chore(openapi): sync shared API contract from cloud@322debb

comfy/cli_args.py

@@ -115,7 +115,6 @@ cache_group.add_argument("--cache-ram", nargs='*', type=float, default=[], metav
 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.")
-cache_group.add_argument("--high-ram", action="store_true", help="Can improve performance slightly on high RAM or on systems where pagefile use is preferred over model loading.")
 
 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.")
@@ -250,9 +249,6 @@ else:
 if args.cache_ram is not None and len(args.cache_ram) > 2:
     parser.error("--cache-ram accepts at most two values: active GB and inactive GB")
 
-if args.high_ram:
-    args.cache_classic = True
-
 if args.windows_standalone_build:
     args.auto_launch = True
 

comfy/ldm/ideogram4/model.py

@@ -106,11 +106,11 @@ class Ideogram4EmbedScalar(nn.Module):
         self.mlp_in = operations.Linear(dim, dim, bias=True, dtype=dtype, device=device)
         self.mlp_out = operations.Linear(dim, dim, bias=True, dtype=dtype, device=device)
 
-    def forward(self, x, dtype):
+    def forward(self, x):
         x = x.to(torch.float32)
         scaled = 1e4 * (x - self.range_min) / (self.range_max - self.range_min)
         emb = _sinusoidal_embedding(scaled, self.dim)
-        emb = emb.to(dtype)
+        emb = emb.to(self.mlp_in.weight.dtype)
         emb = F.silu(self.mlp_in(emb))
         return self.mlp_out(emb)
 
@@ -161,7 +161,7 @@ class Ideogram4Transformer(nn.Module):
         x = x * output_image_mask
         h = self.input_proj(x) * output_image_mask
 
-        t_cond = self.t_embedding(t, dtype=x.dtype)
+        t_cond = self.t_embedding(t)
         if t.dim() == 1:
             t_cond = t_cond.unsqueeze(1)
         adaln_input = F.silu(self.adaln_proj(t_cond))

comfy/model_management.py

@@ -643,8 +643,6 @@ def free_pins(size, evict_active=False):
     return freed_total
 
 def ensure_pin_budget(size, evict_active=False):
-    if args.high_ram:
-        return True
     if args.fast_disk:
         shortfall = TOTAL_PINNED_MEMORY + size - MAX_PINNED_MEMORY
     else:
@@ -1498,8 +1496,6 @@ if not args.disable_pinned_memory:
 PINNING_ALLOWED_TYPES = set(["Tensor", "Parameter", "QuantizedTensor"])
 
 def pinned_hostbuf_size(size):
-    if args.high_ram:
-        return max(0, int(size * 2))
     return max(0, int(min(size, MAX_PINNED_MEMORY) * 2))
 
 def discard_cuda_async_error():

comfy/ops.py

@@ -180,7 +180,7 @@ def cast_modules_with_vbar(comfy_modules, dtype, device, bias_dtype, non_blockin
             if pin is not None:
                 cast_maybe_lowvram_patch([pin], dest, offload_stream)
                 return
-            if signature is None or args.high_ram:
+            if signature is None:
                 comfy.pinned_memory.pin_memory(m, subset=subset, size=size)
                 pin = comfy.pinned_memory.get_pin(m, subset=subset)
             cast_maybe_lowvram_patch(source, pin, offload_stream, xfer_dest2=dest)

comfy_extras/nodes_rtdetr.py

@@ -14,7 +14,7 @@ class RTDETR_detect(io.ComfyNode):
     def define_schema(cls):
         return io.Schema(
             node_id="RTDETR_detect",
-            display_name="Run Real-Time Detection (RT-DETR)",
+            display_name="RT-DETR Detect",
             category="image/detection",
             search_aliases=["bbox", "bounding box", "object detection", "coco"],
             inputs=[

comfy_extras/nodes_sam3.py

@@ -264,7 +264,7 @@ class SAM3_VideoTrack(io.ComfyNode):
     def define_schema(cls):
         return io.Schema(
             node_id="SAM3_VideoTrack",
-            display_name="Run SAM3 Video Track",
+            display_name="SAM3 Video Track",
             category="image/detection",
             search_aliases=["sam3", "video", "track", "propagate"],
             inputs=[

openapi.yaml

@@ -896,11 +896,6 @@ components:
                     additionalProperties: true
                     description: The workflow graph to execute
                     type: object
-                prompt_id:
-                    description: Optional client-supplied job id. Must be a UUID in canonical lowercase hyphenated form; it is echoed back in the response. Omitted or null means the server generates one.
-                    format: uuid
-                    nullable: true
-                    type: string
                 workflow_id:
                     description: UUID identifying the cloud workflow entity to associate with this job
                     type: string