Merge 7c595586dd into 22ad513c72

* add dependency aware cache that removed a cached node as soon as all of its decendents have executed. This allows users with lower RAM to run workflows they would otherwise not be able to run. The downside is that every workflow will fully run each time even if no nodes have changed.

* remove test code

* tidy code

comfy/cli_args.py

@@ -101,6 +101,7 @@ parser.add_argument("--preview-size", type=int, default=512, help="Sets the maxi
 cache_group = parser.add_mutually_exclusive_group()
 cache_group.add_argument("--cache-classic", action="store_true", help="Use the old style (aggressive) caching.")
 cache_group.add_argument("--cache-lru", type=int, default=0, help="Use LRU caching with a maximum of N node results cached. May use more RAM/VRAM.")
+cache_group.add_argument("--cache-none", action="store_true", help="Reduced RAM/VRAM usage at the expense of executing every node for each run.")
 
 attn_group = parser.add_mutually_exclusive_group()
 attn_group.add_argument("--use-split-cross-attention", action="store_true", help="Use the split cross attention optimization. Ignored when xformers is used.")

comfy/comfy_types/node_typing.py

@@ -102,9 +102,13 @@ class InputTypeOptions(TypedDict):
     default: bool | str | float | int | list | tuple
     """The default value of the widget"""
     defaultInput: bool
-    """Defaults to an input slot rather than a widget"""
+    """@deprecated in v1.16 frontend. v1.16 frontend allows input socket and widget to co-exist.
+    - defaultInput on required inputs should be dropped.
+    - defaultInput on optional inputs should be replaced with forceInput.
+    Ref: https://github.com/Comfy-Org/ComfyUI_frontend/pull/3364
+    """
     forceInput: bool
-    """`defaultInput` and also don't allow converting to a widget"""
+    """Forces the input to be an input slot rather than a widget even a widget is available for the input type."""
     lazy: bool
     """Declares that this input uses lazy evaluation"""
     rawLink: bool

comfy/patcher_extension.py

@@ -48,6 +48,7 @@ def get_all_callbacks(call_type: str, transformer_options: dict, is_model_option
 
 class WrappersMP:
     OUTER_SAMPLE = "outer_sample"
+    PREPARE_SAMPLING = "prepare_sampling"
     SAMPLER_SAMPLE = "sampler_sample"
     CALC_COND_BATCH = "calc_cond_batch"
     APPLY_MODEL = "apply_model"

comfy/sampler_helpers.py

@@ -106,6 +106,13 @@ def cleanup_additional_models(models):
 
 
 def prepare_sampling(model: ModelPatcher, noise_shape, conds, model_options=None):
+    executor = comfy.patcher_extension.WrapperExecutor.new_executor(
+        _prepare_sampling,
+        comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.PREPARE_SAMPLING, model_options, is_model_options=True)
+    )
+    return executor.execute(model, noise_shape, conds, model_options=model_options)
+
+def _prepare_sampling(model: ModelPatcher, noise_shape, conds, model_options=None):
     real_model: BaseModel = None
     models, inference_memory = get_additional_models(conds, model.model_dtype())
     models += get_additional_models_from_model_options(model_options)

comfy_execution/caching.py

@@ -316,3 +316,156 @@ class LRUCache(BasicCache):
             self.children[cache_key].append(self.cache_key_set.get_data_key(child_id))
         return self
 
