Fix black image on turing when using int4 models. (#14864)

On AMD/ROCm the CUDA backend is unavailable, so Triton is the only accelerated
comfy-kitchen backend. It was disabled by default (opt-in --enable-triton-backend),
leaving AMD on the slow eager path. Enable it by default when torch.version.hip is
set AND Triton is >= 3.7 -- older Triton lacks libdevice.rint on the HIP backend and
hard-crashes the INT8 path, so on Triton < 3.7 it stays disabled with a log line.
NVIDIA behavior is unchanged; the explicit --enable-triton-backend flag still works
as an override.

Fixes #14861

comfy/ops.py

@@ -1257,7 +1257,7 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec
                 run_every_op()
 
                 input_shape = input.shape
-                reshaped_3d = False
+                reshaped_nd = False
                 #If cast needs to apply lora, it should be done in the compute dtype
                 compute_dtype = input.dtype
 
@@ -1294,12 +1294,12 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec
                 # Inference path (unchanged)
                 if _use_quantized and quantize_input:
 
-                    # Reshape 3D tensors to 2D for quantization (needed for NVFP4 and others)
-                    input_reshaped = input.reshape(-1, input_shape[2]) if input.ndim == 3 else input
+                    # Reshape >=3D tensors to 2D for quantization (needed for NVFP4 and others)
+                    input_reshaped = input.reshape(-1, input_shape[-1]) if input.ndim >= 3 else input
 
                     # Fall back to non-quantized for non-2D tensors
                     if input_reshaped.ndim == 2:
-                        reshaped_3d = input.ndim == 3
+                        reshaped_nd = input.ndim >= 3
                         # dtype is now implicit in the layout class
                         scale = getattr(self, 'input_scale', None)
                         if scale is not None:
@@ -1314,9 +1314,9 @@ def mixed_precision_ops(quant_config={}, compute_dtype=torch.bfloat16, full_prec
                     weight_only_quant=weight_only_quant,
                 )
 
-                # Reshape output back to 3D if input was 3D
-                if reshaped_3d:
-                    output = output.reshape((input_shape[0], input_shape[1], self.weight.shape[0]))
+                # Reshape output back to original rank if input was >2D
+                if reshaped_nd:
+                    output = output.reshape((*input_shape[:-1], self.weight.shape[0]))
 
                 return output
 

comfy/quant_ops.py

@@ -25,10 +25,18 @@ try:
             ck.registry.disable("cuda")
             logging.warning("WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.")
 
-    if args.enable_triton_backend:
+    # On ROCm/AMD the CUDA backend is unavailable, so Triton is the only accelerated
+    # comfy-kitchen backend. Enable it by default there, but only on Triton >= 3.7:
+    # older Triton lacks libdevice.rint on the HIP backend and hard-crashes the INT8 path.
+    if args.enable_triton_backend or torch.version.hip is not None:
         try:
             import triton
-            logging.info("Found triton %s. Enabling comfy-kitchen triton backend.", triton.__version__)
+            triton_version = tuple(int(v) for v in triton.__version__.split(".")[:2])
+            if args.enable_triton_backend or triton_version >= (3, 7):
+                logging.info("Found triton %s. Enabling comfy-kitchen triton backend.", triton.__version__)
+            else:
+                logging.info("Triton %s is too old for the ROCm INT8 path (needs >= 3.7); comfy-kitchen triton backend disabled.", triton.__version__)
+                ck.registry.disable("triton")
         except ImportError as e:
             logging.error(f"Failed to import triton, Error: {e}, the comfy-kitchen triton backend will not be available.")
             ck.registry.disable("triton")

comfy_api_nodes/apis/bytedance.py

@@ -17,10 +17,6 @@ class Seedream4Options(BaseModel):
     max_images: int = Field(15)
 
 
-class Seedream5OptimizePromptOptions(BaseModel):
-    thinking: Literal["auto", "enabled", "disabled"] = Field(...)
-
-
 class Seedream4TaskCreationRequest(BaseModel):
     model: str = Field(...)
     prompt: str = Field(...)
@@ -32,7 +28,6 @@ class Seedream4TaskCreationRequest(BaseModel):
     sequential_image_generation_options: Seedream4Options | None = Field(Seedream4Options(max_images=15))
     watermark: bool = Field(False)
     output_format: str | None = None
-    optimize_prompt_options: Seedream5OptimizePromptOptions | None = None
 
 
 class ImageTaskCreationResponse(BaseModel):

comfy_api_nodes/nodes_bytedance.py

@@ -34,7 +34,6 @@ from comfy_api_nodes.apis.bytedance import (
     SeedanceVirtualLibraryCreateAssetRequest,
     Seedream4Options,
     Seedream4TaskCreationRequest,
-    Seedream5OptimizePromptOptions,
     TaskAudioContent,
     TaskAudioContentUrl,
     TaskCreationResponse,
@@ -876,17 +875,6 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
                     tooltip='Whether to add an "AI generated" watermark to the image.',
                     advanced=True,
                 ),
-                IO.Boolean.Input(
-                    "thinking",
-                    default=True,
-                    tooltip=(
-                        "Enable the model's prompt-optimization reasoning ('thinking') for better adherence. "
-                        "Can substantially increase generation time — notably on Seedream 5.0 Pro. "
-                        "Can only be disabled for text-to-image (not when reference images are provided)."
-                    ),
-                    optional=True,
-                    advanced=True,
-                ),
             ],
             outputs=[
                 IO.Image.Output(),
@@ -932,7 +920,6 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
         model: dict,
         seed: int = 0,
         watermark: bool = False,
-        thinking: bool = True,
     ) -> IO.NodeOutput:
         validate_string(prompt, strip_whitespace=True, min_length=1)
         model_id = SEEDREAM_MODELS[model["model"]]
@@ -992,10 +979,6 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
             raise ValueError(
                 "The maximum number of generated images plus the number of reference images cannot exceed 15."
             )
-        if not thinking and n_input_images > 0:
-            raise ValueError(
-                "'thinking' can only be disabled for text-to-image; enable it when using reference images."
-            )
 
         reference_images_urls: list[str] = []
         if image_tensors:
@@ -1009,9 +992,6 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
                 wait_label="Uploading reference images",
             )
 
-        optimize_prompt_options = None
-        if n_input_images == 0:
-            optimize_prompt_options = Seedream5OptimizePromptOptions(thinking="enabled" if thinking else "disabled")
         response = await sync_op(
             cls,
             ApiEndpoint(path=BYTEPLUS_IMAGE_ENDPOINT, method="POST"),
@@ -1025,7 +1005,6 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
                 sequential_image_generation=None if is_pro else sequential_image_generation,
                 sequential_image_generation_options=None if is_pro else Seedream4Options(max_images=max_images),
                 watermark=watermark,
-                optimize_prompt_options=optimize_prompt_options,
             ),
         )
         if len(response.data) == 1:

requirements.txt

@@ -22,7 +22,7 @@ alembic
 SQLAlchemy>=2.0.0
 filelock
 av>=16.0.0
-comfy-kitchen==0.2.17
+comfy-kitchen==0.2.18
 comfy-aimdo==0.4.10
 requests
 simpleeval>=1.0.0