fix: always send new binary format when client supports feature flag

When prompt_id is None, encode as zero-length string instead of falling
back to old format. Prevents binary parse corruption on the frontend.

Addresses review feedback:
https://github.com/Comfy-Org/ComfyUI/pull/12540#discussion_r2923412491

comfy/comfy_types/node_typing.py

@@ -193,6 +193,8 @@ class HiddenInputTypeDict(TypedDict):
     """EXTRA_PNGINFO is a dictionary that will be copied into the metadata of any .png files saved. Custom nodes can store additional information in this dictionary for saving (or as a way to communicate with a downstream node)."""
     dynprompt: NotRequired[Literal["DYNPROMPT"]]
     """DYNPROMPT is an instance of comfy_execution.graph.DynamicPrompt. It differs from PROMPT in that it may mutate during the course of execution in response to Node Expansion."""
+    prompt_id: NotRequired[Literal["PROMPT_ID"]]
+    """PROMPT_ID is the unique identifier of the current prompt/job being executed. Useful for associating progress updates with specific jobs."""
 
 
 class InputTypeDict(TypedDict):

comfy/model_base.py

@@ -925,25 +925,6 @@ class Flux(BaseModel):
             out['ref_latents'] = list([1, 16, sum(map(lambda a: math.prod(a.size()[2:]), ref_latents))])
         return out
 
-class LongCatImage(Flux):
-    def _apply_model(self, x, t, c_concat=None, c_crossattn=None, control=None, transformer_options={}, **kwargs):
-        transformer_options = transformer_options.copy()
-        rope_opts = transformer_options.get("rope_options", {})
-        rope_opts = dict(rope_opts)
-        rope_opts.setdefault("shift_t", 1.0)
-        rope_opts.setdefault("shift_y", 512.0)
-        rope_opts.setdefault("shift_x", 512.0)
-        transformer_options["rope_options"] = rope_opts
-        return super()._apply_model(x, t, c_concat, c_crossattn, control, transformer_options, **kwargs)
-
-    def encode_adm(self, **kwargs):
-        return None
-
-    def extra_conds(self, **kwargs):
-        out = super().extra_conds(**kwargs)
-        out.pop('guidance', None)
-        return out
-
 class Flux2(Flux):
     def extra_conds(self, **kwargs):
         out = super().extra_conds(**kwargs)

comfy/model_detection.py

@@ -279,8 +279,6 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
             dit_config["txt_norm"] = any_suffix_in(state_dict_keys, key_prefix, 'txt_norm.', ["weight", "scale"])
             if dit_config["yak_mlp"] and dit_config["txt_norm"]:  # Ovis model
                 dit_config["txt_ids_dims"] = [1, 2]
-            if dit_config.get("context_in_dim") == 3584 and dit_config["vec_in_dim"] is None:  # LongCat-Image
-                dit_config["txt_ids_dims"] = [1, 2]
 
         return dit_config
 

comfy/sd.py

@@ -60,7 +60,6 @@ import comfy.text_encoders.jina_clip_2
 import comfy.text_encoders.newbie
 import comfy.text_encoders.anima
 import comfy.text_encoders.ace15
-import comfy.text_encoders.longcat_image
 
 import comfy.model_patcher
 import comfy.lora
@@ -1161,7 +1160,6 @@ class CLIPType(Enum):
     KANDINSKY5_IMAGE = 23
     NEWBIE = 24
     FLUX2 = 25
-    LONGCAT_IMAGE = 26
 
 
 def load_clip(ckpt_paths, embedding_directory=None, clip_type=CLIPType.STABLE_DIFFUSION, model_options={}):
@@ -1374,9 +1372,6 @@ def load_text_encoder_state_dicts(state_dicts=[], embedding_directory=None, clip
             if clip_type == CLIPType.HUNYUAN_IMAGE:
                 clip_target.clip = comfy.text_encoders.hunyuan_image.te(byt5=False, **llama_detect(clip_data))
                 clip_target.tokenizer = comfy.text_encoders.hunyuan_image.HunyuanImageTokenizer
-            elif clip_type == CLIPType.LONGCAT_IMAGE:
-                clip_target.clip = comfy.text_encoders.longcat_image.te(**llama_detect(clip_data))
-                clip_target.tokenizer = comfy.text_encoders.longcat_image.LongCatImageTokenizer
             else:
                 clip_target.clip = comfy.text_encoders.qwen_image.te(**llama_detect(clip_data))
                 clip_target.tokenizer = comfy.text_encoders.qwen_image.QwenImageTokenizer

comfy/supported_models.py

@@ -25,7 +25,6 @@ import comfy.text_encoders.kandinsky5
 import comfy.text_encoders.z_image
 import comfy.text_encoders.anima
 import comfy.text_encoders.ace15
-import comfy.text_encoders.longcat_image
 
 from . import supported_models_base
 from . import latent_formats
@@ -1679,37 +1678,6 @@ class ACEStep15(supported_models_base.BASE):
         return supported_models_base.ClipTarget(comfy.text_encoders.ace15.ACE15Tokenizer, comfy.text_encoders.ace15.te(**detect))
 
