diff --git a/comfy/bg_removal_model.py b/comfy/bg_removal_model.py index 7877afd7f..6dec65e63 100644 --- a/comfy/bg_removal_model.py +++ b/comfy/bg_removal_model.py @@ -44,7 +44,14 @@ class BackgroundRemovalModel(): comfy.model_management.load_model_gpu(self.patcher) H, W = image.shape[1], image.shape[2] pixel_values = comfy.clip_model.clip_preprocess(image.to(self.load_device), size=self.image_size, mean=self.image_mean, std=self.image_std, crop=False) - out = self.model(pixel_values=pixel_values) + + if pixel_values.shape[0] > 1: + out = torch.cat([ + self.model(pixel_values=pixel_values[i:i+1]) + for i in range(pixel_values.shape[0]) + ], dim=0) + else: + out = self.model(pixel_values=pixel_values) out = torch.nn.functional.interpolate(out, size=(H, W), mode="bicubic", antialias=False) mask = out.sigmoid().to(device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype()) diff --git a/comfy/latent_formats.py b/comfy/latent_formats.py index d527eec4a..6e37080bb 100644 --- a/comfy/latent_formats.py +++ b/comfy/latent_formats.py @@ -150,6 +150,7 @@ class SD3(LatentFormat): class StableAudio1(LatentFormat): latent_channels = 64 latent_dimensions = 1 + temporal_downscale_ratio = 2048 class Flux(SD3): latent_channels = 16 @@ -766,6 +767,7 @@ class ACEAudio(LatentFormat): class ACEAudio15(LatentFormat): latent_channels = 64 latent_dimensions = 1 + temporal_downscale_ratio = 1764 class ChromaRadiance(LatentFormat): latent_channels = 3 diff --git a/comfy/model_base.py b/comfy/model_base.py index e726af955..ace02b95b 100644 --- a/comfy/model_base.py +++ b/comfy/model_base.py @@ -1697,6 +1697,13 @@ class HiDreamO1(BaseModel): if text_input_ids is None or noise is None: return out + # handle area conds + area = kwargs.get("area", None) + if area is not None: + crop_h = min(noise.shape[-2] - area[2], area[0]) + crop_w = min(noise.shape[-1] - area[3], area[1]) + noise = torch.empty((noise.shape[0], 3, crop_h, crop_w), dtype=noise.dtype, device=noise.device) + conds = build_extra_conds( text_input_ids, noise, ref_images=kwargs.get("reference_latents", None), diff --git a/comfy/model_patcher.py b/comfy/model_patcher.py index 2ea14bc2c..4f9d8403e 100644 --- a/comfy/model_patcher.py +++ b/comfy/model_patcher.py @@ -1493,27 +1493,30 @@ class ModelPatcher: self.unpatch_hooks() self.clear_cached_hook_weights() - def state_dict_for_saving(self, clip_state_dict=None, vae_state_dict=None, clip_vision_state_dict=None): - original_state_dict = self.model.diffusion_model.state_dict() - unet_state_dict = {} + def model_state_dict_for_saving(self, model=None, prefix=""): + if model is None: + model = self.model + + original_state_dict = model.state_dict() + output_state_dict = {} keys = list(original_state_dict) while len(keys) > 0: k = keys.pop(0) v = original_state_dict[k] op_keys = k.rsplit('.', 1) if (len(op_keys) < 2) or op_keys[1] not in ["weight", "bias"]: - unet_state_dict[k] = v + output_state_dict[k] = v continue try: - op = comfy.utils.get_attr(self.model.diffusion_model, op_keys[0]) + op = comfy.utils.get_attr(model, op_keys[0]) except: - unet_state_dict[k] = v + output_state_dict[k] = v continue if not op or not hasattr(op, "comfy_cast_weights") or \ (hasattr(op, "comfy_patched_weights") and op.comfy_patched_weights == True): - unet_state_dict[k] = v + output_state_dict[k] = v continue - key = "diffusion_model." + k + key = prefix + k weight = comfy.utils.get_attr(self.model, key) if isinstance(weight, QuantizedTensor) and k in original_state_dict: qt_state_dict = weight.state_dict(k) @@ -1521,10 +1524,14 @@ class ModelPatcher: for group_key in (x for x in qt_state_dict if x in original_state_dict): if group_key in keys: keys.remove(group_key) - unet_state_dict.pop(group_key, "") - unet_state_dict[group_key] = LazyCastingParamPiece(caster, "diffusion_model." + group_key, original_state_dict[group_key]) + output_state_dict.pop(group_key, "") + output_state_dict[group_key] = LazyCastingParamPiece(caster, prefix + group_key, original_state_dict[group_key]) continue - unet_state_dict[k] = LazyCastingParam(self, key, weight) + output_state_dict[k] = LazyCastingParam(self, key, weight) + return output_state_dict + + def state_dict_for_saving(self, clip_state_dict=None, vae_state_dict=None, clip_vision_state_dict=None): + unet_state_dict = self.model_state_dict_for_saving(self.model.diffusion_model, "diffusion_model.") return self.model.state_dict_for_saving(unet_state_dict, clip_state_dict=clip_state_dict, vae_state_dict=vae_state_dict, clip_vision_state_dict=clip_vision_state_dict) def __del__(self): diff --git a/comfy/ops.py b/comfy/ops.py index 117cdd327..f9456854b 100644 --- a/comfy/ops.py +++ b/comfy/ops.py @@ -1376,6 +1376,7 @@ def pick_operations(weight_dtype, compute_dtype, load_device=None, disable_fast_ if not fp8_compute: disabled.add("float8_e4m3fn") disabled.add("float8_e5m2") + logging.info("Native ops: {} {}".format(", ".join(QUANT_ALGOS.keys() - disabled), ", emulated ops: {}".format(", ".join(disabled)) if len(disabled) > 0 else "")) return mixed_precision_ops(model_config.quant_config, compute_dtype, disabled=disabled) if ( diff --git a/comfy/sample.py b/comfy/sample.py index 653829582..2be0cae5f 100644 --- a/comfy/sample.py +++ b/comfy/sample.py @@ -37,11 +37,12 @@ def prepare_noise(latent_image, seed, noise_inds=None): return noises -def fix_empty_latent_channels(model, latent_image, downscale_ratio_spacial=None): +def fix_empty_latent_channels(model, latent_image, downscale_ratio_spacial=None, downscale_ratio_temporal=None): if latent_image.is_nested: return latent_image latent_format = model.get_model_object("latent_format") #Resize the empty latent image so it has the right number of channels - if torch.count_nonzero(latent_image) == 0: + is_empty = torch.count_nonzero(latent_image) == 0 + if is_empty: if latent_format.latent_channels != latent_image.shape[1]: latent_image = comfy.utils.repeat_to_batch_size(latent_image, latent_format.latent_channels, dim=1) if downscale_ratio_spacial is not None: @@ -51,6 +52,13 @@ def fix_empty_latent_channels(model, latent_image, downscale_ratio_spacial=None) if latent_format.latent_dimensions == 3 and latent_image.ndim == 4: latent_image = latent_image.unsqueeze(2) + + if is_empty and downscale_ratio_temporal is not None: + if downscale_ratio_temporal != latent_format.temporal_downscale_ratio: + ratio = downscale_ratio_temporal / latent_format.temporal_downscale_ratio + new_t = max(1, round(latent_image.shape[2] * ratio)) + latent_image = comfy.utils.repeat_to_batch_size(latent_image, new_t, dim=2) + return latent_image def prepare_sampling(model, noise_shape, positive, negative, noise_mask): diff --git a/comfy/sd.py b/comfy/sd.py index 1a0041ad5..d48a02f67 100644 --- a/comfy/sd.py +++ b/comfy/sd.py @@ -438,6 +438,13 @@ class CLIP: sd_clip[k] = sd_tokenizer[k] return sd_clip + def state_dict_for_saving(self): + sd_clip = self.patcher.model_state_dict_for_saving() + sd_tokenizer = self.tokenizer.state_dict() + for k in sd_tokenizer: + sd_clip[k] = sd_tokenizer[k] + return sd_clip + def load_model(self, tokens={}): memory_used = 0 if hasattr(self.cond_stage_model, "memory_estimation_function"): @@ -1923,7 +1930,7 @@ def save_checkpoint(output_path, model, clip=None, vae=None, clip_vision=None, m load_models = [model] if clip is not None: load_models.append(clip.load_model()) - clip_sd = clip.get_sd() + clip_sd = clip.state_dict_for_saving() vae_sd = None if vae is not None: vae_sd = vae.get_sd() diff --git a/comfy/text_encoders/qwen35.py b/comfy/text_encoders/qwen35.py index b022009b1..416ce9d18 100644 --- a/comfy/text_encoders/qwen35.py +++ b/comfy/text_encoders/qwen35.py @@ -760,7 +760,7 @@ class Qwen35ImageTokenizer(sd1_clip.SD1Tokenizer): def tokenize_with_weights(self, text, return_word_ids=False, llama_template=None, images=[], prevent_empty_text=False, thinking=False, **kwargs): image = kwargs.get("image", None) if image is not None and len(images) == 0: - images = [image] + images = [image[i:i + 1] for i in