+
+class DependencyAwareCache(BasicCache):
+    """
+    A cache implementation that tracks dependencies between nodes and manages
+    their execution and caching accordingly. It extends the BasicCache class.
+    Nodes are removed from this cache once all of their descendants have been
+    executed.
+    """
+
+    def __init__(self, key_class):
+        """
+        Initialize the DependencyAwareCache.
+
+        Args:
+            key_class: The class used for generating cache keys.
+        """
+        super().__init__(key_class)
+        self.descendants = {}  # Maps node_id -> set of descendant node_ids
+        self.ancestors = {}    # Maps node_id -> set of ancestor node_ids
+        self.executed_nodes = set()  # Tracks nodes that have been executed
+
+    def set_prompt(self, dynprompt, node_ids, is_changed_cache):
+        """
+        Clear the entire cache and rebuild the dependency graph.
+
+        Args:
+            dynprompt: The dynamic prompt object containing node information.
+            node_ids: List of node IDs to initialize the cache for.
+            is_changed_cache: Flag indicating if the cache has changed.
+        """
+        # Clear all existing cache data
+        self.cache.clear()
+        self.subcaches.clear()
+        self.descendants.clear()
+        self.ancestors.clear()
+        self.executed_nodes.clear()
+
+        # Call the parent method to initialize the cache with the new prompt
+        super().set_prompt(dynprompt, node_ids, is_changed_cache)
+
+        # Rebuild the dependency graph
+        self._build_dependency_graph(dynprompt, node_ids)
+
+    def _build_dependency_graph(self, dynprompt, node_ids):
+        """
+        Build the dependency graph for all nodes.
+
+        Args:
+            dynprompt: The dynamic prompt object containing node information.
+            node_ids: List of node IDs to build the graph for.
+        """
+        self.descendants.clear()
+        self.ancestors.clear()
+        for node_id in node_ids:
+            self.descendants[node_id] = set()
+            self.ancestors[node_id] = set()
+
+        for node_id in node_ids:
+            inputs = dynprompt.get_node(node_id)["inputs"]
+            for input_data in inputs.values():
+                if is_link(input_data):  # Check if the input is a link to another node
+                    ancestor_id = input_data[0]
+                    self.descendants[ancestor_id].add(node_id)
+                    self.ancestors[node_id].add(ancestor_id)
+
+    def set(self, node_id, value):
+        """
+        Mark a node as executed and store its value in the cache.
+
+        Args:
+            node_id: The ID of the node to store.
+            value: The value to store for the node.
+        """
+        self._set_immediate(node_id, value)
+        self.executed_nodes.add(node_id)
+        self._cleanup_ancestors(node_id)
+
+    def get(self, node_id):
+        """
+        Retrieve the cached value for a node.
+
+        Args:
+            node_id: The ID of the node to retrieve.
+
+        Returns:
+            The cached value for the node.
+        """
+        return self._get_immediate(node_id)
+
+    def ensure_subcache_for(self, node_id, children_ids):
+        """
+        Ensure a subcache exists for a node and update dependencies.
+
+        Args:
+            node_id: The ID of the parent node.
+            children_ids: List of child node IDs to associate with the parent node.
+
+        Returns:
+            The subcache object for the node.
+        """
+        subcache = super()._ensure_subcache(node_id, children_ids)
+        for child_id in children_ids:
+            self.descendants[node_id].add(child_id)
+            self.ancestors[child_id].add(node_id)
+        return subcache
+
+    def _cleanup_ancestors(self, node_id):
+        """
+        Check if ancestors of a node can be removed from the cache.
+
+        Args:
+            node_id: The ID of the node whose ancestors are to be checked.
+        """
+        for ancestor_id in self.ancestors.get(node_id, []):
+            if ancestor_id in self.executed_nodes:
+                # Remove ancestor if all its descendants have been executed
+                if all(descendant in self.executed_nodes for descendant in self.descendants[ancestor_id]):
+                    self._remove_node(ancestor_id)
+
+    def _remove_node(self, node_id):
+        """
+        Remove a node from the cache.
+
+        Args:
+            node_id: The ID of the node to remove.
+        """
+        cache_key = self.cache_key_set.get_data_key(node_id)
+        if cache_key in self.cache:
+            del self.cache[cache_key]
+        subcache_key = self.cache_key_set.get_subcache_key(node_id)
+        if subcache_key in self.subcaches:
+            del self.subcaches[subcache_key]
+
+    def clean_unused(self):
+        """
+        Clean up unused nodes. This is a no-op for this cache implementation.
+        """
+        pass
+
+    def recursive_debug_dump(self):
+        """
+        Dump the cache and dependency graph for debugging.
+
+        Returns:
+            A list containing the cache state and dependency graph.
+        """
+        result = super().recursive_debug_dump()
+        result.append({
+            "descendants": self.descendants,
+            "ancestors": self.ancestors,
+            "executed_nodes": list(self.executed_nodes),
+        })
+        return result

comfy_extras/nodes_hunyuan3d.py

@@ -209,6 +209,196 @@ def voxel_to_mesh(voxels, threshold=0.5, device=None):
     vertices = torch.fliplr(vertices)
     return vertices, faces
 
