum(-1)
+    )  # T, H, W, N
+    weight = torch.exp(-dist_ * temperature) * visible_align.clamp(0, 1).view(
+        T - 1, 1, 1, N
+    )
+    vert_weight, vert_index = torch.topk(
+        weight, k=min(topk, weight.shape[-1]), dim=-1
+    )
+
+    grid_mode = "bilinear"
+    point_feature = torch.nn.functional.grid_sample(
+        vid.permute(1, 0, 2, 3)[:1],
+        tracks_n[:, :1].type(vid.dtype),
+        mode=grid_mode,
+        padding_mode="zeros",
+        align_corners=False,
+    )
+    point_feature = point_feature.squeeze(0).squeeze(1).permute(1, 0) # N, C=16
+
+    out_feature = merge_final(point_feature, vert_weight, vert_index).permute(3, 0, 1, 2) # T - 1, H, W, C => C, T - 1, H, W
+    out_weight = vert_weight.sum(-1) # T - 1, H, W
+
+    # out feature -> already soft weighted
+    mix_feature = out_feature + vid[:, 1:] * (1 - out_weight.clamp(0, 1))
+
+    out_feature_full = torch.cat([vid[:, :1], mix_feature], dim=1) # C, T, H, W
+    out_mask_full = torch.cat([torch.ones_like(out_weight[:1]), out_weight], dim=0)  # T, H, W
+
+    return out_mask_full[None].expand(vae_divide[0], -1, -1, -1), out_feature_full
+
+
+def patch_motion(
+    tracks: torch.FloatTensor,  # (B, TB, T, N, 4)
+    vid: torch.FloatTensor,     # (C, T, H, W)
+    temperature: float = 220.0,
+    vae_divide: tuple = (4, 16),
+    topk: int = 2,
+):
+    B = len(tracks)
+
+    # Process each batch separately
+    out_masks = []
+    out_features = []
+
+    for b in range(B):
+        mask, feature = _patch_motion_single(
+            tracks[b],  # (T, N, 4)
+            vid[b],        # (C, T, H, W)
+            temperature,
+            vae_divide,
+            topk
+        )
+        out_masks.append(mask)
+        out_features.append(feature)
+
+    # Stack results: (B, C, T, H, W)
+    out_mask_full = torch.stack(out_masks, dim=0)
+    out_feature_full = torch.stack(out_features, dim=0)
+
+    return out_mask_full, out_feature_full
+
+class WanTrackToVideo:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+                    "positive": ("CONDITIONING", ),
+                    "negative": ("CONDITIONING", ),
+                    "vae": ("VAE", ),
+                    "tracks": ("STRING", {"multiline": True, "default": "[]"}),
+                    "width": ("INT", {"default": 832, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
+                    "height": ("INT", {"default": 480, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
+                    "length": ("INT", {"default": 81, "min": 1, "max": nodes.MAX_RESOLUTION, "step": 4}),
+                    "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
+                    "temperature": ("FLOAT", {"default": 220.0, "min": 1.0, "max": 1000.0, "step": 0.1}),
+                    "topk": ("INT", {"default": 2, "min": 1, "max": 10}),
+                    "start_image": ("IMAGE", ),
+                },
+                "optional": {
+                    "clip_vision_output": ("CLIP_VISION_OUTPUT", ),
+                }}
+
+    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
+    RETURN_NAMES = ("positive", "negative", "latent")
+    FUNCTION = "encode"
+
+    CATEGORY = "conditioning/video_models"
+
+    def encode(self, positive, negative, vae, tracks, width, height, length, batch_size,
+               temperature, topk, start_image=None, clip_vision_output=None):
+
+        tracks_data = parse_json_tracks(tracks)
+
+        if not tracks_data:
+            return WanImageToVideo().encode(positive, negative, vae, width, height, length, batch_size, start_image=start_image, clip_vision_output=clip_vision_output)
+
+        latent = torch.zeros([batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8],
+                           device=comfy.model_management.intermediate_device())
+
+        if isinstance(tracks_data[0][0], dict):
+            tracks_data = [tracks_data]
+
+        processed_tracks = []
+        for batch in tracks_data:
+            arrs = []
+            for track in batch:
+                pts = pad_pts(track)
+                arrs.append(pts)
+
+            tracks_np = np.stack(arrs, axis=0)
+            processed_tracks.append(process_tracks(tracks_np, (width, height), length - 1).unsqueeze(0))
+
+        if start_image is not None:
+            start_image = comfy.utils.common_upscale(start_image[:batch_size].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
+            videos = torch.ones((start_image.shape[0], length, height, width, start_image.shape[-1]), device=start_image.device, dtype=start_image.dtype) * 0.5
+            for i in range(start_image.shape[0]):
+                videos[i, 0] = start_image[i]
+
+            latent_videos = []
+            videos = comfy.utils.resize_to_batch_size(videos, batch_size)
+            for i in range(batch_size):
+                latent_videos += [vae.encode(videos[i, :, :, :, :3])]
+            y = torch.cat(latent_videos, dim=0)
+
+            # Scale latent since patch_motion is non-linear
+            y = comfy.latent_formats.Wan21().process_in(y)
+
+            processed_tracks = comfy.utils.resize_list_to_batch_size(processed_tracks, batch_size)
+            res = patch_motion(
+                processed_tracks, y, temperature=temperature, topk=topk, vae_divide=(4, 16)
+            )
+
+            mask, concat_latent_image = res
+            concat_latent_image = comfy.latent_formats.Wan21().process_out(concat_latent_image)
+            mask = -mask + 1.0  # Invert mask to match expected format
+            positive = node_helpers.conditioning_set_values(positive,
+                                                            {"concat_mask": mask,
+                                                            "concat_latent_image": concat_latent_image})
+            negative = node_helpers.conditioning_set_values(negative,
+                                                            {"concat_mask": mask,
+                                                            "concat_latent_image": concat_latent_image})
+
+        if clip_vision_output is not None:
+            positive = node_helpers.conditioning_set_values(positive, {"clip_vision_output": clip_vision_output})
+            negative = node_helpers.conditioning_set_values(negative, {"clip_vision_output": clip_vision_output})
+
+        out_latent = {}
+        out_latent["samples"] = latent
+        return (positive, negative, out_latent)
+
 NODE_CLASS_MAPPINGS = {
+    "WanTrackToVideo": WanTrackToVideo,
     "WanImageToVideo": WanImageToVideo,
     "WanFunControlToVideo": WanFunControlToVideo,
     "WanFunInpaintToVideo": WanFunInpaintToVideo,