range(image.shape[0])] skip_template = False if text.startswith('<|im_start|>'): @@ -771,13 +771,16 @@ class Qwen35ImageTokenizer(sd1_clip.SD1Tokenizer): if skip_template: llama_text = text else: - if llama_template is None: - if len(images) > 0: - llama_text = self.llama_template_images.format(text) - else: - llama_text = self.llama_template.format(text) + if llama_template is not None: + template = llama_template + elif len(images) == 0: + template = self.llama_template else: - llama_text = llama_template.format(text) + template = self.llama_template_images + if len(images) > 1: + vision_block = "<|vision_start|><|image_pad|><|vision_end|>" + template = template.replace(vision_block, vision_block * len(images), 1) + llama_text = template.format(text) if not thinking: llama_text += "\n\n" diff --git a/comfy_api_nodes/apis/bytedance_llm.py b/comfy_api_nodes/apis/bytedance_llm.py new file mode 100644 index 000000000..654c875fc --- /dev/null +++ b/comfy_api_nodes/apis/bytedance_llm.py @@ -0,0 +1,101 @@ +"""Pydantic models for BytePlus ModelArk Responses API. + +See: https://docs.byteplus.com/en/docs/ModelArk/1585128 (request) + https://docs.byteplus.com/en/docs/ModelArk/1783703 (response) +""" + +from typing import Literal + +from pydantic import BaseModel, Field + + +class BytePlusInputText(BaseModel): + type: Literal["input_text"] = "input_text" + text: str = Field(...) + + +class BytePlusInputImage(BaseModel): + type: Literal["input_image"] = "input_image" + image_url: str = Field(..., description="Image URL or `data:image/...;base64,...` payload") + detail: str = Field("auto", description="One of high, low, auto") + + +class BytePlusInputVideo(BaseModel): + type: Literal["input_video"] = "input_video" + video_url: str = Field(..., description="Video URL or `data:video/...;base64,...` payload") + fps: float | None = Field(None, ge=0.2, le=5.0) + + +BytePlusMessageContent = BytePlusInputText | BytePlusInputImage | BytePlusInputVideo + + +class BytePlusInputMessage(BaseModel): + type: Literal["message"] = "message" + role: str = Field(..., description="One of user, system, assistant, developer") + content: list[BytePlusMessageContent] = Field(...) + + +class BytePlusResponseCreateRequest(BaseModel): + model: str = Field(...) + input: list[BytePlusInputMessage] = Field(...) + instructions: str | None = Field(None) + max_output_tokens: int | None = Field(None, ge=1) + temperature: float | None = Field(None, ge=0.0, le=2.0) + store: bool | None = Field(False) + stream: bool | None = Field(False) + + +class BytePlusOutputText(BaseModel): + type: Literal["output_text"] = "output_text" + text: str = Field(...) + + +class BytePlusOutputRefusal(BaseModel): + type: Literal["refusal"] = "refusal" + refusal: str = Field(...) + + +class BytePlusOutputContent(BaseModel): + type: str = Field(...) + text: str | None = Field(None) + refusal: str | None = Field(None) + + +class BytePlusOutputMessage(BaseModel): + type: str = Field(...) + id: str | None = Field(None) + role: str | None = Field(None) + status: str | None = Field(None) + content: list[BytePlusOutputContent] | None = Field(None) + + +class BytePlusInputTokensDetails(BaseModel): + cached_tokens: int | None = Field(None) + + +class BytePlusOutputTokensDetails(BaseModel): + reasoning_tokens: int | None = Field(None) + + +class BytePlusResponseUsage(BaseModel): + input_tokens: int | None = Field(None) + output_tokens: int | None = Field(None) + total_tokens: int | None = Field(None) + input_tokens_details: BytePlusInputTokensDetails | None = Field(None) + output_tokens_details: BytePlusOutputTokensDetails | None = Field(None) + + +class BytePlusResponseError(BaseModel): + code: str = Field(...) + message: str = Field(...) + + +class BytePlusResponseObject(BaseModel): + id: str | None = Field(None) + object: str | None = Field(None) + created_at: int | None = Field(None) + model: str | None = Field(None) + status: str | None = Field(None) + error: BytePlusResponseError | None = Field(None) + output: list[BytePlusOutputMessage] | None = Field(None) + usage: BytePlusResponseUsage | None = Field(None) diff --git a/comfy_api_nodes/nodes_anthropic.py b/comfy_api_nodes/nodes_anthropic.py index 60e1624f7..28dd70d4e 100644 --- a/comfy_api_nodes/nodes_anthropic.py +++ b/comfy_api_nodes/nodes_anthropic.py @@ -49,7 +49,7 @@ def _claude_model_inputs(): min=0.0, max=1.0, step=0.01, - tooltip="Controls randomness. 0.0 is deterministic, 1.0 is most random.", + tooltip="Controls randomness. 0.0 is deterministic, 1.0 is most random. Ignored for Opus 4.7.", advanced=True, ), ] @@ -208,7 +208,7 @@ class ClaudeNode(IO.ComfyNode): validate_string(prompt, strip_whitespace=True, min_length=1) model_label = model["model"] max_tokens = model["max_tokens"] - temperature = model["temperature"] + temperature = None if model_label == "Opus 4.7" else model["temperature"] image_tensors: list[Input.Image] = [t for t in (images or {}).values() if t is not None] if sum(get_number_of_images(t) for t in image_tensors) > CLAUDE_MAX_IMAGES: diff --git a/comfy_api_nodes/nodes_bytedance_llm.py b/comfy_api_nodes/nodes_bytedance_llm.py new file mode 100644 index 000000000..fa7fe370a --- /dev/null +++ b/comfy_api_nodes/nodes_bytedance_llm.py @@ -0,0 +1,271 @@ +"""API Nodes for ByteDance Seed LLM via the BytePlus ModelArk Responses API. + +See: https://docs.byteplus.com/en/docs/ModelArk/1585128 +""" + +from typing_extensions import override + +from comfy_api.latest import IO, ComfyExtension, Input +from comfy_api_nodes.apis.bytedance_llm import ( + BytePlusInputImage, + BytePlusInputMessage, + BytePlusInputText, + BytePlusInputVideo, + BytePlusMessageContent, + BytePlusResponseCreateRequest, + BytePlusResponseObject, +) +from comfy_api_nodes.util import ( + ApiEndpoint, + get_number_of_images, + sync_op, + upload_images_to_comfyapi, + upload_video_to_comfyapi, + validate_string, +) + +BYTEPLUS_RESPONSES_ENDPOINT = "/proxy/byteplus/api/v3/responses" +SEED_MAX_IMAGES = 20 +SEED_MAX_VIDEOS = 4 + +SEED_MODELS: dict[str, str] = { + "Seed 2.0 Pro": "seed-2-0-pro-260328", + "Seed 2.0 Lite": "seed-2-0-lite-260228", + "Seed 2.0 Mini": "seed-2-0-mini-260215", +} + +# USD per 1M tokens: (input, cache_hit_input, output) +_SEED_PRICES_PER_MILLION: dict[str, tuple[float, float, float]] = { + "seed-2-0-pro-260328": (0.50, 0.10, 3.00), + "seed-2-0-lite-260228": (0.25, 0.05, 2.00), + "seed-2-0-mini-260215": (0.10, 0.02, 0.40), +} + + +def _seed_model_inputs(max_images: int = SEED_MAX_IMAGES, max_videos: int = SEED_MAX_VIDEOS): + return [ + IO.Autogrow.Input( + "images", + template=IO.Autogrow.TemplateNames( + IO.Image.Input("image"), + names=[f"image_{i}" for i in range(1, max_images + 1)], + min=0, + ), + tooltip=f"Optional image(s) to use as context for the model. Up to {max_images} images.", + ), + IO.Autogrow.Input( + "videos", + template=IO.Autogrow.TemplateNames( + IO.Video.Input("video"), + names=[f"video_{i}" for i in range(1, max_videos + 1)], + min=0, + ), + tooltip=f"Optional video(s) to use as context for the model. Up to {max_videos} videos.", + ), + IO.Float.Input( + "temperature", + default=1.0, + min=0.0, + max=2.0, + step=0.01, + tooltip="Controls randomness. 