 
-class LongCatImage(supported_models_base.BASE):
-    unet_config = {
-        "image_model": "flux",
-        "guidance_embed": False,
-        "vec_in_dim": None,
-        "context_in_dim": 3584,
-        "txt_ids_dims": [1, 2],
-    }
-
-    sampling_settings = {
-    }
-
-    unet_extra_config = {}
-    latent_format = latent_formats.Flux
-
-    memory_usage_factor = 2.5
-
-    supported_inference_dtypes = [torch.bfloat16, torch.float16, torch.float32]
-
-    vae_key_prefix = ["vae."]
-    text_encoder_key_prefix = ["text_encoders."]
-
-    def get_model(self, state_dict, prefix="", device=None):
-        out = model_base.LongCatImage(self, device=device)
-        return out
-
-    def clip_target(self, state_dict={}):
-        pref = self.text_encoder_key_prefix[0]
-        hunyuan_detect = comfy.text_encoders.hunyuan_video.llama_detect(state_dict, "{}qwen25_7b.transformer.".format(pref))
-        return supported_models_base.ClipTarget(comfy.text_encoders.longcat_image.LongCatImageTokenizer, comfy.text_encoders.longcat_image.te(**hunyuan_detect))
-
-models = [LotusD, Stable_Zero123, SD15_instructpix2pix, SD15, SD20, SD21UnclipL, SD21UnclipH, SDXL_instructpix2pix, SDXLRefiner, SDXL, SSD1B, KOALA_700M, KOALA_1B, Segmind_Vega, SD_X4Upscaler, Stable_Cascade_C, Stable_Cascade_B, SV3D_u, SV3D_p, SD3, StableAudio, AuraFlow, PixArtAlpha, PixArtSigma, HunyuanDiT, HunyuanDiT1, FluxInpaint, Flux, LongCatImage, FluxSchnell, GenmoMochi, LTXV, LTXAV, HunyuanVideo15_SR_Distilled, HunyuanVideo15, HunyuanImage21Refiner, HunyuanImage21, HunyuanVideoSkyreelsI2V, HunyuanVideoI2V, HunyuanVideo, CosmosT2V, CosmosI2V, CosmosT2IPredict2, CosmosI2VPredict2, ZImage, Lumina2, WAN22_T2V, WAN21_T2V, WAN21_I2V, WAN21_FunControl2V, WAN21_Vace, WAN21_Camera, WAN22_Camera, WAN22_S2V, WAN21_HuMo, WAN22_Animate, WAN21_FlowRVS, Hunyuan3Dv2mini, Hunyuan3Dv2, Hunyuan3Dv2_1, HiDream, Chroma, ChromaRadiance, ACEStep, ACEStep15, Omnigen2, QwenImage, Flux2, Kandinsky5Image, Kandinsky5, Anima]
+models = [LotusD, Stable_Zero123, SD15_instructpix2pix, SD15, SD20, SD21UnclipL, SD21UnclipH, SDXL_instructpix2pix, SDXLRefiner, SDXL, SSD1B, KOALA_700M, KOALA_1B, Segmind_Vega, SD_X4Upscaler, Stable_Cascade_C, Stable_Cascade_B, SV3D_u, SV3D_p, SD3, StableAudio, AuraFlow, PixArtAlpha, PixArtSigma, HunyuanDiT, HunyuanDiT1, FluxInpaint, Flux, FluxSchnell, GenmoMochi, LTXV, LTXAV, HunyuanVideo15_SR_Distilled, HunyuanVideo15, HunyuanImage21Refiner, HunyuanImage21, HunyuanVideoSkyreelsI2V, HunyuanVideoI2V, HunyuanVideo, CosmosT2V, CosmosI2V, CosmosT2IPredict2, CosmosI2VPredict2, ZImage, Lumina2, WAN22_T2V, WAN21_T2V, WAN21_I2V, WAN21_FunControl2V, WAN21_Vace, WAN21_Camera, WAN22_Camera, WAN22_S2V, WAN21_HuMo, WAN22_Animate, WAN21_FlowRVS, Hunyuan3Dv2mini, Hunyuan3Dv2, Hunyuan3Dv2_1, HiDream, Chroma, ChromaRadiance, ACEStep, ACEStep15, Omnigen2, QwenImage, Flux2, Kandinsky5Image, Kandinsky5, Anima]
 
 models += [SVD_img2vid]

comfy/text_encoders/ace15.py

@@ -328,14 +328,14 @@ class ACE15TEModel(torch.nn.Module):
                 return getattr(self, self.lm_model).load_sd(sd)
 
     def memory_estimation_function(self, token_weight_pairs, device=None):
-        lm_metadata = token_weight_pairs.get("lm_metadata", {})
+        lm_metadata = token_weight_pairs["lm_metadata"]
         constant = self.constant
         if comfy.model_management.should_use_bf16(device):
             constant *= 0.5
 
         token_weight_pairs = token_weight_pairs.get("lm_prompt", [])
         num_tokens = sum(map(lambda a: len(a), token_weight_pairs))
-        num_tokens += lm_metadata.get("min_tokens", 0)
+        num_tokens += lm_metadata['min_tokens']
         return num_tokens * constant * 1024 * 1024
 
 def te(dtype_llama=None, llama_quantization_metadata=None, lm_model="qwen3_2b"):

comfy/text_encoders/longcat_image.py

@@ -1,184 +0,0 @@
-import re
-import numbers
-import torch
-from comfy import sd1_clip
-from comfy.text_encoders.qwen_image import Qwen25_7BVLITokenizer, Qwen25_7BVLIModel
-import logging
-
-logger = logging.getLogger(__name__)
-
-QUOTE_PAIRS = [("'", "'"), ('"', '"'), ("\u2018", "\u2019"), ("\u201c", "\u201d")]
-QUOTE_PATTERN = "|".join(
-    [
-        re.escape(q1) + r"[^" + re.escape(q1 + q2) + r"]*?" + re.escape(q2)
-        for q1, q2 in QUOTE_PAIRS
-    ]
-)
-WORD_INTERNAL_QUOTE_RE = re.compile(r"[a-zA-Z]+'[a-zA-Z]+")
-
-
-def split_quotation(prompt):
-    matches = WORD_INTERNAL_QUOTE_RE.findall(prompt)
-    mapping = []
-    for i, word_src in enumerate(set(matches)):
-        word_tgt = "longcat_$##$_longcat" * (i + 1)
-        prompt = prompt.replace(word_src, word_tgt)
-        mapping.append((word_src, word_tgt))
-
-    parts = re.split(f"({QUOTE_PATTERN})", prompt)
-    result = []
-    for part in parts:
-        for word_src, word_tgt in mapping:
-            part = part.replace(word_tgt, word_src)
-        if not part:
-            continue
-        is_quoted = bool(re.match(QUOTE_PATTERN, part))
-        result.append((part, is_quoted))
-    return result
-
-
-class LongCatImageBaseTokenizer(Qwen25_7BVLITokenizer):
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self.max_length = 512
-
-    def tokenize_with_weights(self, text, return_word_ids=False, **kwargs):
-        parts = split_quotation(text)
-        all_tokens = []
-        for part_text, is_quoted in parts:
-            if is_quoted:
-                for char in part_text:
-                    ids = self.tokenizer(char, add_special_tokens=False)["input_ids"]
-                    all_tokens.extend(ids)
-            else:
-                ids = self.tokenizer(part_text, add_special_tokens=False)["input_ids"]
-                all_tokens.extend(ids)
-
-        if len(all_tokens) > self.max_length:
-            all_tokens = all_tokens[: self.max_length]
-            logger.warning(f"Truncated prompt to {self.max_length} tokens")
-
-        output = [(t, 1.0) for t in all_tokens]
-        # Pad to max length
-        self.pad_tokens(output, self.max_length - len(output))
-        return [output]
-
-
-class LongCatImageTokenizer(sd1_clip.SD1Tokenizer):
-    def __init__(self, embedding_directory=None, tokenizer_data={}):
-        super().__init__(
-            embedding_directory=embedding_directory,
-            tokenizer_data=tokenizer_data,
-            name="qwen25_7b",
-            tokenizer=LongCatImageBaseTokenizer,
-        )
-        self.longcat_template_prefix = "<|im_start|>system\nAs an image captioning expert, generate a descriptive text prompt based on an image content, suitable for input to a text-to-image model.<|im_end|>\n<|im_start|>user\n"
-        self.longcat_template_suffix = "<|im_end|>\n<|im_start|>assistant\n"
-
-    def tokenize_with_weights(self, text, return_word_ids=False, **kwargs):
-        skip_template = False
-        if text.startswith("<|im_start|>"):
-            skip_template = True
-        if text.startswith("<|start_header_id|>"):
-            skip_template = True
-        if text == "":
-            text = " "
-
-        base_tok = getattr(self, "qwen25_7b")
-        if skip_template:
-            tokens = super().tokenize_with_weights(
-                text, return_word_ids=return_word_ids, disable_weights=True, **kwargs
-            )
-        else:
-            prefix_ids = base_tok.tokenizer(
-                self.longcat_template_prefix, add_special_tokens=False
-            )["input_ids"]
-            suffix_ids = base_tok.tokenizer(
-                self.longcat_template_suffix, add_special_tokens=False
-            )["input_ids"]
-
-            prompt_tokens = base_tok.tokenize_with_weights(
-                text, return_word_ids=return_word_ids, **kwargs
-            )
-            prompt_pairs = prompt_tokens[0]
-
-            prefix_pairs = [(t, 1.0) for t in prefix_ids]
-            suffix_pairs = [(t, 1.0) for t in suffix_ids]
-
-            combined = prefix_pairs + prompt_pairs + suffix_pairs
-            tokens = {"qwen25_7b": [combined]}
-
-        return tokens
-
-
-class LongCatImageTEModel(sd1_clip.SD1ClipModel):
-    def __init__(self, device="cpu", dtype=None, model_options={}):
-        super().__init__(
-            device=device,
-            dtype=dtype,
-            name="qwen25_7b",
-            clip_model=Qwen25_7BVLIModel,
-            model_options=model_options,
-        )
-
-    def encode_token_weights(self, token_weight_pairs, template_end=-1):
-        out, pooled, extra = super().encode_token_weights(token_weight_pairs)
-        tok_pairs = token_weight_pairs["qwen25_7b"][0]
-        count_im_start = 0
-        if template_end == -1:
-            for i, v in enumerate(tok_pairs):
-                elem = v[0]
-                if not torch.is_tensor(elem):
-                    if isinstance(elem, numbers.Integral):
-                        if elem == 151644 and count_im_start < 2:
-                            template_end = i
-                            count_im_start += 1
-
-        if out.shape[1] > (template_end + 3):
-            if tok_pairs[template_end + 1][0] == 872:
-                if tok_pairs[template_end + 2][0] == 198:
-                    template_end += 3
-
-        if template_end == -1:
-            template_end = 0
-
-        suffix_start = None
-        for i in range(len(tok_pairs) - 1, -1, -1):
-            elem = tok_pairs[i][0]
-            if not torch.is_tensor(elem) and isinstance(elem, numbers.Integral):
-                if elem == 151645:
-                    suffix_start = i
-                    break
-
-        out = out[:, template_end:]
-
-        if "attention_mask" in extra:
-            extra["attention_mask"] = extra["attention_mask"][:, template_end:]
-            if extra["attention_mask"].sum() == torch.numel(extra["attention_mask"]):
-                extra.pop("attention_mask")
-
-        if suffix_start is not None:
-            suffix_len = len(tok_pairs) - suffix_start
-            if suffix_len > 0 and out.shape[1] > suffix_len:
-                out = out[:, :-suffix_len]
-                if "attention_mask" in extra:
-                    extra["attention_mask"] = extra["attention_mask"][:, :-suffix_len]
-                    if extra["attention_mask"].sum() == torch.numel(
-                        extra["attention_mask"]
-                    ):
-                        extra.pop("attention_mask")
-
-        return out, pooled, extra
-
-
-def te(dtype_llama=None, llama_quantization_metadata=None):
-    class LongCatImageTEModel_(LongCatImageTEModel):
-        def __init__(self, device="cpu", dtype=None, model_options={}):
-            if llama_quantization_metadata is not None:
-                model_options = model_options.copy()
-                model_options["quantization_metadata"] = llama_quantization_metadata
-            if dtype_llama is not None:
-                dtype = dtype_llama
-            super().__init__(device=device, dtype=dtype, model_options=model_options)
-
-    return LongCatImageTEModel_