+def voxel_to_mesh_surfnet(voxels, threshold=0.5, device=None):
+    if device is None:
+        device = torch.device("cpu")
+    voxels = voxels.to(device)
+
+    D, H, W = voxels.shape
+
+    padded = torch.nn.functional.pad(voxels, (1, 1, 1, 1, 1, 1), 'constant', 0)
+    z, y, x = torch.meshgrid(
+        torch.arange(D, device=device),
+        torch.arange(H, device=device),
+        torch.arange(W, device=device),
+        indexing='ij'
+    )
+    cell_positions = torch.stack([z.flatten(), y.flatten(), x.flatten()], dim=1)
+
+    corner_offsets = torch.tensor([
+        [0, 0, 0], [1, 0, 0], [0, 1, 0], [1, 1, 0],
+        [0, 0, 1], [1, 0, 1], [0, 1, 1], [1, 1, 1]
+    ], device=device)
+
+    corner_values = torch.zeros((cell_positions.shape[0], 8), device=device)
+    for c, (dz, dy, dx) in enumerate(corner_offsets):
+        corner_values[:, c] = padded[
+            cell_positions[:, 0] + dz,
+            cell_positions[:, 1] + dy,
+            cell_positions[:, 2] + dx
+        ]
+
+    corner_signs = corner_values > threshold
+    has_inside = torch.any(corner_signs, dim=1)
+    has_outside = torch.any(~corner_signs, dim=1)
+    contains_surface = has_inside & has_outside
+
+    active_cells = cell_positions[contains_surface]
+    active_signs = corner_signs[contains_surface]
+    active_values = corner_values[contains_surface]
+
+    if active_cells.shape[0] == 0:
+        return torch.zeros((0, 3), device=device), torch.zeros((0, 3), dtype=torch.long, device=device)
+
+    edges = torch.tensor([
+        [0, 1], [0, 2], [0, 4], [1, 3],
+        [1, 5], [2, 3], [2, 6], [3, 7],
+        [4, 5], [4, 6], [5, 7], [6, 7]
+    ], device=device)
+
+    cell_vertices = {}
+    progress = comfy.utils.ProgressBar(100)
+
+    for edge_idx, (e1, e2) in enumerate(edges):
+        progress.update(1)
+        crossing = active_signs[:, e1] != active_signs[:, e2]
+        if not crossing.any():
+            continue
+
+        cell_indices = torch.nonzero(crossing, as_tuple=True)[0]
+
+        v1 = active_values[cell_indices, e1]
+        v2 = active_values[cell_indices, e2]
+
+        t = torch.zeros_like(v1, device=device)
+        denom = v2 - v1
+        valid = denom != 0
+        t[valid] = (threshold - v1[valid]) / denom[valid]
+        t[~valid] = 0.5
+
+        p1 = corner_offsets[e1].float()
+        p2 = corner_offsets[e2].float()
+
+        intersection = p1.unsqueeze(0) + t.unsqueeze(1) * (p2.unsqueeze(0) - p1.unsqueeze(0))
+
+        for i, point in zip(cell_indices.tolist(), intersection):
+            if i not in cell_vertices:
+                cell_vertices[i] = []
+            cell_vertices[i].append(point)
+
+    # Calculate the final vertices as the average of intersection points for each cell
+    vertices = []
+    vertex_lookup = {}
+
+    vert_progress_mod = round(len(cell_vertices)/50)
+
+    for i, points in cell_vertices.items():
+        if not i % vert_progress_mod:
+            progress.update(1)
+
+        if points:
+            vertex = torch.stack(points).mean(dim=0)
+            vertex = vertex + active_cells[i].float()
+            vertex_lookup[tuple(active_cells[i].tolist())] = len(vertices)
+            vertices.append(vertex)
+
+    if not vertices:
+        return torch.zeros((0, 3), device=device), torch.zeros((0, 3), dtype=torch.long, device=device)
+
+    final_vertices = torch.stack(vertices)
+
+    inside_corners_mask = active_signs
+    outside_corners_mask = ~active_signs
+
+    inside_counts = inside_corners_mask.sum(dim=1, keepdim=True).float()
+    outside_counts = outside_corners_mask.sum(dim=1, keepdim=True).float()
+
+    inside_pos = torch.zeros((active_cells.shape[0], 3), device=device)
+    outside_pos = torch.zeros((active_cells.shape[0], 3), device=device)
+
+    for i in range(8):
+        mask_inside = inside_corners_mask[:, i].unsqueeze(1)
+        mask_outside = outside_corners_mask[:, i].unsqueeze(1)
+        inside_pos += corner_offsets[i].float().unsqueeze(0) * mask_inside
+        outside_pos += corner_offsets[i].float().unsqueeze(0) * mask_outside
+
+    inside_pos /= inside_counts
+    outside_pos /= outside_counts
+    gradients = inside_pos - outside_pos
+
+    pos_dirs = torch.tensor([
+        [1, 0, 0],
+        [0, 1, 0],
+        [0, 0, 1]
+    ], device=device)
+
+    cross_products = [
+        torch.linalg.cross(pos_dirs[i].float(), pos_dirs[j].float())
+        for i in range(3) for j in range(i+1, 3)
+    ]
+
+    faces = []
+    all_keys = set(vertex_lookup.keys())
+
+    face_progress_mod = round(len(active_cells)/38*3)
+
+    for pair_idx, (i, j) in enumerate([(0,1), (0,2), (1,2)]):
+        dir_i = pos_dirs[i]
+        dir_j = pos_dirs[j]
+        cross_product = cross_products[pair_idx]
+
+        ni_positions = active_cells + dir_i
+        nj_positions = active_cells + dir_j
+        diag_positions = active_cells + dir_i + dir_j
+
+        alignments = torch.matmul(gradients, cross_product)
+
+        valid_quads = []
+        quad_indices = []
+
+        for idx, active_cell in enumerate(active_cells):
+            if not idx % face_progress_mod:
+                progress.update(1)
+            cell_key = tuple(active_cell.tolist())
+            ni_key = tuple(ni_positions[idx].tolist())
+            nj_key = tuple(nj_positions[idx].tolist())
+            diag_key = tuple(diag_positions[idx].tolist())
+
+            if cell_key in all_keys and ni_key in all_keys and nj_key in all_keys and diag_key in all_keys:
+                v0 = vertex_lookup[cell_key]
+                v1 = vertex_lookup[ni_key]
+                v2 = vertex_lookup[nj_key]
+                v3 = vertex_lookup[diag_key]
+
+                valid_quads.append((v0, v1, v2, v3))
+                quad_indices.append(idx)
+
+        for q_idx, (v0, v1, v2, v3) in enumerate(valid_quads):
+            cell_idx = quad_indices[q_idx]
+            if alignments[cell_idx] > 0:
+                faces.append(torch.tensor([v0, v1, v3], device=device, dtype=torch.long))
+                faces.append(torch.tensor([v0, v3, v2], device=device, dtype=torch.long))
+            else:
+                faces.append(torch.tensor([v0, v3, v1], device=device, dtype=torch.long))
+                faces.append(torch.tensor([v0, v2, v3], device=device, dtype=torch.long))
+
+    if faces:
+        faces = torch.stack(faces)
+    else:
+        faces = torch.zeros((0, 3), dtype=torch.long, device=device)
+
+    v_min = 0
+    v_max = max(D, H, W)
+
+    final_vertices = final_vertices - (v_min + v_max) / 2
+
+    scale = (v_max - v_min) / 2
+    if scale > 0:
+        final_vertices = final_vertices / scale
+
+    final_vertices = torch.fliplr(final_vertices)
+
+    return final_vertices, faces
 