0.0 is deterministic, higher values are more random.", + advanced=True, + ), + ] + + +def _calculate_price(model_id: str, response: BytePlusResponseObject) -> float | None: + """Compute approximate USD price from response usage.""" + if not response.usage: + return None + rates = _SEED_PRICES_PER_MILLION.get(model_id) + if rates is None: + return None + input_rate, cache_hit_rate, output_rate = rates + input_tokens = response.usage.input_tokens or 0 + output_tokens = response.usage.output_tokens or 0 + cached = 0 + if response.usage.input_tokens_details: + cached = response.usage.input_tokens_details.cached_tokens or 0 + fresh_input = max(0, input_tokens - cached) + total = fresh_input * input_rate + cached * cache_hit_rate + output_tokens * output_rate + return total / 1_000_000.0 + + +def _get_text_from_response(response: BytePlusResponseObject) -> str: + """Extract concatenated text from all assistant message output_text blocks.""" + if not response.output: + return "" + chunks: list[str] = [] + for item in response.output: + if item.type != "message" or not item.content: + continue + for block in item.content: + if block.type == "output_text" and block.text: + chunks.append(block.text) + elif block.type == "refusal" and block.refusal: + raise ValueError(f"Model refused to respond: {block.refusal}") + return "\n".join(chunks) + + +async def _build_image_content_blocks( + cls: type[IO.ComfyNode], + image_tensors: list[Input.Image], +) -> list[BytePlusInputImage]: + urls = await upload_images_to_comfyapi( + cls, + image_tensors, + max_images=SEED_MAX_IMAGES, + wait_label="Uploading reference images", + ) + return [BytePlusInputImage(image_url=url) for url in urls] + + +async def _build_video_content_blocks( + cls: type[IO.ComfyNode], + videos: list[Input.Video], +) -> list[BytePlusInputVideo]: + blocks: list[BytePlusInputVideo] = [] + total = len(videos) + for idx, video in enumerate(videos): + label = "Uploading reference video" + if total > 1: + label = f"{label} ({idx + 1}/{total})" + url = await upload_video_to_comfyapi(cls, video, wait_label=label) + blocks.append(BytePlusInputVideo(video_url=url)) + return blocks + + +class ByteDanceSeedNode(IO.ComfyNode): + """Generate text responses from a ByteDance Seed 2.0 model.""" + + @classmethod + def define_schema(cls): + return IO.Schema( + node_id="ByteDanceSeedNode", + display_name="ByteDance Seed", + category="api node/text/ByteDance", + essentials_category="Text Generation", + description="Generate text responses with ByteDance's Seed 2.0 models. " + "Provide a text prompt and optionally one or more images or videos for multimodal context.", + inputs=[ + IO.String.Input( + "prompt", + multiline=True, + default="", + tooltip="Text input to the model.", + ), + IO.DynamicCombo.Input( + "model", + options=[IO.DynamicCombo.Option(label, _seed_model_inputs()) for label in SEED_MODELS], + tooltip="The Seed model used to generate the response.", + ), + IO.Int.Input( + "seed", + default=0, + min=0, + max=2147483647, + control_after_generate=True, + tooltip="Seed controls whether the node should re-run; " + "results are non-deterministic regardless of seed.", + ), + IO.String.Input( + "system_prompt", + multiline=True, + default="", + optional=True, + advanced=True, + tooltip="Foundational instructions that dictate the model's behavior.", + ), + ], + outputs=[IO.String.Output()], + hidden=[ + IO.Hidden.auth_token_comfy_org, + IO.Hidden.api_key_comfy_org, + IO.Hidden.unique_id, + ], + is_api_node=True, + price_badge=IO.PriceBadge( + depends_on=IO.PriceBadgeDepends(widgets=["model"]), + expr=""" + ( + $m := widgets.model; + $contains($m, "mini") ? { + "type": "list_usd", + "usd": [0.00025, 0.0009], + "format": { "approximate": true, "separator": "-", "suffix": " per 1K tokens" } + } + : $contains($m, "lite") ? { + "type": "list_usd", + "usd": [0.0003, 0.002], + "format": { "approximate": true, "separator": "-", "suffix": " per 1K tokens" } + } + : $contains($m, "pro") ? { + "type": "list_usd", + "usd": [0.0005, 0.003], + "format": { "approximate": true, "separator": "-", "suffix": " per 1K tokens" } + } + : {"type":"text", "text":"Token-based"} + ) + """, + ), + ) + + @classmethod + async def execute( + cls, + prompt: str, + model: dict, + seed: int, + system_prompt: str = "", + ) -> IO.NodeOutput: + validate_string(prompt, strip_whitespace=True, min_length=1) + model_label = model["model"] + temperature = model["temperature"] + model_id = SEED_MODELS[model_label] + + image_tensors: list[Input.Image] = [t for t in (model.get("images") or {}).values() if t is not None] + if sum(get_number_of_images(t) for t in image_tensors) > SEED_MAX_IMAGES: + raise ValueError(f"Up to {SEED_MAX_IMAGES} images are supported per request.") + + video_inputs: list[Input.Video] = [v for v in (model.get("videos") or {}).values() if v is not None] + if len(video_inputs) > SEED_MAX_VIDEOS: + raise ValueError(f"Up to {SEED_MAX_VIDEOS} videos are supported per request.") + + content: list[BytePlusMessageContent] = [] + if image_tensors: + content.extend(await _build_image_content_blocks(cls, image_tensors)) + if video_inputs: + content.extend(await _build_video_content_blocks(cls, video_inputs)) + content.append(BytePlusInputText(text=prompt)) + + response = await sync_op( + cls, + ApiEndpoint(path=BYTEPLUS_RESPONSES_ENDPOINT, method="POST"), + response_model=BytePlusResponseObject, + data=BytePlusResponseCreateRequest( + model=model_id, + input=[BytePlusInputMessage(role="user", content=content)], + instructions=system_prompt or None, + temperature=temperature, + store=False, + stream=False, + ), + price_extractor=lambda r: _calculate_price(model_id, r), + ) + if response.error: + raise ValueError(f"Seed API error ({response.error.code}): {response.error.message}") + result = _get_text_from_response(response) + if not result: + raise ValueError("Empty response from Seed model.") + return IO.NodeOutput(result) + + +class ByteDanceLLMExtension(ComfyExtension): + @override + async def get_node_list(self) -> list[type[IO.ComfyNode]]: + return [ByteDanceSeedNode] + + +async def comfy_entrypoint() -> ByteDanceLLMExtension: + return ByteDanceLLMExtension() diff --git a/comfy_extras/nodes_ace.py b/comfy_extras/nodes_ace.py index affcf3b71..247d9ae8a 100644 --- a/comfy_extras/nodes_ace.py +++ b/comfy_extras/nodes_ace.py @@ -104,7 +104,7 @@ class EmptyAceStep15LatentAudio(IO.ComfyNode): def execute(cls, seconds, batch_size) -> IO.NodeOutput: length = round((seconds * 48000 / 1920)) latent = torch.zeros([batch_size, 64, length], device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype()) - return IO.NodeOutput({"samples": latent, "type": "audio"}) + return IO.NodeOutput({"samples": latent, "type": "audio", "downscale_ratio_temporal": 1764}) class ReferenceAudio(IO.ComfyNode): @classmethod diff --git a/comfy_extras/nodes_advanced_samplers.py b/comfy_extras/nodes_advanced_samplers.py index 567c37be0..20717ca38 100644 --- a/comfy_extras/nodes_advanced_samplers.py +++ b/comfy_extras/nodes_advanced_samplers.py @@ -45,7 +45,7 @@ class SamplerLCMUpscale(io.ComfyNode): def define_schema(cls) -> io.Schema: return io.Schema( node_id="SamplerLCMUpscale", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Float.Input("scale_ratio", default=1.0, min=0.1, max=20.0, step=0.01, advanced=True), io.Int.Input("scale_steps", default=-1, min=-1, max=1000, step=1, advanced=True), @@ -123,7 +123,7 @@ class SamplerEulerCFGpp(io.ComfyNode): return io.Schema( node_id="SamplerEulerCFGpp", display_name="SamplerEulerCFG++", - category="experimental", # "sampling/custom_sampling/samplers" + category="experimental", # "sampling/samplers" inputs=[ io.Combo.Input("version", options=["regular", "alternative"], advanced=True), ], diff --git a/comfy_extras/nodes_align_your_steps.py b/comfy_extras/nodes_align_your_steps.py index 4fc511d2c..307f41337 100644 --- a/comfy_extras/nodes_align_your_steps.py +++ b/comfy_extras/nodes_align_your_steps.py @@ -29,7 +29,7 @@ class AlignYourStepsScheduler(io.ComfyNode): return io.Schema( node_id="AlignYourStepsScheduler", search_aliases=["AYS scheduler"], - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Combo.Input("model_type", options=["SD1", "SDXL", "SVD"]), io.Int.Input("steps", default=10, min=1, max=10000), diff --git a/comfy_extras/nodes_ar_video.py b/comfy_extras/nodes_ar_video.py index b36588b14..1a15facfa 100644 --- a/comfy_extras/nodes_ar_video.py +++ b/comfy_extras/nodes_ar_video.py @@ -53,7 +53,7 @@ class SamplerARVideo(io.ComfyNode): return io.Schema( node_id="SamplerARVideo", display_name="Sampler AR Video", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Int.Input( "num_frame_per_block", diff --git a/comfy_extras/nodes_audio.py b/comfy_extras/nodes_audio.py index fcc1c34d5..2d6b3c7ea 100644 --- a/comfy_extras/nodes_audio.py +++ b/comfy_extras/nodes_audio.py @@ -33,7 +33,7 @@ class EmptyLatentAudio(IO.ComfyNode): def execute(cls, seconds, batch_size) -> IO.NodeOutput: length = round((seconds * 44100 / 2048) / 2) * 2 latent = torch.zeros([batch_size, 64, length], device=comfy.model_management.intermediate_device()) - return IO.NodeOutput({"samples":latent, "type": "audio"}) + return IO.NodeOutput({"samples": latent, "type": "audio", "downscale_ratio_temporal": 2048}) generate = execute # TODO: remove diff --git a/comfy_extras/nodes_bg_removal.py b/comfy_extras/nodes_bg_removal.py index 8d046b8d4..793fd802b 100644 --- a/comfy_extras/nodes_bg_removal.py +++ b/comfy_extras/nodes_bg_removal.py @@ -34,6 +34,7 @@ class RemoveBackground(IO.ComfyNode): node_id="RemoveBackground", display_name="Remove Background", category="image/background removal", + description="Generates a foreground mask to remove the background from an image using a background removal model.", inputs=[ IO.Image.Input("image", tooltip="Input image to remove the background from"), IO.BackgroundRemoval.Input("bg_removal_model", tooltip="Background removal model used to generate the mask") diff --git a/comfy_extras/nodes_canny.py b/comfy_extras/nodes_canny.py index 648b4279d..462f6fea0 100644 --- a/comfy_extras/nodes_canny.py +++ b/comfy_extras/nodes_canny.py @@ -11,9 +11,9 @@ class Canny(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="Canny", - display_name="Canny", + display_name="Detect Edges (Canny)", search_aliases=["edge detection", "outline", "contour detection", "line art"], - category="image/preprocessors", + category="image/filters", essentials_category="Image Tools", inputs=[ io.Image.Input("image"), diff --git a/comfy_extras/nodes_compositing.py b/comfy_extras/nodes_compositing.py index 720efc629..8fcbe720e 100644 --- a/comfy_extras/nodes_compositing.py +++ b/comfy_extras/nodes_compositing.py @@ -111,7 +111,7 @@ class PorterDuffImageComposite(io.ComfyNode): node_id="PorterDuffImageComposite", search_aliases=["alpha composite", "blend modes", "layer blend", "transparency blend"], display_name="Porter-Duff Image Composite", - category="mask/compositing", + category="image/compositing", inputs=[ io.Image.Input("source"), io.Mask.Input("source_alpha"), @@ -168,7 +168,7 @@ class SplitImageWithAlpha(io.ComfyNode): node_id="SplitImageWithAlpha", search_aliases=["extract alpha", "separate transparency", "remove alpha"], display_name="Split Image with Alpha", - category="mask/compositing", + category="image/compositing", inputs=[ io.Image.Input("image"), ], @@ -192,7 +192,7 @@ class JoinImageWithAlpha(io.ComfyNode): node_id="JoinImageWithAlpha", search_aliases=["add transparency", "apply alpha", "composite alpha", "RGBA"], display_name="Join Image with Alpha", - category="mask/compositing", + category="image/compositing", inputs=[ io.Image.Input("image"), io.Mask.Input("alpha"), diff --git a/comfy_extras/nodes_custom_sampler.py b/comfy_extras/nodes_custom_sampler.py index c67145d2d..10b56b91c 100644 --- a/comfy_extras/nodes_custom_sampler.py +++ b/comfy_extras/nodes_custom_sampler.py @@ -17,7 +17,7 @@ class BasicScheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="BasicScheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Model.Input("model"), io.Combo.Input("scheduler", options=comfy.samplers.SCHEDULER_NAMES), @@ -47,7 +47,7 @@ class KarrasScheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="KarrasScheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Int.Input("steps", default=20, min=1, max=10000), io.Float.Input("sigma_max", default=14.614642, min=0.0, max=5000.0, step=0.01, round=False, advanced=True), @@ -69,7 +69,7 @@ class ExponentialScheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="ExponentialScheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Int.Input("steps", default=20, min=1, max=10000), io.Float.Input("sigma_max", default=14.614642, min=0.0, max=5000.0, step=0.01, round=False, advanced=True), @@ -90,7 +90,7 @@ class PolyexponentialScheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="PolyexponentialScheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Int.Input("steps", default=20, min=1, max=10000), io.Float.Input("sigma_max", default=14.614642, min=0.0, max=5000.0, step=0.01, round=False, advanced=True), @@ -112,7 +112,7 @@ class LaplaceScheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="LaplaceScheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Int.Input("steps", default=20, min=1, max=10000), io.Float.Input("sigma_max", default=14.614642, min=0.0, max=5000.0, step=0.01, round=False, advanced=True), @@ -136,7 +136,7 @@ class SDTurboScheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SDTurboScheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Model.Input("model"), io.Int.Input("steps", default=1, min=1, max=10), @@ -160,7 +160,7 @@ class BetaSamplingScheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="BetaSamplingScheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Model.Input("model"), io.Int.Input("steps", default=20, min=1, max=10000), @@ -182,7 +182,7 @@ class VPScheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="VPScheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Int.Input("steps", default=20, min=1, max=10000), io.Float.Input("beta_d", default=19.9, min=0.0, max=5000.0, step=0.01, round=False, advanced=True), #TODO: fix default values @@ -204,7 +204,7 @@ class SplitSigmas(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SplitSigmas", - category="sampling/custom_sampling/sigmas", + category="sampling/sigmas", inputs=[ io.Sigmas.Input("sigmas"), io.Int.Input("step", default=0, min=0, max=10000), @@ -228,7 +228,7 @@ class SplitSigmasDenoise(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SplitSigmasDenoise", - category="sampling/custom_sampling/sigmas", + category="sampling/sigmas", inputs=[ io.Sigmas.Input("sigmas"), io.Float.Input("denoise", default=1.0, min=0.0, max=1.0, step=0.01), @@ -254,7 +254,7 @@ class FlipSigmas(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="FlipSigmas", - category="sampling/custom_sampling/sigmas", + category="sampling/sigmas", inputs=[io.Sigmas.Input("sigmas")], outputs=[io.Sigmas.Output()] ) @@ -276,7 +276,7 @@ class SetFirstSigma(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SetFirstSigma", - category="sampling/custom_sampling/sigmas", + category="sampling/sigmas", inputs=[ io.Sigmas.Input("sigmas"), io.Float.Input("sigma", default=136.0, min=0.0, max=20000.0, step=0.001, round=False), @@ -298,7 +298,7 @@ class ExtendIntermediateSigmas(io.ComfyNode): return io.Schema( node_id="ExtendIntermediateSigmas", search_aliases=["interpolate sigmas"], - category="sampling/custom_sampling/sigmas", + category="sampling/sigmas", inputs=[ io.Sigmas.Input("sigmas"), io.Int.Input("steps", default=2, min=1, max=100), @@ -351,7 +351,7 @@ class SamplingPercentToSigma(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SamplingPercentToSigma", - category="sampling/custom_sampling/sigmas", + category="sampling/sigmas", inputs=[ io.Model.Input("model"), io.Float.Input("sampling_percent", default=0.0, min=0.0, max=1.0, step=0.0001), @@ -379,7 +379,7 @@ class KSamplerSelect(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="KSamplerSelect", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[io.Combo.Input("sampler_name", options=comfy.samplers.SAMPLER_NAMES)], outputs=[io.Sampler.Output()] ) @@ -396,7 +396,7 @@ class SamplerDPMPP_3M_SDE(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SamplerDPMPP_3M_SDE", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Float.Input("eta", default=1.0, min=0.0, max=100.0, step=0.01, round=False, advanced=True), io.Float.Input("s_noise", default=1.0, min=0.0, max=100.0, step=0.01, round=False, advanced=True), @@ -421,7 +421,7 @@ class SamplerDPMPP_2M_SDE(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SamplerDPMPP_2M_SDE", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Combo.Input("solver_type", options=['midpoint', 