comfy_api/feature_flags.py

@@ -12,6 +12,7 @@ from comfy.cli_args import args
 # Default server capabilities
 SERVER_FEATURE_FLAGS: dict[str, Any] = {
     "supports_preview_metadata": True,
+    "supports_progress_text_metadata": True,
     "max_upload_size": args.max_upload_size * 1024 * 1024, # Convert MB to bytes
     "extension": {"manager": {"supports_v4": True}},
     "node_replacements": True,

comfy_api/latest/_io.py

@@ -1269,9 +1269,16 @@ class V3Data(TypedDict):
     'When True, the value of the dynamic input will be in the format (value, path_key).'
 
 class HiddenHolder:
+    """Holds hidden input values resolved during node execution.
+
+    Hidden inputs are special values automatically provided by the execution
+    engine (e.g., node ID, prompt data, authentication tokens) rather than
+    being connected by the user in the graph.
+    """
     def __init__(self, unique_id: str, prompt: Any,
                  extra_pnginfo: Any, dynprompt: Any,
-                 auth_token_comfy_org: str, api_key_comfy_org: str, **kwargs):
+                 auth_token_comfy_org: str, api_key_comfy_org: str,
+                 prompt_id: str = None, **kwargs):
         self.unique_id = unique_id
         """UNIQUE_ID is the unique identifier of the node, and matches the id property of the node on the client side. It is commonly used in client-server communications (see messages)."""
         self.prompt = prompt
@@ -1284,6 +1291,8 @@ class HiddenHolder:
         """AUTH_TOKEN_COMFY_ORG is a token acquired from signing into a ComfyOrg account on frontend."""
         self.api_key_comfy_org = api_key_comfy_org
         """API_KEY_COMFY_ORG is an API Key generated by ComfyOrg that allows skipping signing into a ComfyOrg account on frontend."""
+        self.prompt_id = prompt_id
+        """PROMPT_ID is the unique identifier of the current prompt/job being executed."""
 
     def __getattr__(self, key: str):
         '''If hidden variable not found, return None.'''
@@ -1291,6 +1300,14 @@ class HiddenHolder:
 
     @classmethod
     def from_dict(cls, d: dict | None):
+        """Create a HiddenHolder from a dictionary of hidden input values.
+
+        Args:
+            d: Dictionary mapping Hidden enum values to their resolved values.
+
+        Returns:
+            A new HiddenHolder instance with values populated from the dict.
+        """
         if d is None:
             d = {}
         return cls(
@@ -1300,6 +1317,7 @@ class HiddenHolder:
             dynprompt=d.get(Hidden.dynprompt, None),
             auth_token_comfy_org=d.get(Hidden.auth_token_comfy_org, None),
             api_key_comfy_org=d.get(Hidden.api_key_comfy_org, None),
+            prompt_id=d.get(Hidden.prompt_id, None),
         )
 
     @classmethod
@@ -1322,6 +1340,8 @@ class Hidden(str, Enum):
     """AUTH_TOKEN_COMFY_ORG is a token acquired from signing into a ComfyOrg account on frontend."""
     api_key_comfy_org = "API_KEY_COMFY_ORG"
     """API_KEY_COMFY_ORG is an API Key generated by ComfyOrg that allows skipping signing into a ComfyOrg account on frontend."""
+    prompt_id = "PROMPT_ID"
+    """PROMPT_ID is the unique identifier of the current prompt/job being executed. Useful for associating progress updates with specific jobs."""
 
 
 @dataclass

comfy_api_nodes/util/client.py

@@ -17,6 +17,7 @@ from pydantic import BaseModel
 
 from comfy import utils
 from comfy_api.latest import IO
+from comfy_execution.utils import get_executing_context
 from server import PromptServer
 
 from . import request_logger
@@ -436,6 +437,17 @@ def _display_text(
     status: str | int | None = None,
     price: float | None = None,
 ) -> None:
+    """Send a progress text message to the client for display on a node.
+
+    Assembles status, price, and text lines, then sends them via WebSocket.
+    Automatically retrieves the current prompt_id from the execution context.
+
+    Args:
+        node_cls: The ComfyNode class sending the progress text.
+        text: Optional text content to display.
+        status: Optional status string or code to display.
+        price: Optional price in dollars to display as credits.
+    """
     display_lines: list[str] = []
     if status:
         display_lines.append(f"Status: {status.capitalize() if isinstance(status, str) else status}")
@@ -446,7 +458,9 @@ def _display_text(
     if text is not None:
         display_lines.append(text)
     if display_lines:
-        PromptServer.instance.send_progress_text("\n".join(display_lines), get_node_id(node_cls))
+        ctx = get_executing_context()
+        prompt_id = ctx.prompt_id if ctx is not None else None
+        PromptServer.instance.send_progress_text("\n".join(display_lines), get_node_id(node_cls), prompt_id=prompt_id)
 
 
 def _display_time_progress(

comfy_extras/nodes_audio.py

@@ -162,7 +162,7 @@ class SaveAudio(IO.ComfyNode):
             essentials_category="Audio",
             inputs=[
                 IO.Audio.Input("audio"),
-                IO.String.Input("filename_prefix", default="audio/ComfyUI_%year%%month%%day%-%hour%%minute%%second%"),
+                IO.String.Input("filename_prefix", default="audio/ComfyUI"),
             ],
             hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo],
             is_output_node=True,
@@ -187,7 +187,7 @@ class SaveAudioMP3(IO.ComfyNode):
             category="audio",
             inputs=[
                 IO.Audio.Input("audio"),
-                IO.String.Input("filename_prefix", default="audio/ComfyUI_%year%%month%%day%-%hour%%minute%%second%"),
+                IO.String.Input("filename_prefix", default="audio/ComfyUI"),
                 IO.Combo.Input("quality", options=["V0", "128k", "320k"], default="V0"),
             ],
             hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo],
@@ -215,7 +215,7 @@ class SaveAudioOpus(IO.ComfyNode):
             category="audio",
             inputs=[
                 IO.Audio.Input("audio"),
-                IO.String.Input("filename_prefix", default="audio/ComfyUI_%year%%month%%day%-%hour%%minute%%second%"),
+                IO.String.Input("filename_prefix", default="audio/ComfyUI"),
                 IO.Combo.Input("quality", options=["64k", "96k", "128k", "192k", "320k"], default="128k"),
             ],
             hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo],

comfy_extras/nodes_hunyuan3d.py

@@ -637,7 +637,7 @@ class SaveGLB(IO.ComfyNode):
                     ],
                     tooltip="Mesh or 3D file to save",
                 ),
-                IO.String.Input("filename_prefix", default="mesh/ComfyUI_%year%%month%%day%-%hour%%minute%%second%"),
+                IO.String.Input("filename_prefix", default="mesh/ComfyUI"),
             ],
             hidden=[IO.Hidden.prompt, IO.Hidden.extra_pnginfo]
         )

comfy_extras/nodes_images.py

@@ -190,7 +190,7 @@ class SaveAnimatedWEBP(IO.ComfyNode):
             category="image/animation",
             inputs=[
                 IO.Image.Input("images"),
-                IO.String.Input("filename_prefix", default="ComfyUI_%year%%month%%day%-%hour%%minute%%second%"),
+                IO.String.Input("filename_prefix", default="ComfyUI"),
                 IO.Float.Input("fps", default=6.0, min=0.01, max=1000.0, step=0.01),
                 IO.Boolean.Input("lossless", default=True),
                 IO.Int.Input("quality", default=80, min=0, max=100),
@@ -227,7 +227,7 @@ class SaveAnimatedPNG(IO.ComfyNode):
             category="image/animation",
             inputs=[
                 IO.Image.Input("images"),
-                IO.String.Input("filename_prefix", default="ComfyUI_%year%%month%%day%-%hour%%minute%%second%"),
+                IO.String.Input("filename_prefix", default="ComfyUI"),
                 IO.Float.Input("fps", default=6.0, min=0.01, max=1000.0, step=0.01),
                 IO.Int.Input("compress_level", default=4, min=0, max=9, advanced=True),
             ],
@@ -489,7 +489,7 @@ class SaveSVGNode(IO.ComfyNode):
                 IO.SVG.Input("svg"),
                 IO.String.Input(
                     "filename_prefix",
-                    default="svg/ComfyUI_%year%%month%%day%-%hour%%minute%%second%",
+                    default="svg/ComfyUI",
                     tooltip="The prefix for the file to save. This may include formatting information such as %date:yyyy-MM-dd% or %Empty Latent Image.width% to include values from nodes.",
                 ),
             ],
@@ -566,7 +566,7 @@ class GetImageSize(IO.ComfyNode):
                 IO.Int.Output(display_name="height"),
                 IO.Int.Output(display_name="batch_size"),
             ],
-            hidden=[IO.Hidden.unique_id],
+            hidden=[IO.Hidden.unique_id, IO.Hidden.prompt_id],
         )
 
     @classmethod
@@ -577,7 +577,7 @@ class GetImageSize(IO.ComfyNode):
 
         # Send progress text to display size on the node
         if cls.hidden.unique_id:
-            PromptServer.instance.send_progress_text(f"width: {width}, height: {height}\n batch size: {batch_size}", cls.hidden.unique_id)
+            PromptServer.instance.send_progress_text(f"width: {width}, height: {height}\n batch size: {batch_size}", cls.hidden.unique_id, prompt_id=cls.hidden.prompt_id)
 
         return IO.NodeOutput(width, height, batch_size)
 
@@ -706,8 +706,8 @@ class SplitImageToTileList(IO.ComfyNode):
     @staticmethod
     def get_grid_coords(width, height, tile_width, tile_height, overlap):
         coords = []
-        stride_x = round(max(tile_width * 0.25, tile_width - overlap))
-        stride_y = round(max(tile_width * 0.25, tile_height - overlap))
+        stride_x = max(1, tile_width - overlap)
+        stride_y = max(1, tile_height - overlap)
 
         y = 0
         while y < height:
@@ -764,6 +764,34 @@ class ImageMergeTileList(IO.ComfyNode):
             ],
         )
 
+    @staticmethod
+    def get_grid_coords(width, height, tile_width, tile_height, overlap):
+        coords = []
+        stride_x = max(1, tile_width - overlap)
+        stride_y = max(1, tile_height - overlap)
+
+        y = 0
+        while y < height:
+            x = 0
+            y_end = min(y + tile_height, height)
+            y_start = max(0, y_end - tile_height)
+
+            while x < width:
+                x_end = min(x + tile_width, width)
+                x_start = max(0, x_end - tile_width)
+
+                coords.append((x_start, y_start, x_end, y_end))
+
+                if x_end >= width:
+                    break
+                x += stride_x
+
+            if y_end >= height:
+                break
+            y += stride_y
+
+        return coords
+
     @classmethod
     def execute(cls, image_list, final_width, final_height, overlap):
         w = final_width[0]
@@ -776,7 +804,7 @@ class ImageMergeTileList(IO.ComfyNode):
         device = first_tile.device
         dtype = first_tile.dtype
 
-        coords = SplitImageToTileList.get_grid_coords(w, h, t_w, t_h, ovlp)
+        coords = cls.get_grid_coords(w, h, t_w, t_h, ovlp)
 
         canvas = torch.zeros((b, h, w, c), device=device, dtype=dtype)
         weights = torch.zeros((b, h, w, 1), device=device, dtype=dtype)

comfy_extras/nodes_resolution.py

@@ -16,15 +16,15 @@ class AspectRatio(str, Enum):
     WIDESCREEN_V = "9:16 (Portrait Widescreen)"
 
 
-ASPECT_RATIOS: dict[AspectRatio, tuple[int, int]] = {
-    AspectRatio.SQUARE: (1, 1),
-    AspectRatio.PHOTO_H: (3, 2),
-    AspectRatio.STANDARD_H: (4, 3),
-    AspectRatio.WIDESCREEN_H: (16, 9),
-    AspectRatio.ULTRAWIDE_H: (21, 9),
-    AspectRatio.PHOTO_V: (2, 3),
-    AspectRatio.STANDARD_V: (3, 4),
-    AspectRatio.WIDESCREEN_V: (9, 16),
+ASPECT_RATIOS: dict[str, tuple[int, int]] = {
+    "1:1 (Square)": (1, 1),
+    "3:2 (Photo)": (3, 2),
+    "4:3 (Standard)": (4, 3),
+    "16:9 (Widescreen)": (16, 9),
+    "21:9 (Ultrawide)": (21, 9),
+    "2:3 (Portrait Photo)": (2, 3),
+    "3:4 (Portrait Standard)": (3, 4),
+    "9:16 (Portrait Widescreen)": (9, 16),
 }
 
 
@@ -55,12 +55,8 @@ class ResolutionSelector(io.ComfyNode):
                 ),
             ],
             outputs=[
-                io.Int.Output(
-                    "width", tooltip="Calculated width in pixels (multiple of 8)."
-                ),
-                io.Int.Output(
-                    "height", tooltip="Calculated height in pixels (multiple of 8)."
-                ),
+                io.Int.Output("width", tooltip="Calculated width in pixels (multiple of 8)."),
+                io.Int.Output("height", tooltip="Calculated height in pixels (multiple of 8)."),
             ],
         )
 

comfy_extras/nodes_video.py

@@ -21,7 +21,7 @@ class SaveWEBM(io.ComfyNode):
             is_experimental=True,
             inputs=[
                 io.Image.Input("images"),
-                io.String.Input("filename_prefix", default="ComfyUI_%year%%month%%day%-%hour%%minute%%second%"),
+                io.String.Input("filename_prefix", default="ComfyUI"),
                 io.Combo.Input("codec", options=["vp9", "av1"]),
                 io.Float.Input("fps", default=24.0, min=0.01, max=1000.0, step=0.01),
                 io.Float.Input("crf", default=32.0, min=0, max=63.0, step=1, tooltip="Higher crf means lower quality with a smaller file size, lower crf means higher quality higher filesize."),
@@ -77,7 +77,7 @@ class SaveVideo(io.ComfyNode):
             description="Saves the input images to your ComfyUI output directory.",
             inputs=[
                 io.Video.Input("video", tooltip="The video to save."),
-                io.String.Input("filename_prefix", default="video/ComfyUI_%year%%month%%day%-%hour%%minute%%second%", tooltip="The prefix for the file to save. This may include formatting information such as %date:yyyy-MM-dd% or %Empty Latent Image.width% to include values from nodes."),
+                io.String.Input("filename_prefix", default="video/ComfyUI", tooltip="The prefix for the file to save. This may include formatting information such as %date:yyyy-MM-dd% or %Empty Latent Image.width% to include values from nodes."),
                 io.Combo.Input("format", options=Types.VideoContainer.as_input(), default="auto", tooltip="The format to save the video as."),
                 io.Combo.Input("codec", options=Types.VideoCodec.as_input(), default="auto", tooltip="The codec to use for the video."),
             ],

execution.py

@@ -149,7 +149,7 @@ class CacheSet:
 
 SENSITIVE_EXTRA_DATA_KEYS = ("auth_token_comfy_org", "api_key_comfy_org")
 
-def get_input_data(inputs, class_def, unique_id, execution_list=None, dynprompt=None, extra_data={}):
+def get_input_data(inputs, class_def, unique_id, execution_list=None, dynprompt=None, extra_data={}, prompt_id=None):
     is_v3 = issubclass(class_def, _ComfyNodeInternal)
     v3_data: io.V3Data = {}
     hidden_inputs_v3 = {}
@@ -196,6 +196,8 @@ def get_input_data(inputs, class_def, unique_id, execution_list=None, dynprompt=
                 hidden_inputs_v3[io.Hidden.auth_token_comfy_org] = extra_data.get("auth_token_comfy_org", None)
             if io.Hidden.api_key_comfy_org.name in hidden:
                 hidden_inputs_v3[io.Hidden.api_key_comfy_org] = extra_data.get("api_key_comfy_org", None)
+            if io.Hidden.prompt_id.name in hidden:
+                hidden_inputs_v3[io.Hidden.prompt_id] = prompt_id
     else:
         if "hidden" in valid_inputs:
             h = valid_inputs["hidden"]
@@ -212,6 +214,8 @@ def get_input_data(inputs, class_def, unique_id, execution_list=None, dynprompt=
                     input_data_all[x] = [extra_data.get("auth_token_comfy_org", None)]
                 if h[x] == "API_KEY_COMFY_ORG":
                     input_data_all[x] = [extra_data.get("api_key_comfy_org", None)]
+                if h[x] == "PROMPT_ID":
+                    input_data_all[x] = [prompt_id]
     v3_data["hidden_inputs"] = hidden_inputs_v3
     return input_data_all, missing_keys, v3_data
 
@@ -469,7 +473,7 @@ async def execute(server, dynprompt, caches, current_item, extra_data, executed,
             has_subgraph = False
         else:
             get_progress_state().start_progress(unique_id)
-            input_data_all, missing_keys, v3_data = get_input_data(inputs, class_def, unique_id, execution_list, dynprompt, extra_data)
+            input_data_all, missing_keys, v3_data = get_input_data(inputs, class_def, unique_id, execution_list, dynprompt, extra_data, prompt_id=prompt_id)
             if server.client_id is not None:
                 server.last_node_id = display_node_id
                 server.send_sync("executing", { "node": unique_id, "display_node": display_node_id, "prompt_id": prompt_id }, server.client_id)

nodes.py

@@ -976,7 +976,7 @@ class CLIPLoader:
     @classmethod
     def INPUT_TYPES(s):
         return {"required": { "clip_name": (folder_paths.get_filename_list("text_encoders"), ),
-                              "type": (["stable_diffusion", "stable_cascade", "sd3", "stable_audio", "mochi", "ltxv", "pixart", "cosmos", "lumina2", "wan", "hidream", "chroma", "ace", "omnigen2", "qwen_image", "hunyuan_image", "flux2", "ovis", "longcat_image"], ),
+                              "type": (["stable_diffusion", "stable_cascade", "sd3", "stable_audio", "mochi", "ltxv", "pixart", "cosmos", "lumina2", "wan", "hidream", "chroma", "ace", "omnigen2", "qwen_image", "hunyuan_image", "flux2", "ovis"], ),
                               },
                 "optional": {
                               "device": (["default", "cpu"], {"advanced": True}),
@@ -1638,7 +1638,7 @@ class SaveImage:
         return {
             "required": {
                 "images": ("IMAGE", {"tooltip": "The images to save."}),
-                "filename_prefix": ("STRING", {"default": "ComfyUI_%year%%month%%day%-%hour%%minute%%second%", "tooltip": "The prefix for the file to save. This may include formatting information such as %date:yyyy-MM-dd% or %Empty Latent Image.width% to include values from nodes."})
+                "filename_prefix": ("STRING", {"default": "ComfyUI", "tooltip": "The prefix for the file to save. This may include formatting information such as %date:yyyy-MM-dd% or %Empty Latent Image.width% to include values from nodes."})
             },
             "hidden": {
                 "prompt": "PROMPT", "extra_pnginfo": "EXTRA_PNGINFO"

requirements.txt

@@ -31,4 +31,5 @@ spandrel
 pydantic~=2.0
 pydantic-settings~=2.0
 PyOpenGL
+PyOpenGL-accelerate
 glfw

server.py

@@ -1233,13 +1233,47 @@ class PromptServer():
         return json_data
 
     def send_progress_text(
-        self, text: Union[bytes, bytearray, str], node_id: str, sid=None
+        self,
+        text: Union[bytes, bytearray, str],
+        node_id: str,
+        prompt_id: Optional[str] = None,
+        sid=None,
     ):
+        """Send a progress text message to the client via WebSocket.
+
+        Encodes the text as a binary message with length-prefixed node_id. When
+        the client supports the ``supports_progress_text_metadata`` feature flag,
+        the prompt_id is always prepended as a length-prefixed field (empty string
+        when None) to ensure consistent binary framing.
+
+        Args:
+            text: The progress text content to send.
+            node_id: The unique identifier of the node sending the progress.
+            prompt_id: Optional prompt/job identifier to associate the message with.
+            sid: Optional session ID to target a specific client.
+        """
         if isinstance(text, str):
             text = text.encode("utf-8")
         node_id_bytes = str(node_id).encode("utf-8")
 
-        # Pack the node_id length as a 4-byte unsigned integer, followed by the node_id bytes
-        message = struct.pack(">I", len(node_id_bytes)) + node_id_bytes + text
+        # Auto-resolve sid to the currently executing client
+        target_sid = sid if sid is not None else self.client_id
 
-        self.send_sync(BinaryEventTypes.TEXT, message, sid)
+        # When client supports the new format, always send
+        # [prompt_id_len][prompt_id][node_id_len][node_id][text]
+        # even when prompt_id is None (encoded as zero-length string)
+        if feature_flags.supports_feature(
+            self.sockets_metadata, target_sid, "supports_progress_text_metadata"
+        ):
+            prompt_id_bytes = (prompt_id or "").encode("utf-8")
+            message = (
+                struct.pack(">I", len(prompt_id_bytes))
+                + prompt_id_bytes
+                + struct.pack(">I", len(node_id_bytes))
+                + node_id_bytes
+                + text
+            )
+        else:
+            message = struct.pack(">I", len(node_id_bytes)) + node_id_bytes + text
+
+        self.send_sync(BinaryEventTypes.TEXT, message, target_sid)

tests-unit/comfy_test/model_detection_test.py

@@ -1,112 +0,0 @@
-import torch
-
-from comfy.model_detection import detect_unet_config, model_config_from_unet_config
-import comfy.supported_models
-
-
-def _make_longcat_comfyui_sd():
-    """Minimal ComfyUI-format state dict for pre-converted LongCat-Image weights."""
-    sd = {}
-    H = 32  # Reduce hidden state dimension to reduce memory usage
-    C_IN = 16
-    C_CTX = 3584
-
-    sd["img_in.weight"] = torch.empty(H, C_IN * 4)
-    sd["img_in.bias"] = torch.empty(H)
-    sd["txt_in.weight"] = torch.empty(H, C_CTX)
-    sd["txt_in.bias"] = torch.empty(H)
-
-    sd["time_in.in_layer.weight"] = torch.empty(H, 256)
-    sd["time_in.in_layer.bias"] = torch.empty(H)
-    sd["time_in.out_layer.weight"] = torch.empty(H, H)
-    sd["time_in.out_layer.bias"] = torch.empty(H)
-
-    sd["final_layer.adaLN_modulation.1.weight"] = torch.empty(2 * H, H)
-    sd["final_layer.adaLN_modulation.1.bias"] = torch.empty(2 * H)
-    sd["final_layer.linear.weight"] = torch.empty(C_IN * 4, H)
-    sd["final_layer.linear.bias"] = torch.empty(C_IN * 4)
-
-    for i in range(19):
-        sd[f"double_blocks.{i}.img_attn.norm.key_norm.weight"] = torch.empty(128)
-        sd[f"double_blocks.{i}.img_attn.qkv.weight"] = torch.empty(3 * H, H)
-        sd[f"double_blocks.{i}.img_mod.lin.weight"] = torch.empty(H, H)
-    for i in range(38):
-        sd[f"single_blocks.{i}.modulation.lin.weight"] = torch.empty(H, H)
-
-    return sd
-
-
-def _make_flux_schnell_comfyui_sd():
-    """Minimal ComfyUI-format state dict for standard Flux Schnell."""
-    sd = {}
-    H = 32  # Reduce hidden state dimension to reduce memory usage
-    C_IN = 16
-
-    sd["img_in.weight"] = torch.empty(H, C_IN * 4)
-    sd["img_in.bias"] = torch.empty(H)
-    sd["txt_in.weight"] = torch.empty(H, 4096)
-    sd["txt_in.bias"] = torch.empty(H)
-
-    sd["double_blocks.0.img_attn.norm.key_norm.weight"] = torch.empty(128)
-    sd["double_blocks.0.img_attn.qkv.weight"] = torch.empty(3 * H, H)
-    sd["double_blocks.0.img_mod.lin.weight"] = torch.empty(H, H)
-
-    for i in range(19):
-        sd[f"double_blocks.{i}.img_attn.norm.key_norm.weight"] = torch.empty(128)
-    for i in range(38):
-        sd[f"single_blocks.{i}.modulation.lin.weight"] = torch.empty(H, H)
-
-    return sd
-
-
-class TestModelDetection:
-    """Verify that first-match model detection selects the correct model
-    based on list ordering and unet_config specificity."""
-
-    def test_longcat_before_schnell_in_models_list(self):
-        """LongCatImage must appear before FluxSchnell in the models list."""
-        models = comfy.supported_models.models
-        longcat_idx = next(i for i, m in enumerate(models) if m.__name__ == "LongCatImage")
-        schnell_idx = next(i for i, m in enumerate(models) if m.__name__ == "FluxSchnell")
-        assert longcat_idx < schnell_idx, (
-            f"LongCatImage (index {longcat_idx}) must come before "
-            f"FluxSchnell (index {schnell_idx}) in the models list"
-        )
-
-    def test_longcat_comfyui_detected_as_longcat(self):
-        sd = _make_longcat_comfyui_sd()
-        unet_config = detect_unet_config(sd, "")
-        assert unet_config is not None
-        assert unet_config["image_model"] == "flux"
-        assert unet_config["context_in_dim"] == 3584
-        assert unet_config["vec_in_dim"] is None
-        assert unet_config["guidance_embed"] is False
-        assert unet_config["txt_ids_dims"] == [1, 2]
-
-        model_config = model_config_from_unet_config(unet_config, sd)
-        assert model_config is not None
-        assert type(model_config).__name__ == "LongCatImage"
-
-    def test_longcat_comfyui_keys_pass_through_unchanged(self):
-        """Pre-converted weights should not be transformed by process_unet_state_dict."""
-        sd = _make_longcat_comfyui_sd()
-        unet_config = detect_unet_config(sd, "")
-        model_config = model_config_from_unet_config(unet_config, sd)
-
-        processed = model_config.process_unet_state_dict(dict(sd))
-        assert "img_in.weight" in processed
-        assert "txt_in.weight" in processed
-        assert "time_in.in_layer.weight" in processed
-        assert "final_layer.linear.weight" in processed
-
-    def test_flux_schnell_comfyui_detected_as_flux_schnell(self):
-        sd = _make_flux_schnell_comfyui_sd()
-        unet_config = detect_unet_config(sd, "")
-        assert unet_config is not None
-        assert unet_config["image_model"] == "flux"
-        assert unet_config["context_in_dim"] == 4096
-        assert unet_config["txt_ids_dims"] == []
-
-        model_config = model_config_from_unet_config(unet_config, sd)
-        assert model_config is not None
-        assert type(model_config).__name__ == "FluxSchnell"