Add Batch Images, Batch Masks, and Batch Latents nodes with Autogrow, deprecate old Batch Images + LatentBatch nodes

(cherry picked from commit 98c6840aa4e5fd5407ba9ab113d209011e474bf6)

comfy/ldm/lumina/model.py

@@ -491,7 +491,8 @@ class NextDiT(nn.Module):
                 for layer_id in range(n_layers)
             ]
         )
-        self.norm_final = operation_settings.get("operations").RMSNorm(dim, eps=norm_eps, elementwise_affine=True, device=operation_settings.get("device"), dtype=operation_settings.get("dtype"))
+        # This norm final is in the lumina 2.0 code but isn't actually used for anything.
+        # self.norm_final = operation_settings.get("operations").RMSNorm(dim, eps=norm_eps, elementwise_affine=True, device=operation_settings.get("device"), dtype=operation_settings.get("dtype"))
         self.final_layer = FinalLayer(dim, patch_size, self.out_channels, z_image_modulation=z_image_modulation, operation_settings=operation_settings)
 
         if self.pad_tokens_multiple is not None:

comfy/model_management.py

@@ -1019,8 +1019,8 @@ NUM_STREAMS = 0
 if args.async_offload is not None:
     NUM_STREAMS = args.async_offload
 else:
-    #  Enable by default on Nvidia
-    if is_nvidia():
+    #  Enable by default on Nvidia and AMD
+    if is_nvidia() or is_amd():
         NUM_STREAMS = 2
 
 if args.disable_async_offload:
@@ -1126,6 +1126,16 @@ if not args.disable_pinned_memory:
 
 PINNING_ALLOWED_TYPES = set(["Parameter", "QuantizedTensor"])
 
+def discard_cuda_async_error():
+    try:
+        a = torch.tensor([1], dtype=torch.uint8, device=get_torch_device())
+        b = torch.tensor([1], dtype=torch.uint8, device=get_torch_device())
+        _ = a + b
+        torch.cuda.synchronize()
+    except torch.AcceleratorError:
+        #Dump it! We already know about it from the synchronous return
+        pass
+
 def pin_memory(tensor):
     global TOTAL_PINNED_MEMORY
     if MAX_PINNED_MEMORY <= 0:
@@ -1158,6 +1168,9 @@ def pin_memory(tensor):
         PINNED_MEMORY[ptr] = size
         TOTAL_PINNED_MEMORY += size
         return True
+    else:
+        logging.warning("Pin error.")
+        discard_cuda_async_error()
 
     return False
 
@@ -1186,6 +1199,9 @@ def unpin_memory(tensor):
         if len(PINNED_MEMORY) == 0:
             TOTAL_PINNED_MEMORY = 0
         return True
+    else:
+        logging.warning("Unpin error.")
+        discard_cuda_async_error()
 
     return False
 

comfy_api_nodes/nodes_veo2.py

@@ -168,6 +168,8 @@ class VeoVideoGenerationNode(IO.ComfyNode):
         # Only add generateAudio for Veo 3 models
         if model.find("veo-2.0") == -1:
             parameters["generateAudio"] = generate_audio
+            # force "enhance_prompt" to True for Veo3 models
+            parameters["enhancePrompt"] = True
 
         initial_response = await sync_op(
             cls,
@@ -291,7 +293,7 @@ class Veo3VideoGenerationNode(VeoVideoGenerationNode):
                 IO.Boolean.Input(
                     "enhance_prompt",
                     default=True,
-                    tooltip="Whether to enhance the prompt with AI assistance",
+                    tooltip="This parameter is deprecated and ignored.",
                     optional=True,
                 ),
                 IO.Combo.Input(

comfy_api_nodes/util/client.py

@@ -430,9 +430,9 @@ def _display_text(
     if status:
         display_lines.append(f"Status: {status.capitalize() if isinstance(status, str) else status}")
     if price is not None:
-        p = f"{float(price):,.4f}".rstrip("0").rstrip(".")
+        p = f"{float(price) * 211:,.1f}".rstrip("0").rstrip(".")
         if p != "0":
-            display_lines.append(f"Price: ${p}")
+            display_lines.append(f"Price: {p} credits")
     if text is not None:
         display_lines.append(text)
     if display_lines:

comfy_extras/nodes_dataset.py

@@ -667,16 +667,19 @@ class ResizeImagesByLongerEdgeNode(ImageProcessingNode):
 