'heun']), io.Float.Input("eta", default=1.0, min=0.0, max=100.0, step=0.01, round=False, advanced=True), @@ -448,7 +448,7 @@ class SamplerDPMPP_SDE(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SamplerDPMPP_SDE", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Float.Input("eta", default=1.0, min=0.0, max=100.0, step=0.01, round=False, advanced=True), io.Float.Input("s_noise", default=1.0, min=0.0, max=100.0, step=0.01, round=False, advanced=True), @@ -474,7 +474,7 @@ class SamplerDPMPP_2S_Ancestral(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SamplerDPMPP_2S_Ancestral", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Float.Input("eta", default=1.0, min=0.0, max=100.0, step=0.01, round=False), io.Float.Input("s_noise", default=1.0, min=0.0, max=100.0, step=0.01, round=False), @@ -494,7 +494,7 @@ class SamplerEulerAncestral(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SamplerEulerAncestral", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Float.Input("eta", default=1.0, min=0.0, max=100.0, step=0.01, round=False, advanced=True), io.Float.Input("s_noise", default=1.0, min=0.0, max=100.0, step=0.01, round=False, advanced=True), @@ -515,7 +515,7 @@ class SamplerEulerAncestralCFGPP(io.ComfyNode): return io.Schema( node_id="SamplerEulerAncestralCFGPP", display_name="SamplerEulerAncestralCFG++", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Float.Input("eta", default=1.0, min=0.0, max=1.0, step=0.01, round=False), io.Float.Input("s_noise", default=1.0, min=0.0, max=10.0, step=0.01, round=False), @@ -537,7 +537,7 @@ class SamplerLMS(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SamplerLMS", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[io.Int.Input("order", default=4, min=1, max=100, advanced=True)], outputs=[io.Sampler.Output()] ) @@ -554,7 +554,7 @@ class SamplerDPMAdaptative(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SamplerDPMAdaptative", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Int.Input("order", default=3, min=2, max=3, advanced=True), io.Float.Input("rtol", default=0.05, min=0.0, max=100.0, step=0.01, round=False, advanced=True), @@ -585,7 +585,7 @@ class SamplerER_SDE(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SamplerER_SDE", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Combo.Input("solver_type", options=["ER-SDE", "Reverse-time SDE", "ODE"]), io.Int.Input("max_stage", default=3, min=1, max=3, advanced=True), @@ -623,7 +623,7 @@ class SamplerSASolver(io.ComfyNode): return io.Schema( node_id="SamplerSASolver", search_aliases=["sde"], - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Model.Input("model"), io.Float.Input("eta", default=1.0, min=0.0, max=10.0, step=0.01, round=False, advanced=True), @@ -668,7 +668,7 @@ class SamplerSEEDS2(io.ComfyNode): return io.Schema( node_id="SamplerSEEDS2", search_aliases=["sde", "exp heun"], - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[ io.Combo.Input("solver_type", options=["phi_1", "phi_2"]), io.Float.Input("eta", default=1.0, min=0.0, max=100.0, step=0.01, round=False, tooltip="Stochastic strength", advanced=True), @@ -750,7 +750,7 @@ class SamplerCustom(io.ComfyNode): latent = latent_image latent_image = latent["samples"] latent = latent.copy() - latent_image = comfy.sample.fix_empty_latent_channels(model, latent_image, latent.get("downscale_ratio_spacial", None)) + latent_image = comfy.sample.fix_empty_latent_channels(model, latent_image, latent.get("downscale_ratio_spacial", None), latent.get("downscale_ratio_temporal", None)) latent["samples"] = latent_image if not add_noise: @@ -770,6 +770,7 @@ class SamplerCustom(io.ComfyNode): out = latent.copy() out.pop("downscale_ratio_spacial", None) + out.pop("downscale_ratio_temporal", None) out["samples"] = samples if "x0" in x0_output: x0_out = model.model.process_latent_out(x0_output["x0"].cpu()) @@ -793,7 +794,8 @@ class BasicGuider(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="BasicGuider", - category="sampling/custom_sampling/guiders", + display_name="Basic Guider", + category="sampling/guiders", inputs=[ io.Model.Input("model"), io.Conditioning.Input("conditioning"), @@ -814,7 +816,8 @@ class CFGGuider(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="CFGGuider", - category="sampling/custom_sampling/guiders", + display_name="CFG Guider", + category="sampling/guiders", inputs=[ io.Model.Input("model"), io.Conditioning.Input("positive"), @@ -868,7 +871,8 @@ class DualCFGGuider(io.ComfyNode): return io.Schema( node_id="DualCFGGuider", search_aliases=["dual prompt guidance"], - category="sampling/custom_sampling/guiders", + display_name="Dual CFG Guider", + category="sampling/guiders", inputs=[ io.Model.Input("model"), io.Conditioning.Input("cond1"), @@ -896,7 +900,7 @@ class DisableNoise(io.ComfyNode): return io.Schema( node_id="DisableNoise", search_aliases=["zero noise"], - category="sampling/custom_sampling/noise", + category="sampling/noise", inputs=[], outputs=[io.Noise.Output()] ) @@ -913,7 +917,7 @@ class RandomNoise(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="RandomNoise", - category="sampling/custom_sampling/noise", + category="sampling/noise", inputs=[io.Int.Input("noise_seed", default=0, min=0, max=0xffffffffffffffff, control_after_generate=True)], outputs=[io.Noise.Output()] ) @@ -949,7 +953,7 @@ class SamplerCustomAdvanced(io.ComfyNode): latent = latent_image latent_image = latent["samples"] latent = latent.copy() - latent_image = comfy.sample.fix_empty_latent_channels(guider.model_patcher, latent_image, latent.get("downscale_ratio_spacial", None)) + latent_image = comfy.sample.fix_empty_latent_channels(guider.model_patcher, latent_image, latent.get("downscale_ratio_spacial", None), latent.get("downscale_ratio_temporal", None)) latent["samples"] = latent_image noise_mask = None @@ -965,6 +969,7 @@ class SamplerCustomAdvanced(io.ComfyNode): out = latent.copy() out.pop("downscale_ratio_spacial", None) + out.pop("downscale_ratio_temporal", None) out["samples"] = samples if "x0" in x0_output: x0_out = guider.model_patcher.model.process_latent_out(x0_output["x0"].cpu()) diff --git a/comfy_extras/nodes_flux.py b/comfy_extras/nodes_flux.py index 5e04a5f77..997f21c09 100644 --- a/comfy_extras/nodes_flux.py +++ b/comfy_extras/nodes_flux.py @@ -215,7 +215,7 @@ class Flux2Scheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="Flux2Scheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Int.Input("steps", default=20, min=1, max=4096), io.Int.Input("width", default=1024, min=16, max=nodes.MAX_RESOLUTION, step=1), @@ -263,7 +263,7 @@ class FluxKVCache(io.ComfyNode): node_id="FluxKVCache", display_name="Flux KV Cache", description="Enables KV Cache optimization for reference images on Flux family models.", - category="", + category="experimental", is_experimental=True, inputs=[ io.Model.Input("model", tooltip="The model to use KV Cache on."), diff --git a/comfy_extras/nodes_gits.py b/comfy_extras/nodes_gits.py index d48483862..0b7666524 100644 --- a/comfy_extras/nodes_gits.py +++ b/comfy_extras/nodes_gits.py @@ -340,7 +340,7 @@ class GITSScheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="GITSScheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Float.Input("coeff", default=1.20, min=0.80, max=1.50, step=0.05, advanced=True), io.Int.Input("steps", default=10, min=2, max=1000), diff --git a/comfy_extras/nodes_images.py b/comfy_extras/nodes_images.py index e48b2ea2d..6326c5be8 100644 --- a/comfy_extras/nodes_images.py +++ b/comfy_extras/nodes_images.py @@ -162,7 +162,7 @@ class ImageAddNoise(IO.ComfyNode): node_id="ImageAddNoise", search_aliases=["film grain"], display_name="Add Noise to Image", - category="image/postprocessing", + category="image/filters", inputs=[ IO.Image.Input("image"), IO.Int.Input( @@ -194,7 +194,8 @@ class SaveAnimatedWEBP(IO.ComfyNode): def define_schema(cls): return IO.Schema( node_id="SaveAnimatedWEBP", - category="image/animation", + display_name="Save Animated WEBP", + category="image", inputs=[ IO.Image.Input("images"), IO.String.Input("filename_prefix", default="ComfyUI"), @@ -231,7 +232,8 @@ class SaveAnimatedPNG(IO.ComfyNode): def define_schema(cls): return IO.Schema( node_id="SaveAnimatedPNG", - category="image/animation", + display_name="Save Animated PNG", + category="image", inputs=[ IO.Image.Input("images"), IO.String.Input("filename_prefix", default="ComfyUI"), @@ -493,7 +495,7 @@ class SaveSVGNode(IO.ComfyNode): search_aliases=["export vector", "save vector graphics"], display_name="Save SVG", description="Save SVG files on disk.", - category="image/save", + category="image", inputs=[ IO.SVG.Input("svg"), IO.String.Input( diff --git a/comfy_extras/nodes_lt.py b/comfy_extras/nodes_lt.py index fdae458e5..675de4f81 100644 --- a/comfy_extras/nodes_lt.py +++ b/comfy_extras/nodes_lt.py @@ -175,7 +175,7 @@ class LTXVImgToVideoInplace(io.ComfyNode): generate = execute # TODO: remove -def _append_guide_attention_entry(positive, negative, pre_filter_count, latent_shape, strength=1.0): +def _append_guide_attention_entry(positive, negative, pre_filter_count, latent_shape, strength=1.0, attention_mask=None): """Append a guide_attention_entry to both positive and negative conditioning. Each entry tracks one guide reference for per-reference attention control. @@ -184,9 +184,10 @@ def _append_guide_attention_entry(positive, negative, pre_filter_count, latent_s new_entry = { "pre_filter_count": pre_filter_count, "strength": strength, - "pixel_mask": None, + "pixel_mask": attention_mask.unsqueeze(0).unsqueeze(0) if attention_mask is not None else None, # reshape to (1, 1, F, H, W) "latent_shape": latent_shape, } + results = [] for cond in (positive, negative): # Read existing entries from this specific conditioning @@ -196,8 +197,7 @@ def _append_guide_attention_entry(positive, negative, pre_filter_count, latent_s if found is not None: existing = found break - # Shallow copy and append (no deepcopy needed — entries contain - # only scalars and None for pixel_mask at this call site). + # Shallow copy only and append (pixel_mask is never mutated). entries = [*existing, new_entry] results.append(node_helpers.conditioning_set_values( cond, {"guide_attention_entries": entries} @@ -263,6 +263,12 @@ class LTXVAddGuide(io.ComfyNode): "down to the nearest multiple of 8. Negative values are counted from the end of the video.", ), io.Float.Input("strength", default=1.0, min=0.0, max=10.0, step=0.01), + io.Mask.Input( + "attention_mask", + optional=True, + tooltip="Optional pixel-space spatial mask. Controls per-region " + "conditioning influence via self-attention, multiplied by strength.", + ), ICLoRAParameters.Input( "iclora_parameters", optional=True, @@ -410,7 +416,7 @@ class LTXVAddGuide(io.ComfyNode): return latent_image, noise_mask @classmethod - def execute(cls, positive, negative, vae, latent, image, frame_idx, strength, iclora_parameters=None) -> io.NodeOutput: + def execute(cls, positive, negative, vae, latent, image, frame_idx, strength, attention_mask=None, iclora_parameters=None) -> io.NodeOutput: scale_factors = vae.downscale_index_formula latent_image = latent["samples"] noise_mask = get_noise_mask(latent) @@ -469,6 +475,7 @@ class LTXVAddGuide(io.ComfyNode): pre_filter_count = t.shape[2] * t.shape[3] * t.shape[4] positive, negative = _append_guide_attention_entry( positive, negative, pre_filter_count, guide_latent_shape, strength=strength, + attention_mask=attention_mask, ) return io.NodeOutput(positive, negative, {"samples": latent_image, "noise_mask": noise_mask}) @@ -594,7 +601,7 @@ class LTXVScheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="LTXVScheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Int.Input("steps", default=20, min=1, max=10000), io.Float.Input("max_shift", default=2.05, min=0.0, max=100.0, step=0.01), diff --git a/comfy_extras/nodes_mask.py b/comfy_extras/nodes_mask.py index 96ee1a0f8..d15f1f4e7 100644 --- a/comfy_extras/nodes_mask.py +++ b/comfy_extras/nodes_mask.py @@ -83,7 +83,7 @@ class ImageCompositeMasked(IO.ComfyNode): node_id="ImageCompositeMasked", search_aliases=["overlay", "layer", "paste image", "images composition"], display_name="Image Composite Masked", - category="image", + category="image/compositing", inputs=[ IO.Image.Input("destination"), IO.Image.Input("source"), @@ -112,7 +112,7 @@ class MaskToImage(IO.ComfyNode): node_id="MaskToImage", search_aliases=["convert mask"], display_name="Convert Mask to Image", - category="mask", + category="image/mask", inputs=[ IO.Mask.Input("mask"), ], @@ -134,7 +134,7 @@ class ImageToMask(IO.ComfyNode): node_id="ImageToMask", search_aliases=["extract channel", "channel to mask"], display_name="Convert Image to Mask", - category="mask", + category="image/mask", inputs=[ IO.Image.Input("image"), IO.Combo.Input("channel", options=["red", "green", "blue", "alpha"]), @@ -157,7 +157,8 @@ class ImageColorToMask(IO.ComfyNode): return IO.Schema( node_id="ImageColorToMask", search_aliases=["color keying", "chroma key"], - category="mask", + display_name="Convert Image Color to Mask", + category="image/mask", inputs=[ IO.Image.Input("image"), IO.Int.Input("color", default=0, min=0, max=0xFFFFFF, step=1, display_mode=IO.NumberDisplay.number), @@ -180,7 +181,8 @@ class SolidMask(IO.ComfyNode): def define_schema(cls): return IO.Schema( node_id="SolidMask", - category="mask", + display_name="Create Solid Mask", + category="image/mask", inputs=[ IO.Float.Input("value", default=1.0, min=0.0, max=1.0, step=0.01), IO.Int.Input("width", default=512, min=1, max=nodes.MAX_RESOLUTION, step=1), @@ -204,7 +206,7 @@ class InvertMask(IO.ComfyNode): node_id="InvertMask", search_aliases=["reverse mask", "flip mask"], display_name="Invert Mask", - category="mask", + category="image/mask", inputs=[ IO.Mask.Input("mask"), ], @@ -226,7 +228,7 @@ class CropMask(IO.ComfyNode): node_id="CropMask", search_aliases=["cut mask", "extract mask region", "mask slice"], display_name="Crop Mask", - category="mask", + category="image/mask", inputs=[ IO.Mask.Input("mask"), IO.Int.Input("x", default=0, min=0, max=nodes.MAX_RESOLUTION, step=1), @@ -253,7 +255,7 @@ class MaskComposite(IO.ComfyNode): node_id="MaskComposite", search_aliases=["combine masks", "blend masks", "layer masks", "masks composition"], display_name="Combine Masks", - category="mask", + category="image/mask", inputs=[ IO.Mask.Input("destination"), IO.Mask.Input("source"), @@ -304,7 +306,7 @@ class FeatherMask(IO.ComfyNode): node_id="FeatherMask", search_aliases=["soft edge mask", "blur mask edges", "gradient mask edge"], display_name="Feather Mask", - category="mask", + category="image/mask", inputs=[ IO.Mask.Input("mask"), IO.Int.Input("left", default=0, min=0, max=nodes.MAX_RESOLUTION, step=1), @@ -330,7 +332,7 @@ class FeatherMask(IO.ComfyNode): for x in range(right): feather_rate = (x + 1) / right - output[:, :, -x] *= feather_rate + output[:, :, -(x + 1)] *= feather_rate for y in range(top): feather_rate = (y + 1) / top @@ -338,7 +340,7 @@ class FeatherMask(IO.ComfyNode): for y in range(bottom): feather_rate = (y + 1) / bottom - output[:, -y, :] *= feather_rate + output[:, -(y + 1), :] *= feather_rate return IO.NodeOutput(output) @@ -352,7 +354,7 @@ class GrowMask(IO.ComfyNode): node_id="GrowMask", search_aliases=["expand mask", "shrink mask"], display_name="Grow Mask", - category="mask", + category="image/mask", inputs=[ IO.Mask.Input("mask"), IO.Int.Input("expand", default=0, min=-nodes.MAX_RESOLUTION, max=nodes.MAX_RESOLUTION, step=1), @@ -388,7 +390,8 @@ class ThresholdMask(IO.ComfyNode): return IO.Schema( node_id="ThresholdMask", search_aliases=["binary mask"], - category="mask", + display_name="Threshold Mask", + category="image/mask", inputs=[ IO.Mask.Input("mask"), IO.Float.Input("value", default=0.5, min=0.0, max=1.0, step=0.01), @@ -414,7 +417,7 @@ class MaskPreview(IO.ComfyNode): node_id="MaskPreview", search_aliases=["show mask", "view mask", "inspect mask", "debug mask"], display_name="Preview Mask", - category="mask", + category="image/mask", description="Saves the input images to your ComfyUI output