 class MESH:
     def __init__(self, vertices, faces):
@@ -237,6 +427,34 @@ class VoxelToMeshBasic:
 
         return (MESH(torch.stack(vertices), torch.stack(faces)), )
 
+class VoxelToMesh:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {"voxel": ("VOXEL", ),
+                             "algorithm": (["surface net", "basic"], ),
+                             "threshold": ("FLOAT", {"default": 0.6, "min": -1.0, "max": 1.0, "step": 0.01}),
+                             }}
+    RETURN_TYPES = ("MESH",)
+    FUNCTION = "decode"
+
+    CATEGORY = "3d"
+
+    def decode(self, voxel, algorithm, threshold):
+        vertices = []
+        faces = []
+
+        if algorithm == "basic":
+            mesh_function = voxel_to_mesh
+        elif algorithm == "surface net":
+            mesh_function = voxel_to_mesh_surfnet
+
+        for x in voxel.data:
+            v, f = mesh_function(x, threshold=threshold, device=None)
+            vertices.append(v)
+            faces.append(f)
+
+        return (MESH(torch.stack(vertices), torch.stack(faces)), )
+
 
 def save_glb(vertices, faces, filepath, metadata=None):
     """
@@ -411,5 +629,6 @@ NODE_CLASS_MAPPINGS = {
     "Hunyuan3Dv2ConditioningMultiView": Hunyuan3Dv2ConditioningMultiView,
     "VAEDecodeHunyuan3D": VAEDecodeHunyuan3D,
     "VoxelToMeshBasic": VoxelToMeshBasic,
+    "VoxelToMesh": VoxelToMesh,
     "SaveGLB": SaveGLB,
 }

execution.py

@@ -15,7 +15,7 @@ import nodes
 import comfy.model_management
 from comfy_execution.graph import get_input_info, ExecutionList, DynamicPrompt, ExecutionBlocker
 from comfy_execution.graph_utils import is_link, GraphBuilder
-from comfy_execution.caching import HierarchicalCache, LRUCache, CacheKeySetInputSignature, CacheKeySetID
+from comfy_execution.caching import HierarchicalCache, LRUCache, DependencyAwareCache, CacheKeySetInputSignature, CacheKeySetID
 from comfy_execution.validation import validate_node_input
 
 class ExecutionResult(Enum):
@@ -59,20 +59,27 @@ class IsChangedCache:
             self.is_changed[node_id] = node["is_changed"]
         return self.is_changed[node_id]
 
-class CacheSet:
-    def __init__(self, lru_size=None):
-        if lru_size is None or lru_size == 0:
-            self.init_classic_cache()
-        else:
-            self.init_lru_cache(lru_size)
-        self.all = [self.outputs, self.ui, self.objects]
 
-    # Useful for those with ample RAM/VRAM -- allows experimenting without
+class CacheType(Enum):
-    # blowing away the cache every time
+    CLASSIC = 0
-    def init_lru_cache(self, cache_size):
+    LRU = 1
-        self.outputs = LRUCache(CacheKeySetInputSignature, max_size=cache_size)
+    DEPENDENCY_AWARE = 2
-        self.ui = LRUCache(CacheKeySetInputSignature, max_size=cache_size)
+
-        self.objects = HierarchicalCache(CacheKeySetID)
+
+class CacheSet:
+    def __init__(self, cache_type=None, cache_size=None):
+        if cache_type == CacheType.DEPENDENCY_AWARE:
+            self.init_dependency_aware_cache()
+            logging.info("Disabling intermediate node cache.")
+        elif cache_type == CacheType.LRU:
+            if cache_size is None:
+                cache_size = 0
+            self.init_lru_cache(cache_size)
+            logging.info("Using LRU cache")
+        else:
+            self.init_classic_cache()
+
+        self.all = [self.outputs, self.ui, self.objects]
 
     # Performs like the old cache -- dump data ASAP
     def init_classic_cache(self):
@@ -80,6 +87,17 @@ class CacheSet:
         self.ui = HierarchicalCache(CacheKeySetInputSignature)
         self.objects = HierarchicalCache(CacheKeySetID)
 
+    def init_lru_cache(self, cache_size):
+        self.outputs = LRUCache(CacheKeySetInputSignature, max_size=cache_size)
+        self.ui = LRUCache(CacheKeySetInputSignature, max_size=cache_size)
+        self.objects = HierarchicalCache(CacheKeySetID)
+
+    # only hold cached items while the decendents have not executed
+    def init_dependency_aware_cache(self):
+        self.outputs = DependencyAwareCache(CacheKeySetInputSignature)
+        self.ui = DependencyAwareCache(CacheKeySetInputSignature)
+        self.objects = DependencyAwareCache(CacheKeySetID)
+
     def recursive_debug_dump(self):
         result = {
             "outputs": self.outputs.recursive_debug_dump(),
@@ -414,13 +432,14 @@ def execute(server, dynprompt, caches, current_item, extra_data, executed, promp
     return (ExecutionResult.SUCCESS, None, None)
 
 class PromptExecutor:
-    def __init__(self, server, lru_size=None):
+    def __init__(self, server, cache_type=False, cache_size=None):
-        self.lru_size = lru_size
+        self.cache_size = cache_size
+        self.cache_type = cache_type
         self.server = server
         self.reset()
 
     def reset(self):
-        self.caches = CacheSet(self.lru_size)
+        self.caches = CacheSet(cache_type=self.cache_type, cache_size=self.cache_size)
         self.status_messages = []
         self.success = True
 
@@ -775,7 +794,7 @@ def validate_prompt(prompt):
                 "details": f"Node ID '#{x}'",
                 "extra_info": {}
             }
-            return (False, error, [], [])
+            return (False, error, [], {})
 
         class_type = prompt[x]['class_type']
         class_ = nodes.NODE_CLASS_MAPPINGS.get(class_type, None)
@@ -786,7 +805,7 @@ def validate_prompt(prompt):
                 "details": f"Node ID '#{x}'",
                 "extra_info": {}
             }
-            return (False, error, [], [])
+            return (False, error, [], {})
 
         if hasattr(class_, 'OUTPUT_NODE') and class_.OUTPUT_NODE is True:
             outputs.add(x)
@@ -798,7 +817,7 @@ def validate_prompt(prompt):
             "details": "",
             "extra_info": {}
         }
-        return (False, error, [], [])
+        return (False, error, [], {})
 
     good_outputs = set()
     errors = []

main.py

@@ -156,7 +156,13 @@ def cuda_malloc_warning():
 
 def prompt_worker(q, server_instance):
     current_time: float = 0.0
-    e = execution.PromptExecutor(server_instance, lru_size=args.cache_lru)
+    cache_type = execution.CacheType.CLASSIC
+    if args.cache_lru > 0:
+        cache_type = execution.CacheType.LRU
+    elif args.cache_none:
+        cache_type = execution.CacheType.DEPENDENCY_AWARE
+
+    e = execution.PromptExecutor(server_instance, cache_type=cache_type, cache_size=args.cache_lru)
     last_gc_collect = 0
     need_gc = False
     gc_collect_interval = 10.0

nodes.py

@@ -786,6 +786,8 @@ class ControlNetLoader:
     def load_controlnet(self, control_net_name):
         controlnet_path = folder_paths.get_full_path_or_raise("controlnet", control_net_name)
         controlnet = comfy.controlnet.load_controlnet(controlnet_path)
+        if controlnet is None:
+            raise RuntimeError("ERROR: controlnet file is invalid and does not contain a valid controlnet model.")
         return (controlnet,)
 
 class DiffControlNetLoader:
@@ -1690,6 +1692,9 @@ class LoadImage:
             if 'A' in i.getbands():
                 mask = np.array(i.getchannel('A')).astype(np.float32) / 255.0
                 mask = 1. - torch.from_numpy(mask)
+            elif i.mode == 'P' and 'transparency' in i.info:
+                mask = np.array(i.convert('RGBA').getchannel('A')).astype(np.float32) / 255.0
+                mask = 1. - torch.from_numpy(mask)
             else:
                 mask = torch.zeros((64,64), dtype=torch.float32, device="cpu")
             output_images.append(image)
@@ -2125,21 +2130,25 @@ def get_module_name(module_path: str) -> str:
 
 
 def load_custom_node(module_path: str, ignore=set(), module_parent="custom_nodes") -> bool:
-    module_name = os.path.basename(module_path)
+    module_name = get_module_name(module_path)
     if os.path.isfile(module_path):
         sp = os.path.splitext(module_path)
         module_name = sp[0]
+        sys_module_name = module_name
+    elif os.path.isdir(module_path):
+        sys_module_name = module_path.replace(".", "_x_")
+
     try:
         logging.debug("Trying to load custom node {}".format(module_path))
         if os.path.isfile(module_path):
-            module_spec = importlib.util.spec_from_file_location(module_name, module_path)
+            module_spec = importlib.util.spec_from_file_location(sys_module_name, module_path)
             module_dir = os.path.split(module_path)[0]
         else:
-            module_spec = importlib.util.spec_from_file_location(module_name, os.path.join(module_path, "__init__.py"))
+            module_spec = importlib.util.spec_from_file_location(sys_module_name, os.path.join(module_path, "__init__.py"))
             module_dir = module_path
 
         module = importlib.util.module_from_spec(module_spec)
-        sys.modules[module_name] = module
+        sys.modules[sys_module_name] = module
         module_spec.loader.exec_module(module)
 
         LOADED_MODULE_DIRS[module_name] = os.path.abspath(module_dir)

requirements.txt

@@ -1,4 +1,4 @@
-comfyui-frontend-package==1.14.6
+comfyui-frontend-package==1.15.13
 torch
 torchsde
 torchvision

script_examples/gradio_websockets_api_example.py

@@ -0,0 +1,309 @@
+# This is a Gradio example demonstrating using the websocket api and that also decodes preview images
+# Gradio has a lot of idiosyncrasies and I'm definitely not an expert at coding for it
+# I'm sure there are a million and one better ways to code this, but this works pretty well and should get you started
+# I suggest taking the time to check any relevant comments throughout the code
+# For more info on working with Gradio: https://www.gradio.app/docs
+
+# Ensure that ComfyUI has latent previews enabled
+# If you use Comfy Manager, make sure to set the preview type there because it will override --preview-method auto/latent2rgb/taesd launch flag settings
+# Check or change the preview_method in "/custom_nodes/ComfyUI-Manager/config.ini"
+
+# If you chose to install Gradio to your ComfyUI python venv, open a command prompt in this script_examples directory and run:
+# ..\..\python_embeded\python.exe -s ..\script_examples\gradio_websockets_api_example.py
+# To launch the app
+
+import websocket #NOTE: websocket-client (https://github.com/websocket-client/websocket-client)
+import uuid
+import json
+import urllib.request
+import urllib.parse
+from PIL import Image
+import io
+from io import BytesIO
+import random
+
+#If you want to use your local ComfyUI python installation, you'll need to navigate to your comfyui/python_embeded folder, open a cmd prompt and run "python.exe -m pip install gradio"
+import gradio as gr
+
+# adjust to your ComfyUI API settings
+server_address = "127.0.0.1:8188"
+client_id = str(uuid.uuid4())
+
+#some globals to store previews, active state and progress
+preview_image = None
+active = False
+interrupted = False
+step_current = None
+step_total = None
+
+def interrupt_diffusion():
+    global interrupted, step_current, step_total
+    interrupted = True
+    step_current = None
+    step_total = None
+    req = urllib.request.Request("http://{}/interrupt".format(server_address), method='POST')
+    return urllib.request.urlopen(req)
+
+def queue_prompt(prompt):
+    p = {"prompt": prompt, "client_id": client_id}
+    data = json.dumps(p).encode('utf-8')
+    req = urllib.request.Request("http://{}/prompt".format(server_address), data=data)
+    return json.loads(urllib.request.urlopen(req).read())
+
+def get_image(filename, subfolder, folder_type):
+    data = {"filename": filename, "subfolder": subfolder, "type": folder_type}
+    url_values = urllib.parse.urlencode(data)
+    with urllib.request.urlopen("http://{}/view?{}".format(server_address, url_values)) as response:
+        return response.read()
+
+def get_history(prompt_id):
+    with urllib.request.urlopen("http://{}/history/{}".format(server_address, prompt_id)) as response:
+        return json.loads(response.read())
+
+def get_images(ws, prompt):
+    global preview_image, active, step_current, step_total
+    prompt_id = queue_prompt(prompt)['prompt_id']
+    output_images = {}
+    while True:
+        out = ws.recv()
+        if isinstance(out, str):
+            message = json.loads(out)
+            if message['type'] == 'executing':
+                data = message['data']
+                if data['node'] is None and data['prompt_id'] == prompt_id:
+                    preview_image = None #clear these globals on completion just in case
+                    step_current = None
+                    step_total = None
+                    active = False
+                    break #Execution is done
+            elif message['type'] == 'progress':
+                data = message['data']
+                step_current = data['value']
+                step_total = data['max']
+        else:
+            bytesIO = BytesIO(out[8:])
+            preview_image = Image.open(bytesIO) # This is your preview in PIL image format
+
+    history = get_history(prompt_id)[prompt_id]
+    for node_id in history['outputs']:
+        node_output = history['outputs'][node_id]
+        images_output = []
+        if 'images' in node_output:
+            for image in node_output['images']:
+                image_data = get_image(image['filename'], image['subfolder'], image['type'])
+                images_output.append(image_data)
+        output_images[node_id] = images_output
+
+    return output_images
+
+def get_prompt_images(prompt):
+    global preview_image
+    ws = websocket.WebSocket()
+    ws.connect("ws://{}/ws?clientId={}".format(server_address, client_id))
+    images = get_images(ws, prompt)
+    outputs = []
+    for node_id in images:
+        for image_data in images[node_id]:
+            image = Image.open(io.BytesIO(image_data))
+            outputs.append(image)
+    ws.close()
+    return outputs
+
+############################################################################################################################
+# Edit or add your own api workflow here. Make sure to enable dev mode in ComfyUI and to use the "Save(API Format)" option #
+############################################################################################################################
+prompt_text = """
+{
+    "3": {
+        "class_type": "KSampler",
+        "inputs": {
+            "cfg": 8,
+            "denoise": 1,
+            "latent_image": [
+                "5",
+                0
+            ],
+            "model": [
+                "4",
+                0
+            ],
+            "negative": [
+                "7",
+                0
+            ],
+            "positive": [
+                "6",
+                0
+            ],
+            "sampler_name": "euler",
+            "scheduler": "normal",
+            "seed": -1,
+            "steps": 25
+        }
+    },
+    "4": {
+        "class_type": "CheckpointLoaderSimple",
+        "inputs": {
+            "ckpt_name": "sdxl_base_1.0_0.9vae.safetensors"
+        }
+    },
+    "5": {
+        "class_type": "EmptyLatentImage",
+        "inputs": {
+            "batch_size": 1,
+            "height": 1024,
+            "width": 1024
+        }
+    },
+    "6": {
+        "class_type": "CLIPTextEncode",
+        "inputs": {
+            "clip": [
+                "4",
+                1
+            ],
+            "text": ""
+        }
+    },
+    "7": {
+        "class_type": "CLIPTextEncode",
+        "inputs": {
+            "clip": [
+                "4",
+                1
+            ],
+            "text": ""
+        }
+    },
+    "8": {
+        "class_type": "VAEDecode",
+        "inputs": {
+            "samples": [
+                "3",
+                0
+            ],
+            "vae": [
+                "4",
+                2
+            ]
+        }
+    },
+    "9": {
+        "class_type": "SaveImage",
+        "inputs": {
+            "filename_prefix": "ComfyUI",
+            "images": [
+                "8",
+                0
+            ]
+        }
+    }
+}
+"""
+
+prompt = json.loads(prompt_text)
+
+# You can also use the following if you'd rather just load a json, make sure to comment out or remove the line above
+# with open("/path/to/workflow.json", "r", encoding="utf-8") as f:
+    # prompt = json.load(f)
+
+# start and stop timer are used for live updating the preview and progress
+# no point in keeping the timer ticking if it's not currently generating
+def start_timer(): 
+    global active
+    active = True
+    return gr.Timer(active=True)
+    
+def stop_timer():
+    global active
+    active = False
+    return gr.Timer(active=False)
+
+def update_preview():
+    return gr.Image(value=preview_image)
+
+# Gradio is somewhat finicky about multiple things trying to change the same output, so we switch between preview and image, while hiding the other
+def window_preview():
+    return gr.Image(visible=False, value=None), gr.Image(visible=True, value=None), gr.Button(visible=False),  gr.Button(visible=True, value="Stop: Busy")
+
+def window_final():
+    if interrupted: #if we interrupted during the process, put things back to normal
+        return gr.Image(visible=True, value=None), gr.Image(visible=False), gr.Button(visible=True), gr.Button(visible=False)
+    else:
+        return gr.Image(visible=True), gr.Image(visible=False, value=None), gr.Button(visible=True), gr.Button(visible=False)
+
+# Puts the progress on the stop button
+def update_progress():
+    if step_current == 0 or step_current == None:
+        x = 0
+    else:
+        x = int(100 * (step_current / step_total))
+    if step_current == None or active == False:
+        message = "Stop: Busy"
+    else:
+        message = f"Stop: {step_current} / {step_total} steps {x}%"
+    return gr.Button(value=message)
+
+# You will need to do a lot of editing here to match your workflow
+def process(pos, neg, width, height, cfg, seed):
+    if seed <= -1:
+        seed = random.randint(0, 999999999)
+    prompt["4"]["inputs"]["ckpt_name"] = "sdxl_base_1.0_0.9vae.safetensors" #if you want to change the model, do it here
+    prompt["6"]["inputs"]["text"] = pos
+    prompt["7"]["inputs"]["text"] = neg
+    prompt["3"]["inputs"]["seed"] = seed
+    prompt["3"]["inputs"]["cfg"] = cfg
+    prompt["5"]["inputs"]["height"] = height
+    prompt["5"]["inputs"]["width"] = width
+    
+    global interrupted
+    interrupted = False
+    
+    images = get_prompt_images(prompt)
+    
+    global active
+    active = False
+
+    try:
+      return gr.Image(value=images[0]) #not covering batch generations in this example because it requires setting the image output to a gr.Gallery, along with some other changes
+    except:
+      return gr.Image()
+
+with gr.Blocks(analytics_enabled=False, fill_width=True, fill_height=True,) as example:
+    preview_timer = gr.Timer(value=1, active=False) # You can also lower the timer to something like 0.5 to get more frequent updates, but there's not really much point to it
+    with gr.Row():
+        with gr.Column():
+            with gr.Group():
+                user_prompt = gr.Textbox(label="Positive Prompt: ", value="orange cat, full moon, vibrant impressionistic painting, bright vivid rainbow of colors", lines=5, max_lines=20)
+                user_negativeprompt = gr.Textbox(label="Negative Prompt: ", value="text, watermark", lines=2, max_lines=10,)
+            with gr.Group():
+                with gr.Row():
+                    user_width = gr.Slider(label="Width", minimum=512, maximum=1600, step=64, value=1152,)
+                    user_height = gr.Slider(label="Height", minimum=512, maximum=1600, step=64, value=896,)
+                with gr.Row():
+                    user_cfg = gr.Slider(label="CFG: ", minimum=1.0, maximum=16.0, step=0.1, value=4.5,)
+                    user_seed = gr.Slider(label="Seed: (-1 for random)", minimum=-1, maximum=999999999, step=1, value=-1,)   
+            generate = gr.Button("Generate", variant="primary")
+            stop = gr.Button("Stop", variant="stop", visible=False)
+        with gr.Column():    
+            output_image = gr.Image(label="Image: ", type="pil", format="jpeg", interactive=False, visible=True)            
+            output_preview = gr.Image(label="Preview: ", type="pil", format="jpeg", interactive=False, visible=False)
+    
+    # On tick, we update the preview and then the progress
+    preview_timer.tick(
+        fn=update_preview, outputs=output_preview, show_progress="hidden").then(
+        fn=update_progress, outputs=stop, show_progress="hidden")
+    
+    # On generate we switch windows/buttons, start the update tick, diffuse the image, stop the update tick and then finally, swap the image outputs/buttons back
+    generate.click(
+        fn=window_preview, outputs=[output_image, output_preview, generate, stop], show_progress="hidden").then(
+        fn=start_timer, outputs=preview_timer, show_progress="hidden").then(
+        fn=process, inputs=[user_prompt, user_negativeprompt, user_width, user_height, user_cfg, user_seed], outputs=output_image).then(
+        fn=stop_timer, outputs=preview_timer, show_progress="hidden").then(
+        fn=window_final, outputs=[output_image, output_preview, generate, stop], show_progress="hidden") 
+    
+    stop.click(fn=interrupt_diffusion, show_progress="hidden")
+
+# Adjust settings to your needs https://www.gradio.app/docs/gradio/blocks#blocks-launch for more info
+example.queue(max_size=2,) # how many users can queue up in line
+example.launch(share=False, inbrowser=True, server_name="0.0.0.0", server_port=7860, enable_monitoring=False) # good for LAN-only setups

server.py

@@ -48,7 +48,7 @@ async def send_socket_catch_exception(function, message):
 @web.middleware
 async def cache_control(request: web.Request, handler):
     response: web.Response = await handler(request)
-    if request.path.endswith('.js') or request.path.endswith('.css'):
+    if request.path.endswith('.js') or request.path.endswith('.css') or request.path.endswith('index.json'):
         response.headers.setdefault('Cache-Control', 'no-cache')
     return response
 
@@ -657,7 +657,13 @@ class PromptServer():
                     logging.warning("invalid prompt: {}".format(valid[1]))
                     return web.json_response({"error": valid[1], "node_errors": valid[3]}, status=400)
             else:
-                return web.json_response({"error": "no prompt", "node_errors": []}, status=400)
+                error = {
+                    "type": "no_prompt",
+                    "message": "No prompt provided",
+                    "details": "No prompt provided",
+                    "extra_info": {}
+                }
+                return web.json_response({"error": error, "node_errors": {}}, status=400)
 
         @routes.post("/queue")
         async def post_queue(request):