server.py

@@ -559,6 +559,7 @@ class PromptServer():
             ram_free = comfy.model_management.get_free_memory(cpu_device)
             vram_total, torch_vram_total = comfy.model_management.get_total_memory(device, torch_total_too=True)
             vram_free, torch_vram_free = comfy.model_management.get_free_memory(device, torch_free_too=True)
+            required_frontend_version = FrontendManager.get_required_frontend_version()
 
             system_stats = {
                 "system": {
@@ -566,6 +567,7 @@ class PromptServer():
                     "ram_total": ram_total,
                     "ram_free": ram_free,
                     "comfyui_version": __version__,
+                    "required_frontend_version": required_frontend_version,
                     "python_version": sys.version,
                     "pytorch_version": comfy.model_management.torch_version,
                     "embedded_python": os.path.split(os.path.split(sys.executable)[0])[1] == "python_embeded",

tests-unit/app_test/frontend_manager_test.py

@@ -1,7 +1,7 @@
 import argparse
 import pytest
 from requests.exceptions import HTTPError
-from unittest.mock import patch
+from unittest.mock import patch, mock_open
 
 from app.frontend_management import (
     FrontendManager,
@@ -172,3 +172,36 @@ def test_init_frontend_fallback_on_error():
     # Assert
     assert frontend_path == "/default/path"
     mock_check.assert_called_once()
+
+
+def test_get_frontend_version():
+    # Arrange
+    expected_version = "1.25.0"
+    mock_requirements_content = """torch
+torchsde
+comfyui-frontend-package==1.25.0
+other-package==1.0.0
+numpy"""
+
+    # Act
+    with patch("builtins.open", mock_open(read_data=mock_requirements_content)):
+        version = FrontendManager.get_required_frontend_version()
+
+    # Assert
+    assert version == expected_version
+
+
+def test_get_frontend_version_invalid_semver():
+    # Arrange
+    mock_requirements_content = """torch
+torchsde
+comfyui-frontend-package==1.29.3.75
+other-package==1.0.0
+numpy"""
+
+    # Act
+    with patch("builtins.open", mock_open(read_data=mock_requirements_content)):
+        version = FrontendManager.get_required_frontend_version()
+
+    # Assert
+    assert version is None