directory.", inputs=[ IO.Mask.Input("mask"), diff --git a/comfy_extras/nodes_model_merging.py b/comfy_extras/nodes_model_merging.py index 5384ed531..b6b29e34a 100644 --- a/comfy_extras/nodes_model_merging.py +++ b/comfy_extras/nodes_model_merging.py @@ -276,8 +276,8 @@ class CLIPSave: for x in extra_pnginfo: metadata[x] = json.dumps(extra_pnginfo[x]) - comfy.model_management.load_models_gpu([clip.load_model()], force_patch_weights=True) - clip_sd = clip.get_sd() + clip.load_model() + clip_sd = clip.state_dict_for_saving() for prefix in ["clip_l.", "clip_g.", "clip_h.", "t5xxl.", "pile_t5xl.", "mt5xl.", "umt5xxl.", "t5base.", "gemma2_2b.", "llama.", "hydit_clip.", ""]: k = list(filter(lambda a: a.startswith(prefix), clip_sd.keys())) diff --git a/comfy_extras/nodes_morphology.py b/comfy_extras/nodes_morphology.py index c01b9436d..0142040dd 100644 --- a/comfy_extras/nodes_morphology.py +++ b/comfy_extras/nodes_morphology.py @@ -13,8 +13,8 @@ class Morphology(io.ComfyNode): return io.Schema( node_id="Morphology", search_aliases=["erode", "dilate"], - display_name="ImageMorphology", - category="image/postprocessing", + display_name="Apply Morphology", + category="image/filters", inputs=[ io.Image.Input("image"), io.Combo.Input( diff --git a/comfy_extras/nodes_nop.py b/comfy_extras/nodes_nop.py index 953061bcb..f9c1357c3 100644 --- a/comfy_extras/nodes_nop.py +++ b/comfy_extras/nodes_nop.py @@ -13,7 +13,7 @@ class wanBlockSwap(io.ComfyNode): return io.Schema( node_id="wanBlockSwap", category="", - description="NOP", + description="Intercept wanBlockSwap custom node that causes major instability and make it no-op.", inputs=[ io.Model.Input("model"), ], diff --git a/comfy_extras/nodes_number_convert.py b/comfy_extras/nodes_number_convert.py index ab3f2aa8a..e38a33c15 100644 --- a/comfy_extras/nodes_number_convert.py +++ b/comfy_extras/nodes_number_convert.py @@ -20,7 +20,7 @@ class NumberConvertNode(io.ComfyNode): def define_schema(cls) -> io.Schema: return io.Schema( node_id="ComfyNumberConvert", - display_name="Number Convert", + display_name="Convert Number", category="utils", search_aliases=[ "int to float", "float to int", "number convert", diff --git a/comfy_extras/nodes_optimalsteps.py b/comfy_extras/nodes_optimalsteps.py index 73f0104d8..5beeaa7db 100644 --- a/comfy_extras/nodes_optimalsteps.py +++ b/comfy_extras/nodes_optimalsteps.py @@ -31,7 +31,7 @@ class OptimalStepsScheduler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="OptimalStepsScheduler", - category="sampling/custom_sampling/schedulers", + category="sampling/schedulers", inputs=[ io.Combo.Input("model_type", options=["FLUX", "Wan", "Chroma"]), io.Int.Input("steps", default=20, min=3, max=1000), diff --git a/comfy_extras/nodes_post_processing.py b/comfy_extras/nodes_post_processing.py index 1fa14d2d2..a25db277c 100644 --- a/comfy_extras/nodes_post_processing.py +++ b/comfy_extras/nodes_post_processing.py @@ -22,7 +22,7 @@ class Blend(io.ComfyNode): node_id="ImageBlend", search_aliases=["mix images"], display_name="Blend Images", - category="image/postprocessing", + category="image/filters", essentials_category="Image Tools", inputs=[ io.Image.Input("image1"), @@ -80,8 +80,8 @@ class Blur(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="ImageBlur", - display_name="Image Blur", - category="image/postprocessing", + display_name="Blur Image", + category="image/filters", inputs=[ io.Image.Input("image"), io.Int.Input("blur_radius", default=1, min=1, max=31, step=1), @@ -117,7 +117,7 @@ class Quantize(io.ComfyNode): return io.Schema( node_id="ImageQuantize", display_name="Quantize Image", - category="image/postprocessing", + category="image/filters", inputs=[ io.Image.Input("image"), io.Int.Input("colors", default=256, min=1, max=256, step=1), @@ -183,7 +183,7 @@ class Sharpen(io.ComfyNode): return io.Schema( node_id="ImageSharpen", display_name="Sharpen Image", - category="image/postprocessing", + category="image/filters", inputs=[ io.Image.Input("image"), io.Int.Input("sharpen_radius", default=1, min=1, max=31, step=1, advanced=True), @@ -568,7 +568,7 @@ def batch_latents(latents: list[dict[str, torch.Tensor]]) -> dict[str, torch.Ten class BatchImagesNode(io.ComfyNode): @classmethod def define_schema(cls): - autogrow_template = io.Autogrow.TemplatePrefix(io.Image.Input("image"), prefix="image", min=2, max=50) + autogrow_template = io.Autogrow.TemplatePrefix(io.Image.Input("image"), prefix="image", min=1, max=50) return io.Schema( node_id="BatchImagesNode", display_name="Batch Images", @@ -590,12 +590,12 @@ class BatchImagesNode(io.ComfyNode): class BatchMasksNode(io.ComfyNode): @classmethod def define_schema(cls): - autogrow_template = io.Autogrow.TemplatePrefix(io.Mask.Input("mask"), prefix="mask", min=2, max=50) + autogrow_template = io.Autogrow.TemplatePrefix(io.Mask.Input("mask"), prefix="mask", min=1, max=50) return io.Schema( node_id="BatchMasksNode", search_aliases=["combine masks", "stack masks", "merge masks"], display_name="Batch Masks", - category="mask", + category="image/mask", inputs=[ io.Autogrow.Input("masks", template=autogrow_template) ], @@ -611,7 +611,7 @@ class BatchMasksNode(io.ComfyNode): class BatchLatentsNode(io.ComfyNode): @classmethod def define_schema(cls): - autogrow_template = io.Autogrow.TemplatePrefix(io.Latent.Input("latent"), prefix="latent", min=2, max=50) + autogrow_template = io.Autogrow.TemplatePrefix(io.Latent.Input("latent"), prefix="latent", min=1, max=50) return io.Schema( node_id="BatchLatentsNode", search_aliases=["combine latents", "stack latents", "merge latents"], @@ -670,8 +670,8 @@ class ColorTransfer(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="ColorTransfer", - display_name="Color Transfer", - category="image/postprocessing", + display_name="Transfer Color", + category="image/filters", description="Match the colors of one image to another using various algorithms.", search_aliases=["color match", "color grading", "color correction", "match colors", "color transform", "mkl", "reinhard", "histogram"], inputs=[ diff --git a/comfy_extras/nodes_rtdetr.py b/comfy_extras/nodes_rtdetr.py index a321577c7..e5a9b3902 100644 --- a/comfy_extras/nodes_rtdetr.py +++ b/comfy_extras/nodes_rtdetr.py @@ -15,7 +15,7 @@ class RTDETR_detect(io.ComfyNode): return io.Schema( node_id="RTDETR_detect", display_name="RT-DETR Detect", - category="detection", + category="image/detection", search_aliases=["bbox", "bounding box", "object detection", "coco"], inputs=[ io.Model.Input("model", display_name="model"), @@ -71,7 +71,7 @@ class DrawBBoxes(io.ComfyNode): return io.Schema( node_id="DrawBBoxes", display_name="Draw BBoxes", - category="detection", + category="image/detection", search_aliases=["bbox", "bounding box", "object detection", "rt_detr", "visualize detections", "coco"], inputs=[ io.Image.Input("image", optional=True), diff --git a/comfy_extras/nodes_sam3.py b/comfy_extras/nodes_sam3.py index 4ea9221e9..daac52f9b 100644 --- a/comfy_extras/nodes_sam3.py +++ b/comfy_extras/nodes_sam3.py @@ -93,7 +93,7 @@ class SAM3_Detect(io.ComfyNode): return io.Schema( node_id="SAM3_Detect", display_name="SAM3 Detect", - category="detection", + category="image/detection", search_aliases=["sam3", "segment anything", "open vocabulary", "text detection", "segment"], inputs=[ io.Model.Input("model", display_name="model"), @@ -265,7 +265,7 @@ class SAM3_VideoTrack(io.ComfyNode): return io.Schema( node_id="SAM3_VideoTrack", display_name="SAM3 Video Track", - category="detection", + category="image/detection", search_aliases=["sam3", "video", "track", "propagate"], inputs=[ io.Image.Input("images", display_name="images", tooltip="Video frames as batched images"), @@ -320,7 +320,7 @@ class SAM3_TrackPreview(io.ComfyNode): return io.Schema( node_id="SAM3_TrackPreview", display_name="SAM3 Track Preview", - category="detection", + category="image/detection", inputs=[ SAM3TrackData.Input("track_data", display_name="track_data"), io.Image.Input("images", display_name="images", optional=True), @@ -478,7 +478,7 @@ class SAM3_TrackToMask(io.ComfyNode): return io.Schema( node_id="SAM3_TrackToMask", display_name="SAM3 Track to Mask", - category="detection", + category="image/detection", inputs=[ SAM3TrackData.Input("track_data", display_name="track_data"), io.String.Input("object_indices", display_name="object_indices", default="", diff --git a/comfy_extras/nodes_sdpose.py b/comfy_extras/nodes_sdpose.py index 96b6821bd..20d459b00 100644 --- a/comfy_extras/nodes_sdpose.py +++ b/comfy_extras/nodes_sdpose.py @@ -353,7 +353,8 @@ class SDPoseDrawKeypoints(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SDPoseDrawKeypoints", - category="image/preprocessors", + display_name="SDPose Draw Keypoints", + category="image/detection", search_aliases=["openpose", "pose detection", "preprocessor", "keypoints", "pose"], inputs=[ io.Custom("POSE_KEYPOINT").Input("keypoints"), @@ -421,7 +422,8 @@ class SDPoseKeypointExtractor(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SDPoseKeypointExtractor", - category="image/preprocessors", + display_name="SDPose Keypoint Extractor", + category="image/detection", search_aliases=["openpose", "pose detection", "preprocessor", "keypoints", "sdpose"], description="Extract pose keypoints from images using the SDPose model: https://huggingface.co/Comfy-Org/SDPose/tree/main/checkpoints", inputs=[ @@ -595,7 +597,8 @@ class SDPoseFaceBBoxes(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="SDPoseFaceBBoxes", - category="image/preprocessors", + display_name="SDPose Face Bounding Boxes", + category="image/detection", search_aliases=["face bbox", "face bounding box", "pose", "keypoints"], inputs=[ io.Custom("POSE_KEYPOINT").Input("keypoints"), @@ -652,7 +655,8 @@ class CropByBBoxes(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="CropByBBoxes", - category="image/preprocessors", + display_name="Crop By Bounding Boxes", + category="image/transform", search_aliases=["crop", "face crop", "bbox crop", "pose", "bounding box"], description="Crop and resize regions from the input image batch based on provided bounding boxes.", inputs=[ diff --git a/comfy_extras/nodes_video_model.py b/comfy_extras/nodes_video_model.py index 0f3881a24..8f19895a1 100644 --- a/comfy_extras/nodes_video_model.py +++ b/comfy_extras/nodes_video_model.py @@ -65,7 +65,7 @@ class VideoLinearCFGGuidance: RETURN_TYPES = ("MODEL",) FUNCTION = "patch" - CATEGORY = "sampling/video_models" + CATEGORY = "sampling/guiders" def patch(self, model, min_cfg): def linear_cfg(args): @@ -89,7 +89,7 @@ class VideoTriangleCFGGuidance: RETURN_TYPES = ("MODEL",) FUNCTION = "patch" - CATEGORY = "sampling/video_models" + CATEGORY = "sampling/guiders" def patch(self, model, min_cfg): def linear_cfg(args): @@ -157,5 +157,7 @@ NODE_CLASS_MAPPINGS = { } NODE_DISPLAY_NAME_MAPPINGS = { - "ImageOnlyCheckpointLoader": "Image Only Checkpoint Loader (img2vid model)", + "ImageOnlyCheckpointLoader": "Load Checkpoint Image Only (img2vid model)", + "VideoLinearCFGGuidance": "Video Linear CFG Guidance", + "VideoTriangleCFGGuidance": "Video Triangle CFG Guidance", } diff --git a/comfy_extras/nodes_void.py b/comfy_extras/nodes_void.py index e7a8f3757..be724371a 100644 --- a/comfy_extras/nodes_void.py +++ b/comfy_extras/nodes_void.py @@ -122,7 +122,8 @@ class VOIDQuadmaskPreprocess(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="VOIDQuadmaskPreprocess", - category="mask/video", + display_name="VOID Quadmask Preprocessor", + category="image/mask", inputs=[ io.Mask.Input("mask"), io.Int.Input("dilate_width", default=0, min=0, max=50, step=1, @@ -392,7 +393,7 @@ class VOIDWarpedNoiseSource(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="VOIDWarpedNoiseSource", - category="sampling/custom_sampling/noise", + category="sampling/noise", inputs=[ io.Latent.Input("warped_noise", tooltip="Warped noise latent from VOIDWarpedNoise"), @@ -454,7 +455,7 @@ class VOIDSampler(io.ComfyNode): def define_schema(cls): return io.Schema( node_id="VOIDSampler", - category="sampling/custom_sampling/samplers", + category="sampling/samplers", inputs=[], outputs=[io.Sampler.Output()], ) diff --git a/execution.py b/execution.py index f37d0360d..4c7de2e84 100644 --- a/execution.py +++ b/execution.py @@ -626,7 +626,7 @@ async def execute(server, dynprompt, caches, current_item, extra_data, executed, if comfy.model_management.is_oom(ex): tips = "This error means you ran out of memory on your GPU.\n\nTIPS: If the workflow worked before you might have accidentally set the batch_size to a large number." - logging.info("Memory summary: {}".format(comfy.model_management.debug_memory_summary())) + logging.info("Memory summary:\n{}".format(comfy.model_management.debug_memory_summary())) logging.error("Got an OOM, unloading all loaded models.") comfy.model_management.unload_all_models() elif isinstance(ex, RuntimeError) and ("mat1 and mat2 shapes" in str(ex)) and "Sampler" in class_type: diff --git a/nodes.py b/nodes.py index 374217eea..fdd6eeb5f 100644 --- a/nodes.py +++ b/nodes.py @@ -691,7 +691,7 @@ class LoraLoader: FUNCTION = "load_lora" CATEGORY = "loaders" - DESCRIPTION = "LoRAs are used to modify diffusion and CLIP models, altering the way in which latents are denoised such as applying styles. Multiple LoRA nodes can be linked together." + DESCRIPTION = "This LoRA loader is used to modify both diffusion and CLIP models, altering the way in which latents are denoised such as applying styles. Multiple LoRA nodes can be linked together." SEARCH_ALIASES = ["lora", "load lora", "apply lora", "lora loader", "lora model"] def load_lora(self, model, clip, lora_name, strength_model, strength_clip): @@ -723,6 +723,7 @@ class LoraLoaderModelOnly(LoraLoader): "strength_model": ("FLOAT", {"default": 1.0, "min": -100.0, "max": 100.0, "step": 0.01}), }} RETURN_TYPES = ("MODEL",) + DESCRIPTION = "This LoRAs loader is used to modify the diffusion model, altering the way in which latents are denoised such as applying styles. Multiple LoRA nodes can be linked together." FUNCTION = "load_lora_model_only" def load_lora_model_only(self, model, lora_name, strength_model): @@ -1524,7 +1525,7 @@ class SetLatentNoiseMask: def common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent, denoise=1.0, disable_noise=False, start_step=None, last_step=None, force_full_denoise=False): latent_image = latent["samples"] - latent_image = comfy.sample.fix_empty_latent_channels(model, latent_image, latent.get("downscale_ratio_spacial", None)) + latent_image = comfy.sample.fix_empty_latent_channels(model, latent_image, latent.get("downscale_ratio_spacial", None), latent.get("downscale_ratio_temporal", None)) if disable_noise: noise = torch.zeros(latent_image.size(), dtype=latent_image.dtype, layout=latent_image.layout, device="cpu") @@ -1543,6 +1544,7 @@ def common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, force_full_denoise=force_full_denoise, noise_mask=noise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed) out = latent.copy() out.pop("downscale_ratio_spacial", None) + out.pop("downscale_ratio_temporal", None) out["samples"] = samples return (out, ) @@ -1775,7 +1777,7 @@ class LoadImageMask(LoadImage): } } - CATEGORY = "mask" + CATEGORY = "image" RETURN_TYPES = ("MASK",) FUNCTION = "load_image_mask" diff --git a/openapi.yaml b/openapi.yaml index 214962c5c..9a3117e22 100644 --- a/openapi.yaml +++ b/openapi.yaml @@ -485,8 +485,15 @@ paths: post: operationId: uploadMask tags: [upload] - summary: Upload a mask image - description: Uploads a mask image associated with a previously-uploaded reference image. + deprecated: true + summary: Upload a mask image (deprecated) + description: | + Deprecated. Clients should composite the mask onto the source image + client-side and upload the resulting image via POST /api/upload/image + instead. This endpoint will continue to function for older clients, + but will not receive new features. + + Uploads a mask image associated with a previously-uploaded reference image. requestBody: required: true content: