diff --git a/comfy/ldm/chroma_radiance/model.py b/comfy/ldm/chroma_radiance/model.py index 47aa11b04..7d7be80f5 100644 --- a/comfy/ldm/chroma_radiance/model.py +++ b/comfy/ldm/chroma_radiance/model.py @@ -189,15 +189,15 @@ class ChromaRadiance(Chroma): nerf_pixels = nn.functional.unfold(img_orig, kernel_size=patch_size, stride=patch_size) nerf_pixels = nerf_pixels.transpose(1, 2) # -> [B, NumPatches, C * P * P] + # Reshape for per-patch processing + nerf_hidden = img_out.reshape(B * num_patches, params.hidden_size) + nerf_pixels = nerf_pixels.reshape(B * num_patches, C, patch_size**2).transpose(1, 2) + if params.nerf_tile_size > 0 and num_patches > params.nerf_tile_size: # Enable tiling if nerf_tile_size isn't 0 and we actually have more patches than # the tile size. - img_dct = self.forward_tiled_nerf(img_out, nerf_pixels, B, C, num_patches, patch_size, params) + img_dct = self.forward_tiled_nerf(nerf_hidden, nerf_pixels, B, C, num_patches, patch_size, params) else: - # Reshape for per-patch processing - nerf_hidden = img_out.reshape(B * num_patches, params.hidden_size) - nerf_pixels = nerf_pixels.reshape(B * num_patches, C, patch_size**2).transpose(1, 2) - # Get DCT-encoded pixel embeddings [pixel-dct] img_dct = self.nerf_image_embedder(nerf_pixels) @@ -240,17 +240,8 @@ class ChromaRadiance(Chroma): end = min(i + tile_size, num_patches) # Slice the current tile from the input tensors - nerf_hidden_tile = nerf_hidden[:, i:end, :] - nerf_pixels_tile = nerf_pixels[:, i:end, :] - - # Get the actual number of patches in this tile (can be smaller for the last tile) - num_patches_tile = nerf_hidden_tile.shape[1] - - # Reshape the tile for per-patch processing - # [B, NumPatches_tile, D] -> [B * NumPatches_tile, D] - nerf_hidden_tile = nerf_hidden_tile.reshape(batch * num_patches_tile, params.hidden_size) - # [B, NumPatches_tile, C*P*P] -> [B*NumPatches_tile, C, P*P] -> [B*NumPatches_tile, P*P, C] - nerf_pixels_tile = nerf_pixels_tile.reshape(batch * num_patches_tile, channels, patch_size**2).transpose(1, 2) + nerf_hidden_tile = nerf_hidden[i * batch:end * batch] + nerf_pixels_tile = nerf_pixels[i * batch:end * batch] # get DCT-encoded pixel embeddings [pixel-dct] img_dct_tile = self.nerf_image_embedder(nerf_pixels_tile) diff --git a/comfy/model_detection.py b/comfy/model_detection.py index 7677617c0..141f1e164 100644 --- a/comfy/model_detection.py +++ b/comfy/model_detection.py @@ -213,7 +213,7 @@ def detect_unet_config(state_dict, key_prefix, metadata=None): dit_config["nerf_mlp_ratio"] = 4 dit_config["nerf_depth"] = 4 dit_config["nerf_max_freqs"] = 8 - dit_config["nerf_tile_size"] = 32 + dit_config["nerf_tile_size"] = 512 dit_config["nerf_final_head_type"] = "conv" if f"{key_prefix}nerf_final_layer_conv.norm.scale" in state_dict_keys else "linear" dit_config["nerf_embedder_dtype"] = torch.float32 else: diff --git a/comfy/model_management.py b/comfy/model_management.py index 709ebc40b..79d6ff9d4 100644 --- a/comfy/model_management.py +++ b/comfy/model_management.py @@ -330,14 +330,21 @@ except: SUPPORT_FP8_OPS = args.supports_fp8_compute + +AMD_RDNA2_AND_OLDER_ARCH = ["gfx1030", "gfx1031", "gfx1010", "gfx1011", "gfx1012", "gfx906", "gfx900", "gfx803"] + try: if is_amd(): - torch.backends.cudnn.enabled = False # Seems to improve things a lot on AMD + arch = torch.cuda.get_device_properties(get_torch_device()).gcnArchName + if not (any((a in arch) for a in AMD_RDNA2_AND_OLDER_ARCH)): + torch.backends.cudnn.enabled = False # Seems to improve things a lot on AMD + logging.info("Set: torch.backends.cudnn.enabled = False for better AMD performance.") + try: rocm_version = tuple(map(int, str(torch.version.hip).split(".")[:2])) except: rocm_version = (6, -1) - arch = torch.cuda.get_device_properties(get_torch_device()).gcnArchName + logging.info("AMD arch: {}".format(arch)) logging.info("ROCm version: {}".format(rocm_version)) if args.use_split_cross_attention == False and args.use_quad_cross_attention == False: @@ -349,7 +356,7 @@ try: if any((a in arch) for a in ["gfx1201"]): ENABLE_PYTORCH_ATTENTION = True if torch_version_numeric >= (2, 7) and rocm_version >= (6, 4): - if any((a in arch) for a in ["gfx1200", "gfx1201", "gfx942", "gfx950"]): # TODO: more arches + if any((a in arch) for a in ["gfx1200", "gfx1201", "gfx950"]): # TODO: more arches, "gfx942" gives error on pytorch nightly 2.10 1013 rocm7.0 SUPPORT_FP8_OPS = True except: @@ -371,6 +378,9 @@ try: except: pass +if torch.cuda.is_available() and torch.backends.cudnn.is_available() and PerformanceFeature.AutoTune in args.fast: + torch.backends.cudnn.benchmark = True + try: if torch_version_numeric >= (2, 5): torch.backends.cuda.allow_fp16_bf16_reduction_math_sdp(True) @@ -1327,7 +1337,7 @@ def should_use_bf16(device=None, model_params=0, prioritize_performance=True, ma 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 + if any((a in arch) for a in AMD_RDNA2_AND_OLDER_ARCH): # RDNA2 and older don't support bf16 if manual_cast: return True return False diff --git a/comfy/ops.py b/comfy/ops.py index b2096b40e..934e21261 100644 --- a/comfy/ops.py +++ b/comfy/ops.py @@ -25,6 +25,9 @@ import comfy.rmsnorm import contextlib def run_every_op(): + if torch.compiler.is_compiling(): + return + comfy.model_management.throw_exception_if_processing_interrupted() def scaled_dot_product_attention(q, k, v, *args, **kwargs): @@ -52,14 +55,22 @@ try: except (ModuleNotFoundError, TypeError): logging.warning("Could not set sdpa backend priority.") -cast_to = comfy.model_management.cast_to #TODO: remove once no more references +NVIDIA_MEMORY_CONV_BUG_WORKAROUND = False +try: + if comfy.model_management.is_nvidia(): + if torch.backends.cudnn.version() >= 91002 and comfy.model_management.torch_version_numeric >= (2, 9) and comfy.model_management.torch_version_numeric <= (2, 10): + #TODO: change upper bound version once it's fixed' + NVIDIA_MEMORY_CONV_BUG_WORKAROUND = True + logging.info("working around nvidia conv3d memory bug.") +except: + pass -if torch.cuda.is_available() and torch.backends.cudnn.is_available() and PerformanceFeature.AutoTune in args.fast: - torch.backends.cudnn.benchmark = True +cast_to = comfy.model_management.cast_to #TODO: remove once no more references def cast_to_input(weight, input, non_blocking=False, copy=True): return comfy.model_management.cast_to(weight, input.dtype, input.device, non_blocking=non_blocking, copy=copy) +@torch.compiler.disable() def cast_bias_weight(s, input=None, dtype=None, device=None, bias_dtype=None): if input is not None: if dtype is None: @@ -151,6 +162,15 @@ class disable_weight_init: def reset_parameters(self): return None + def _conv_forward(self, input, weight, bias, *args, **kwargs): + if NVIDIA_MEMORY_CONV_BUG_WORKAROUND and weight.dtype in (torch.float16, torch.bfloat16): + out = torch.cudnn_convolution(input, weight, self.padding, self.stride, self.dilation, self.groups, benchmark=False, deterministic=False, allow_tf32=True) + if bias is not None: + out += bias.reshape((1, -1) + (1,) * (out.ndim - 2)) + return out + else: + return super()._conv_forward(input, weight, bias, *args, **kwargs) + def forward_comfy_cast_weights(self, input): weight, bias = cast_bias_weight(self, input) return self._conv_forward(input, weight, bias) diff --git a/comfy/patcher_extension.py b/comfy/patcher_extension.py index 46cc7b2a8..5ee4d5ee5 100644 --- a/comfy/patcher_extension.py +++ b/comfy/patcher_extension.py @@ -150,7 +150,7 @@ def merge_nested_dicts(dict1: dict, dict2: dict, copy_dict1=True): for key, value in dict2.items(): if isinstance(value, dict): curr_value = merged_dict.setdefault(key, {}) - merged_dict[key] = merge_nested_dicts(value, curr_value) + merged_dict[key] = merge_nested_dicts(curr_value, value) elif isinstance(value, list): merged_dict.setdefault(key, []).extend(value) else: diff --git a/comfy/samplers.py b/comfy/samplers.py index c59e296a1..e7efaf470 100755 --- a/comfy/samplers.py +++ b/comfy/samplers.py @@ -306,17 +306,10 @@ def _calc_cond_batch(model: BaseModel, conds: list[list[dict]], x_in: torch.Tens copy_dict1=False) if patches is not None: - # TODO: replace with merge_nested_dicts function - if "patches" in transformer_options: - cur_patches = transformer_options["patches"].copy() - for p in patches: - if p in cur_patches: - cur_patches[p] = cur_patches[p] + patches[p] - else: - cur_patches[p] = patches[p] - transformer_options["patches"] = cur_patches - else: - transformer_options["patches"] = patches + transformer_options["patches"] = comfy.patcher_extension.merge_nested_dicts( + transformer_options.get("patches", {}), + patches + ) transformer_options["cond_or_uncond"] = cond_or_uncond[:] transformer_options["uuids"] = uuids[:] diff --git a/comfy_api_nodes/nodes_veo2.py b/comfy_api_nodes/nodes_veo2.py index 4588a7991..daeaa823e 100644 --- a/comfy_api_nodes/nodes_veo2.py +++ b/comfy_api_nodes/nodes_veo2.py @@ -27,6 +27,13 @@ from comfy_api_nodes.apinode_utils import ( ) AVERAGE_DURATION_VIDEO_GEN = 32 +MODELS_MAP = { + "veo-2.0-generate-001": "veo-2.0-generate-001", + "veo-3.1-generate": "veo-3.1-generate-preview", + "veo-3.1-fast-generate": "veo-3.1-fast-generate-preview", + "veo-3.0-generate-001": "veo-3.0-generate-001", + "veo-3.0-fast-generate-001": "veo-3.0-fast-generate-001", +} def convert_image_to_base64(image: torch.Tensor): if image is None: @@ -158,6 +165,7 @@ class VeoVideoGenerationNode(IO.ComfyNode): model="veo-2.0-generate-001", generate_audio=False, ): + model = MODELS_MAP[model] # Prepare the instances for the request instances = [] @@ -385,7 +393,9 @@ class Veo3VideoGenerationNode(VeoVideoGenerationNode): ), IO.Combo.Input( "model", - options=["veo-3.0-generate-001", "veo-3.0-fast-generate-001"], + options=[ + "veo-3.1-generate", "veo-3.1-fast-generate", "veo-3.0-generate-001", "veo-3.0-fast-generate-001" + ], default="veo-3.0-generate-001", tooltip="Veo 3 model to use for video generation", optional=True, diff --git a/comfy_extras/nodes_controlnet.py b/comfy_extras/nodes_controlnet.py index 2d20e1fed..e835feed7 100644 --- a/comfy_extras/nodes_controlnet.py +++ b/comfy_extras/nodes_controlnet.py @@ -1,20 +1,26 @@ from comfy.cldm.control_types import UNION_CONTROLNET_TYPES import nodes import comfy.utils +from typing_extensions import override +from comfy_api.latest import ComfyExtension, io -class SetUnionControlNetType: +class SetUnionControlNetType(io.ComfyNode): @classmethod - def INPUT_TYPES(s): - return {"required": {"control_net": ("CONTROL_NET", ), - "type": (["auto"] + list(UNION_CONTROLNET_TYPES.keys()),) - }} + def define_schema(cls): + return io.Schema( + node_id="SetUnionControlNetType", + category="conditioning/controlnet", + inputs=[ + io.ControlNet.Input("control_net"), + io.Combo.Input("type", options=["auto"] + list(UNION_CONTROLNET_TYPES.keys())), + ], + outputs=[ + io.ControlNet.Output(), + ], + ) - CATEGORY = "conditioning/controlnet" - RETURN_TYPES = ("CONTROL_NET",) - - FUNCTION = "set_controlnet_type" - - def set_controlnet_type(self, control_net, type): + @classmethod + def execute(cls, control_net, type) -> io.NodeOutput: control_net = control_net.copy() type_number = UNION_CONTROLNET_TYPES.get(type, -1) if type_number >= 0: @@ -22,27 +28,36 @@ class SetUnionControlNetType: else: control_net.set_extra_arg("control_type", []) - return (control_net,) + return io.NodeOutput(control_net) -class ControlNetInpaintingAliMamaApply(nodes.ControlNetApplyAdvanced): + set_controlnet_type = execute # TODO: remove + + +class ControlNetInpaintingAliMamaApply(io.ComfyNode): @classmethod - def INPUT_TYPES(s): - return {"required": {"positive": ("CONDITIONING", ), - "negative": ("CONDITIONING", ), - "control_net": ("CONTROL_NET", ), - "vae": ("VAE", ), - "image": ("IMAGE", ), - "mask": ("MASK", ), - "strength": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}), - "start_percent": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.001}), - "end_percent": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.001}) - }} + def define_schema(cls): + return io.Schema( + node_id="ControlNetInpaintingAliMamaApply", + category="conditioning/controlnet", + inputs=[ + io.Conditioning.Input("positive"), + io.Conditioning.Input("negative"), + io.ControlNet.Input("control_net"), + io.Vae.Input("vae"), + io.Image.Input("image"), + io.Mask.Input("mask"), + io.Float.Input("strength", default=1.0, min=0.0, max=10.0, step=0.01), + io.Float.Input("start_percent", default=0.0, min=0.0, max=1.0, step=0.001), + io.Float.Input("end_percent", default=1.0, min=0.0, max=1.0, step=0.001), + ], + outputs=[ + io.Conditioning.Output(display_name="positive"), + io.Conditioning.Output(display_name="negative"), + ], + ) - FUNCTION = "apply_inpaint_controlnet" - - CATEGORY = "conditioning/controlnet" - - def apply_inpaint_controlnet(self, positive, negative, control_net, vae, image, mask, strength, start_percent, end_percent): + @classmethod + def execute(cls, positive, negative, control_net, vae, image, mask, strength, start_percent, end_percent) -> io.NodeOutput: extra_concat = [] if control_net.concat_mask: mask = 1.0 - mask.reshape((-1, 1, mask.shape[-2], mask.shape[-1])) @@ -50,11 +65,20 @@ class ControlNetInpaintingAliMamaApply(nodes.ControlNetApplyAdvanced): image = image * mask_apply.movedim(1, -1).repeat(1, 1, 1, image.shape[3]) extra_concat = [mask] - return self.apply_controlnet(positive, negative, control_net, image, strength, start_percent, end_percent, vae=vae, extra_concat=extra_concat) + result = nodes.ControlNetApplyAdvanced().apply_controlnet(positive, negative, control_net, image, strength, start_percent, end_percent, vae=vae, extra_concat=extra_concat) + return io.NodeOutput(result[0], result[1]) + + apply_inpaint_controlnet = execute # TODO: remove +class ControlNetExtension(ComfyExtension): + @override + async def get_node_list(self) -> list[type[io.ComfyNode]]: + return [ + SetUnionControlNetType, + ControlNetInpaintingAliMamaApply, + ] -NODE_CLASS_MAPPINGS = { - "SetUnionControlNetType": SetUnionControlNetType, - "ControlNetInpaintingAliMamaApply": ControlNetInpaintingAliMamaApply, -} + +async def comfy_entrypoint() -> ControlNetExtension: + return ControlNetExtension() diff --git a/comfy_extras/nodes_easycache.py b/comfy_extras/nodes_easycache.py index c170e9fd9..1359e2f99 100644 --- a/comfy_extras/nodes_easycache.py +++ b/comfy_extras/nodes_easycache.py @@ -244,6 +244,8 @@ class EasyCacheHolder: self.total_steps_skipped += 1 batch_offset = x.shape[0] // len(uuids) for i, uuid in enumerate(uuids): + # slice out only what is relevant to this cond + batch_slice = [slice(i*batch_offset,(i+1)*batch_offset)] # if cached dims don't match x dims, cut off excess and hope for the best (cosmos world2video) if x.shape[1:] != self.uuid_cache_diffs[uuid].shape[1:]: if not self.allow_mismatch: @@ -261,9 +263,8 @@ class EasyCacheHolder: slicing.append(slice(None, dim_u)) else: slicing.append(slice(None)) - slicing = [slice(i*batch_offset,(i+1)*batch_offset)] + slicing - x = x[slicing] - x += self.uuid_cache_diffs[uuid].to(x.device) + batch_slice = batch_slice + slicing + x[batch_slice] += self.uuid_cache_diffs[uuid].to(x.device) return x def update_cache_diff(self, output: torch.Tensor, x: torch.Tensor, uuids: list[UUID]): diff --git a/comfy_extras/nodes_eps.py b/comfy_extras/nodes_eps.py index 7852d85e5..4d8061741 100644 --- a/comfy_extras/nodes_eps.py +++ b/comfy_extras/nodes_eps.py @@ -1,5 +1,7 @@ +import torch from typing_extensions import override +from comfy.k_diffusion.sampling import sigma_to_half_log_snr from comfy_api.latest import ComfyExtension, io @@ -63,12 +65,105 @@ class EpsilonScaling(io.ComfyNode): return io.NodeOutput(model_clone) +def compute_tsr_rescaling_factor( + snr: torch.Tensor, tsr_k: float, tsr_variance: float +) -> torch.Tensor: + """Compute the rescaling score ratio in Temporal Score Rescaling. + + See equation (6) in https://arxiv.org/pdf/2510.01184v1. + """ + posinf_mask = torch.isposinf(snr) + rescaling_factor = (snr * tsr_variance + 1) / (snr * tsr_variance / tsr_k + 1) + return torch.where(posinf_mask, tsr_k, rescaling_factor) # when snr → inf, r = tsr_k + + +class TemporalScoreRescaling(io.ComfyNode): + @classmethod + def define_schema(cls): + return io.Schema( + node_id="TemporalScoreRescaling", + display_name="TSR - Temporal Score Rescaling", + category="model_patches/unet", + inputs=[ + io.Model.Input("model"), + io.Float.Input( + "tsr_k", + tooltip=( + "Controls the rescaling strength.\n" + "Lower k produces more detailed results; higher k produces smoother results in image generation. Setting k = 1 disables rescaling." + ), + default=0.95, + min=0.01, + max=100.0, + step=0.001, + display_mode=io.NumberDisplay.number, + ), + io.Float.Input( + "tsr_sigma", + tooltip=( + "Controls how early rescaling takes effect.\n" + "Larger values take effect earlier." + ), + default=1.0, + min=0.01, + max=100.0, + step=0.001, + display_mode=io.NumberDisplay.number, + ), + ], + outputs=[ + io.Model.Output( + display_name="patched_model", + ), + ], + description=( + "[Post-CFG Function]\n" + "TSR - Temporal Score Rescaling (2510.01184)\n\n" + "Rescaling the model's score or noise to steer the sampling diversity.\n" + ), + ) + + @classmethod + def execute(cls, model, tsr_k, tsr_sigma) -> io.NodeOutput: + tsr_variance = tsr_sigma**2 + + def temporal_score_rescaling(args): + denoised = args["denoised"] + x = args["input"] + sigma = args["sigma"] + curr_model = args["model"] + + # No rescaling (r = 1) or no noise + if tsr_k == 1 or sigma == 0: + return denoised + + model_sampling = curr_model.current_patcher.get_model_object("model_sampling") + half_log_snr = sigma_to_half_log_snr(sigma, model_sampling) + snr = (2 * half_log_snr).exp() + + # No rescaling needed (r = 1) + if snr == 0: + return denoised + + rescaling_r = compute_tsr_rescaling_factor(snr, tsr_k, tsr_variance) + + # Derived from scaled_denoised = (x - r * sigma * noise) / alpha + alpha = sigma * half_log_snr.exp() + return torch.lerp(x / alpha, denoised, rescaling_r) + + m = model.clone() + m.set_model_sampler_post_cfg_function(temporal_score_rescaling) + return io.NodeOutput(m) + + class EpsilonScalingExtension(ComfyExtension): @override async def get_node_list(self) -> list[type[io.ComfyNode]]: return [ EpsilonScaling, + TemporalScoreRescaling, ] + async def comfy_entrypoint() -> EpsilonScalingExtension: return EpsilonScalingExtension() diff --git a/comfyui_version.py b/comfyui_version.py index d39c1fdc4..33a06bbb0 100644 --- a/comfyui_version.py +++ b/comfyui_version.py @@ -1,3 +1,3 @@ # This file is automatically generated by the build process when version is # updated in pyproject.toml. -__version__ = "0.3.65" +__version__ = "0.3.66" diff --git a/cuda_malloc.py b/cuda_malloc.py index c1d9ae3ca..6520d5123 100644 --- a/cuda_malloc.py +++ b/cuda_malloc.py @@ -1,6 +1,6 @@ import os import importlib.util -from comfy.cli_args import args +from comfy.cli_args import args, PerformanceFeature import subprocess #Can't use pytorch to get the GPU names because the cuda malloc has to be set before the first import. @@ -75,8 +75,9 @@ if not args.cuda_malloc: spec.loader.exec_module(module) version = module.__version__ - if int(version[0]) >= 2 and "+cu" in version: #enable by default for torch version 2.0 and up only on cuda torch - args.cuda_malloc = cuda_malloc_supported() + if int(version[0]) >= 2 and "+cu" in version: # enable by default for torch version 2.0 and up only on cuda torch + if PerformanceFeature.AutoTune not in args.fast: # Autotune has issues with cuda malloc + args.cuda_malloc = cuda_malloc_supported() except: pass diff --git a/pyproject.toml b/pyproject.toml index 653604e24..0c6b23a25 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [project] name = "ComfyUI" -version = "0.3.65" +version = "0.3.66" readme = "README.md" license = { file = "LICENSE" } requires-python = ">=3.9" diff --git a/requirements.txt b/requirements.txt index bbb22364f..dd2afcab0 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,5 +1,5 @@ -comfyui-frontend-package==1.27.10 -comfyui-workflow-templates==0.1.95 +comfyui-frontend-package==1.28.7 +comfyui-workflow-templates==0.2.1 comfyui-embedded-docs==0.3.0 torch torchsde diff --git a/server.py b/server.py index 80e9d3fa7..10c2698b5 100644 --- a/server.py +++ b/server.py @@ -48,6 +48,28 @@ async def send_socket_catch_exception(function, message): except (aiohttp.ClientError, aiohttp.ClientPayloadError, ConnectionResetError, BrokenPipeError, ConnectionError) as err: logging.warning("send error: {}".format(err)) +# Track deprecated paths that have been warned about to only warn once per file +_deprecated_paths_warned = set() + +@web.middleware +async def deprecation_warning(request: web.Request, handler): + """Middleware to warn about deprecated frontend API paths""" + path = request.path + + if path.startswith("/scripts/ui") or path.startswith("/extensions/core/"): + # Only warn once per unique file path + if path not in _deprecated_paths_warned: + _deprecated_paths_warned.add(path) + logging.warning( + f"[DEPRECATION WARNING] Detected import of deprecated legacy API: {path}. " + f"This is likely caused by a custom node extension using outdated APIs. " + f"Please update your extensions or contact the extension author for an updated version." + ) + + response: web.Response = await handler(request) + return response + + @web.middleware async def compress_body(request: web.Request, handler): accept_encoding = request.headers.get("Accept-Encoding", "") @@ -159,7 +181,7 @@ class PromptServer(): self.client_session:Optional[aiohttp.ClientSession] = None self.number = 0 - middlewares = [cache_control] + middlewares = [cache_control, deprecation_warning] if args.enable_compress_response_body: middlewares.append(compress_body)