     @classmethod
     def _process(cls, image, longer_edge):
-        img = tensor_to_pil(image)
-        w, h = img.size
-        if w > h:
-            new_w = longer_edge
-            new_h = int(h * (longer_edge / w))
-        else:
-            new_h = longer_edge
-            new_w = int(w * (longer_edge / h))
-        img = img.resize((new_w, new_h), Image.Resampling.LANCZOS)
-        return pil_to_tensor(img)
+        resized_images = []
+        for image_i in image:
+            img = tensor_to_pil(image_i)
+            w, h = img.size
+            if w > h:
+                new_w = longer_edge
+                new_h = int(h * (longer_edge / w))
+            else:
+                new_h = longer_edge
+                new_w = int(w * (longer_edge / h))
+            img = img.resize((new_w, new_h), Image.Resampling.LANCZOS)
+            resized_images.append(pil_to_tensor(img))
+        return torch.cat(resized_images, dim=0)
 
 
 class CenterCropImagesNode(ImageProcessingNode):

comfy_extras/nodes_latent.py

@@ -255,6 +255,7 @@ class LatentBatch(io.ComfyNode):
         return io.Schema(
             node_id="LatentBatch",
             category="latent/batch",
+            is_deprecated=True,
             inputs=[
                 io.Latent.Input("samples1"),
                 io.Latent.Input("samples2"),

comfy_extras/nodes_post_processing.py

@@ -498,6 +498,66 @@ def batch_latents(latents: list[dict[str, torch.Tensor]]) -> dict[str, torch.Ten
     samples_out["samples"] = torch.cat(tensors, dim=0)
     return samples_out
 
+class BatchImagesNode(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        autogrow_template = io.Autogrow.TemplatePrefix(io.Image.Input("image"), prefix="image", min=2, max=50)
+        return io.Schema(
+            node_id="BatchImagesNode",
+            display_name="Batch Images",
+            category="image",
+            inputs=[
+                io.Autogrow.Input("images", template=autogrow_template)
+            ],
+            outputs=[
+                io.Image.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, images: io.Autogrow.Type) -> io.NodeOutput:
+        return io.NodeOutput(batch_images(list(images.values())))
+
+class BatchMasksNode(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        autogrow_template = io.Autogrow.TemplatePrefix(io.Mask.Input("mask"), prefix="mask", min=2, max=50)
+        return io.Schema(
+            node_id="BatchMasksNode",
+            display_name="Batch Masks",
+            category="mask",
+            inputs=[
+                io.Autogrow.Input("masks", template=autogrow_template)
+            ],
+            outputs=[
+                io.Mask.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, masks: io.Autogrow.Type) -> io.NodeOutput:
+        return io.NodeOutput(batch_masks(list(masks.values())))
+
+class BatchLatentsNode(io.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        autogrow_template = io.Autogrow.TemplatePrefix(io.Latent.Input("latent"), prefix="latent", min=2, max=50)
+        return io.Schema(
+            node_id="BatchLatentsNode",
+            display_name="Batch Latents",
+            category="latent",
+            inputs=[
+                io.Autogrow.Input("latents", template=autogrow_template)
+            ],
+            outputs=[
+                io.Latent.Output()
+            ]
+        )
+
+    @classmethod
+    def execute(cls, latents: io.Autogrow.Type) -> io.NodeOutput:
+        return io.NodeOutput(batch_latents(list(latents.values())))
+
 class BatchImagesMasksLatentsNode(io.ComfyNode):
     @classmethod
     def define_schema(cls):
@@ -542,6 +602,9 @@ class PostProcessingExtension(ComfyExtension):
             Sharpen,
             ImageScaleToTotalPixels,
             ResizeImageMaskNode,
+            BatchImagesNode,
+            BatchMasksNode,
+            BatchLatentsNode,
             # BatchImagesMasksLatentsNode,
         ]
 

nodes.py

@@ -1863,6 +1863,7 @@ class ImageBatch:
     FUNCTION = "batch"
 
     CATEGORY = "image"
+    DEPRECATED = True
 
     def batch(self, image1, image2):
         if image1.shape[-1] != image2.shape[-1]: