chore(openapi): sync shared API contract from cloud@5989e82

comfy/ldm/krea2/model.py

@@ -15,7 +15,6 @@ from einops import rearrange
 import comfy.model_management
 import comfy.patcher_extension
 import comfy.ldm.common_dit
-import comfy.utils
 from comfy.ldm.flux.layers import EmbedND, timestep_embedding
 from comfy.ldm.flux.math import apply_rope
 from comfy.ldm.modules.attention import optimized_attention_masked
@@ -159,44 +158,8 @@ class SingleStreamBlock(nn.Module):
         self.attn = Attention(features, heads, kvheads=kvheads, bias=bias, device=device, dtype=dtype, operations=operations)
         self.mlp = SwiGLU(features, multiplier, bias, device=device, dtype=dtype, operations=operations)
 
-    def forward(self, x, vec, freqs, mask=None, timestep_zero_index=None, transformer_options={}):
+    def forward(self, x, vec, freqs, mask=None, transformer_options={}):
         prescale, preshift, pregate, postscale, postshift, postgate = self.mod(vec)
-        if timestep_zero_index is not None:
-            bs = x.shape[0]
-            ref_prescale = prescale[bs:]
-            ref_preshift = preshift[bs:]
-            ref_pregate = pregate[bs:]
-            ref_postscale = postscale[bs:]
-            ref_postshift = postshift[bs:]
-            ref_postgate = postgate[bs:]
-            prescale = prescale[:bs]
-            preshift = preshift[:bs]
-            pregate = pregate[:bs]
-            postscale = postscale[:bs]
-            postshift = postshift[:bs]
-            postgate = postgate[:bs]
-
-            pre = self.prenorm(x)
-            pre[:, :timestep_zero_index].mul_(1 + prescale).add_(preshift)
-            pre[:, timestep_zero_index:].mul_(1 + ref_prescale).add_(ref_preshift)
-            attn = self.attn(pre, freqs, mask, transformer_options=transformer_options)
-            del pre
-            attn[:, :timestep_zero_index].mul_(pregate)
-            attn[:, timestep_zero_index:].mul_(ref_pregate)
-            x = x + attn
-            del attn
-
-            post = self.postnorm(x)
-            post[:, :timestep_zero_index].mul_(1 + postscale).add_(postshift)
-            post[:, timestep_zero_index:].mul_(1 + ref_postscale).add_(ref_postshift)
-            mlp = self.mlp(post)
-            del post
-            mlp[:, :timestep_zero_index].mul_(postgate)
-            mlp[:, timestep_zero_index:].mul_(ref_postgate)
-            x = x + mlp
-            del mlp
-            return x
-
         x = x + pregate * self.attn((1 + prescale) * self.prenorm(x) + preshift, freqs, mask, transformer_options=transformer_options)
         x = x + postgate * self.mlp((1 + postscale) * self.postnorm(x) + postshift)
         return x
@@ -258,96 +221,61 @@ class SingleStreamDiT(nn.Module):
             operations.Linear(features, features * 6, device=device, dtype=dtype),
         )
 
-    def forward(self, x, timesteps, context, attention_mask=None, ref_latents=None, transformer_options={}, **kwargs):
+    def forward(self, x, timesteps, context, attention_mask=None, transformer_options={}, **kwargs):
         return comfy.patcher_extension.WrapperExecutor.new_class_executor(
             self._forward,
             self,
             comfy.patcher_extension.get_all_wrappers(comfy.patcher_extension.WrappersMP.DIFFUSION_MODEL, transformer_options),
-        ).execute(x, timesteps, context, attention_mask, ref_latents, transformer_options, **kwargs)
+        ).execute(x, timesteps, context, attention_mask, transformer_options, **kwargs)
 
-    def process_img(self, x, index=0):
-        patch = self.patch
-        x = comfy.ldm.common_dit.pad_to_patch_size(x, (patch, patch))
-        h, w = x.shape[-2] // patch, x.shape[-1] // patch
-        img = rearrange(x, "b c (h ph) (w pw) -> b (h w) (c ph pw)", ph=patch, pw=patch)
-
-        img_ids = torch.zeros(h, w, 3, device=x.device, dtype=torch.float32)
-        img_ids[..., 0] = index
-        img_ids[..., 1] = torch.arange(h, device=x.device, dtype=torch.float32)[:, None]
-        img_ids[..., 2] = torch.arange(w, device=x.device, dtype=torch.float32)[None, :]
-        return img, img_ids.reshape(1, h * w, 3).repeat(x.shape[0], 1, 1), h, w
-
-    def _forward(self, x, timesteps, context, attention_mask=None, ref_latents=None, transformer_options={}, **kwargs):
+    def _forward(self, x, timesteps, context, attention_mask=None, transformer_options={}, **kwargs):
         temporal = x.ndim == 5
         if temporal:
             b5, c5, t5, h5, w5 = x.shape
             x = x.reshape(b5 * t5, c5, h5, w5)
-        bs, _, h_orig, w_orig = x.shape
+        bs, c, H_orig, W_orig = x.shape
         patch = self.patch
+        # Pad the latent up to a multiple of patch (as Flux/Lumina/QwenImage do); crop back at the end.
+        x = comfy.ldm.common_dit.pad_to_patch_size(x, (patch, patch))
+        H, W = x.shape[-2], x.shape[-1]
+        h_, w_ = H // patch, W // patch
 
         # context arrives as (B, seq, txtlayers*txtdim); reshape to (B, txtlayers, seq, txtdim).
         context = self._unpack_context(context)
 
-        img, imgpos, h_, w_ = self.process_img(x)
-        img_tokens = img.shape[1]
-        timestep_zero_index = None
-        if ref_latents is not None and len(ref_latents) > 0:
-            ref_tokens = []
-            ref_pos = []
-            ref_num_tokens = []
-            for index, ref in enumerate(ref_latents, 1):
-                if ref.ndim == 5:
-                    rb, rc, rt, rh5, rw5 = ref.shape
-                    ref = ref.reshape(rb * rt, rc, rh5, rw5)
-                ref = comfy.utils.repeat_to_batch_size(ref, bs)
-                kontext, kontext_ids, _, _ = self.process_img(ref, index=index)
-                ref_tokens.append(kontext)
-                ref_pos.append(kontext_ids)
-                ref_num_tokens.append(kontext.shape[1])
-            img = torch.cat([img] + ref_tokens, dim=1)
-            imgpos = torch.cat([imgpos] + ref_pos, dim=1)
-            del ref_tokens, ref_pos
-            timestep_zero_index = img_tokens
-            transformer_options = transformer_options.copy()
-            transformer_options["reference_image_num_tokens"] = ref_num_tokens
-
+        img = rearrange(x, "b c (h ph) (w pw) -> b (h w) (c ph pw)", ph=patch, pw=patch)
         img = self.first(img)
 
         t = self.tmlp(timestep_embedding(timesteps, self.tdim).unsqueeze(1).to(img.dtype))
         tvec = self.tproj(t)
-        if timestep_zero_index is not None:
-            t0 = self.tmlp(timestep_embedding(torch.zeros_like(timesteps), self.tdim).unsqueeze(1).to(img.dtype))
-            tvec = torch.cat((tvec, self.tproj(t0)), dim=0)
 
         context = self.txtfusion(context, mask=None, transformer_options=transformer_options)
         context = self.txtmlp(context)
 
-        txtlen = context.shape[1]
+        txtlen, imglen = context.shape[1], img.shape[1]
         combined = torch.cat((context, img), dim=1)
-        del context, img
-        if timestep_zero_index is not None:
-            timestep_zero_index += txtlen
 
         # Position ids: text at 0, image at (0, h_idx, w_idx).
         device = combined.device
         txtpos = torch.zeros(bs, txtlen, 3, device=device, dtype=torch.float32)
+        imgids = torch.zeros(h_, w_, 3, device=device, dtype=torch.float32)
+        imgids[..., 1] = torch.arange(h_, device=device, dtype=torch.float32)[:, None]
+        imgids[..., 2] = torch.arange(w_, device=device, dtype=torch.float32)[None, :]
+        imgpos = imgids.reshape(1, h_ * w_, 3).repeat(bs, 1, 1)
         pos = torch.cat((txtpos, imgpos), dim=1)
-        del txtpos, imgpos
 
         freqs = self.pe_embedder(pos)
-        del pos
 
         for block in self.blocks:
-            combined = block(combined, tvec, freqs, None, timestep_zero_index=timestep_zero_index, transformer_options=transformer_options)
+            combined = block(combined, tvec, freqs, None, transformer_options=transformer_options)
 
         final = self.last(combined, t)
-        del combined
-        out = final[:, txtlen:txtlen + img_tokens, :]
+        out = final[:, txtlen:txtlen + imglen, :]
         out = rearrange(out, "b (h w) (c ph pw) -> b c (h ph) (w pw)",
                         h=h_, w=w_, ph=patch, pw=patch, c=self.channels)
-        out = out[:, :, :h_orig, :w_orig]  # crop padding back off
+        out = out[:, :, :H_orig, :W_orig]  # crop padding back off
         if temporal:
-            out = out.reshape(b5, t5, self.channels, h_orig, w_orig).movedim(1, 2)
+            out = out.reshape(b5, t5, self.channels, H_orig, W_orig).movedim(1, 2)
         return out
 
     def _unpack_context(self, context):

comfy/model_base.py

@@ -2282,26 +2282,12 @@ class Ideogram4(BaseModel):
 class Krea2(BaseModel):
     def __init__(self, model_config, model_type=ModelType.FLUX, device=None):
         super().__init__(model_config, model_type, device=device, unet_model=comfy.ldm.krea2.model.SingleStreamDiT)
-        self.memory_usage_factor_conds = ("ref_latents",)
 
     def extra_conds(self, **kwargs):
         out = super().extra_conds(**kwargs)
         cross_attn = kwargs.get("cross_attn", None)
         if cross_attn is not None:
             out['c_crossattn'] = comfy.conds.CONDRegular(cross_attn)
-        ref_latents = kwargs.get("reference_latents", None)
-        if ref_latents is not None:
-            latents = []
-            for lat in ref_latents:
-                latents.append(self.process_latent_in(lat))
-            out['ref_latents'] = comfy.conds.CONDList(latents)
-        return out
-
-    def extra_conds_shapes(self, **kwargs):
-        out = {}
-        ref_latents = kwargs.get("reference_latents", None)
-        if ref_latents is not None:
-            out['ref_latents'] = list([1, 16, sum(map(lambda a: math.prod(a.size()), ref_latents)) // 16])
         return out
 
 class HunyuanImage21(BaseModel):

comfy/sd.py

@@ -1255,10 +1255,7 @@ class VAE:
             return None
 
     def is_dynamic(self):
-        # A VAE built from a state dict with no detectable VAE weights returns early
-        # from __init__ ("No VAE weights detected") before self.patcher is assigned.
-        patcher = getattr(self, "patcher", None)
-        return patcher is not None and patcher.is_dynamic()
+        return self.patcher.is_dynamic()
 
 class StyleModel:
     def __init__(self, model, device="cpu"):

comfy_api_nodes/apis/bytedance.py

@@ -24,8 +24,8 @@ class Seedream4TaskCreationRequest(BaseModel):
     image: list[str] | None = Field(None, description="Image URLs")
     size: str = Field(...)
     seed: int = Field(..., ge=0, le=2147483647)
-    sequential_image_generation: str | None = Field("disabled")
-    sequential_image_generation_options: Seedream4Options | None = Field(Seedream4Options(max_images=15))
+    sequential_image_generation: str = Field("disabled")
+    sequential_image_generation_options: Seedream4Options = Field(Seedream4Options(max_images=15))
     watermark: bool = Field(False)
     output_format: str | None = None
 
@@ -261,19 +261,6 @@ _PRESETS_SEEDREAM_4K = [
 
 _CUSTOM_PRESET = [("Custom", None, None)]
 
-_PRESETS_SEEDREAM_2K_PRO = [
-    ("(2K) 2048x2048 (1:1)", 2048, 2048),
-    ("(2K) 1728x2304 (3:4)", 1728, 2304),
-    ("(2K) 2304x1728 (4:3)", 2304, 1728),
-    # ("(2K) 2848x1600 (16:9)", 2848, 1600),  # 4,556,800 px - temporarily unavailable
-    # ("(2K) 1600x2848 (9:16)", 1600, 2848),  # 4,556,800 px - temporarily unavailable
-    ("(2K) 1664x2496 (2:3)", 1664, 2496),
-    ("(2K) 2496x1664 (3:2)", 2496, 1664),
-    # ("(2K) 3136x1344 (21:9)", 3136, 1344),  # 4,214,784 px - temporarily unavailable
-]
-RECOMMENDED_PRESETS_SEEDREAM_5_PRO = (
-    _PRESETS_SEEDREAM_1K + _PRESETS_SEEDREAM_2K_PRO + _CUSTOM_PRESET
-)
 RECOMMENDED_PRESETS_SEEDREAM_5_LITE = (
     _PRESETS_SEEDREAM_2K + _PRESETS_SEEDREAM_3K + _PRESETS_SEEDREAM_4K + _CUSTOM_PRESET
 )

comfy_api_nodes/nodes_bytedance.py

@@ -16,7 +16,6 @@ from comfy_api_nodes.apis.bytedance import (
     RECOMMENDED_PRESETS_SEEDREAM_4_0,
     RECOMMENDED_PRESETS_SEEDREAM_4_5,
     RECOMMENDED_PRESETS_SEEDREAM_5_LITE,
-    RECOMMENDED_PRESETS_SEEDREAM_5_PRO,
     SEEDANCE2_REF_VIDEO_PIXEL_LIMITS,
     VIDEO_TASKS_EXECUTION_TIME,
     GetAssetResponse,
@@ -81,14 +80,12 @@ _VERIFICATION_POLL_TIMEOUT_SEC = 120
 _VERIFICATION_POLL_INTERVAL_SEC = 3
 
 SEEDREAM_MODELS = {
-    "seedream 5.0 pro": "seedream-5-0-pro-260628",
     "seedream 5.0 lite": "seedream-5-0-260128",
     "seedream-4-5-251128": "seedream-4-5-251128",
     "seedream-4-0-250828": "seedream-4-0-250828",
 }
 
 SEEDREAM_PRESETS = {
-    "seedream-5-0-pro-260628": RECOMMENDED_PRESETS_SEEDREAM_5_PRO,
     "seedream-5-0-260128": RECOMMENDED_PRESETS_SEEDREAM_5_LITE,
     "seedream-4-5-251128": RECOMMENDED_PRESETS_SEEDREAM_4_5,
     "seedream-4-0-250828": RECOMMENDED_PRESETS_SEEDREAM_4_0,
@@ -746,15 +743,8 @@ class ByteDanceSeedreamNode(IO.ComfyNode):
         return IO.NodeOutput(torch.cat([await download_url_to_image_tensor(i) for i in urls]))
 
 
-def _seedream_model_inputs(
-    *,
-    max_ref_images: int,
-    presets: list,
-    max_width: int = 6240,
-    max_height: int = 4992,
-    supports_batch: bool = True,
-):
-    inputs = [
+def _seedream_model_inputs(*, max_ref_images: int, presets: list):
+    return [
         IO.Combo.Input(
             "size_preset",
             options=[label for label, _, _ in presets],
@@ -764,7 +754,7 @@ def _seedream_model_inputs(
             "width",
             default=2048,
             min=1024,
-            max=max_width,
+            max=6240,
             step=2,
             tooltip="Custom width for image. Value is working only if `size_preset` is set to `Custom`",
         ),
@@ -772,27 +762,22 @@ def _seedream_model_inputs(
             "height",
             default=2048,
             min=1024,
-            max=max_height,
+            max=4992,
             step=2,
             tooltip="Custom height for image. Value is working only if `size_preset` is set to `Custom`",
         ),
-    ]
-    if supports_batch:
-        inputs.append(
-            IO.Int.Input(
-                "max_images",
-                default=1,
-                min=1,
-                max=max_ref_images,
-                step=1,
-                display_mode=IO.NumberDisplay.number,
-                tooltip="Maximum number of images to generate. With 1, exactly one image is produced. "
-                "With >1, the model generates between 1 and max_images related images "
-                "(e.g., story scenes, character variations). "
-                "Total images (input + generated) cannot exceed 15.",
-            )
-        )
-    inputs.append(
+        IO.Int.Input(
+            "max_images",
+            default=1,
+            min=1,
+            max=max_ref_images,
+            step=1,
+            display_mode=IO.NumberDisplay.number,
+            tooltip="Maximum number of images to generate. With 1, exactly one image is produced. "
+            "With >1, the model generates between 1 and max_images related images "
+            "(e.g., story scenes, character variations). "
+            "Total images (input + generated) cannot exceed 15.",
+        ),
         IO.Autogrow.Input(
             "images",
             template=IO.Autogrow.TemplateNames(
@@ -802,18 +787,14 @@ def _seedream_model_inputs(
             ),
             tooltip=f"Optional reference image(s) for image-to-image or multi-reference generation. "
             f"Up to {max_ref_images} images.",
-        )
-    )
-    if supports_batch:
-        inputs.append(
-            IO.Boolean.Input(
-                "fail_on_partial",
-                default=False,
-                tooltip="If enabled, abort execution if any requested images are missing or return an error.",
-                advanced=True,
-            )
-        )
-    return inputs
+        ),
+        IO.Boolean.Input(
+            "fail_on_partial",
+            default=False,
+            tooltip="If enabled, abort execution if any requested images are missing or return an error.",
+            advanced=True,
+        ),
+    ]
 
 
 class ByteDanceSeedreamNodeV2(IO.ComfyNode):
@@ -835,16 +816,6 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
                 IO.DynamicCombo.Input(
                     "model",
                     options=[
-                        IO.DynamicCombo.Option(
-                            "seedream 5.0 pro",
-                            _seedream_model_inputs(
-                                max_ref_images=10,
-                                presets=RECOMMENDED_PRESETS_SEEDREAM_5_PRO,
-                                max_width=3136,
-                                max_height=2496,
-                                supports_batch=False,
-                            ),
-                        ),
                         IO.DynamicCombo.Option(
                             "seedream 5.0 lite",
                             _seedream_model_inputs(max_ref_images=14, presets=RECOMMENDED_PRESETS_SEEDREAM_5_LITE),
@@ -886,27 +857,15 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
             ],
             is_api_node=True,
             price_badge=IO.PriceBadge(
-                depends_on=IO.PriceBadgeDepends(
-                    widgets=["model", "model.size_preset", "model.width", "model.height"]
-                ),
+                depends_on=IO.PriceBadgeDepends(widgets=["model"]),
                 expr="""
                 (
-                  $sp := $lookup(widgets, "model.size_preset");
-                  $px := $lookup(widgets, "model.width") * $lookup(widgets, "model.height");
-                  $isPro := $contains(widgets.model, "5.0 pro");
-                  $price := $isPro
-                              ? (
-                                  $contains($sp, "custom")
-                                    ? ($px <= 2360000 ? 0.045 : 0.09)
-                                    : ($contains($sp, "1k") ? 0.045 : 0.09)
-                                )
-                              : $contains(widgets.model, "5.0 lite") ? 0.035
-                              : $contains(widgets.model, "4-5") ? 0.04
-                              : 0.03;
+                  $price := $contains(widgets.model, "5.0 lite") ? 0.035 :
+                            $contains(widgets.model, "4-5") ? 0.04 : 0.03;
                   {
-                    "type": "usd",
+                    "type":"usd",
                     "usd": $price,
-                    "format": { "suffix": $isPro ? "/Image" : " x images/Run", "approximate": true }
+                    "format": { "suffix":" x images/Run", "approximate": true }
                   }
                 )
                 """,
@@ -924,7 +883,6 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
         validate_string(prompt, strip_whitespace=True, min_length=1)
         model_id = SEEDREAM_MODELS[model["model"]]
         presets = SEEDREAM_PRESETS[model_id]
-        is_pro = "seedream-5-0-pro" in model_id
 
         size_preset = model.get("size_preset", presets[0][0])
         width = model.get("width", 2048)
@@ -944,29 +902,19 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
 
         out_num_pixels = w * h
         mp_provided = out_num_pixels / 1_000_000.0
-        if is_pro:
-            if out_num_pixels < 921_600:
-                raise ValueError(
-                    f"Minimum image resolution for the selected model is 0.92MP, but {mp_provided:.2f}MP provided."
-                )
-            if out_num_pixels > 4_194_304:
-                raise ValueError(
-                    f"Maximum image resolution for the selected model is 4.19MP, but {mp_provided:.2f}MP provided."
-                )
-        else:
-            if ("seedream-4-5" in model_id or "seedream-5-0" in model_id) and out_num_pixels < 3_686_400:
-                raise ValueError(
-                    f"Minimum image resolution for the selected model is 3.68MP, but {mp_provided:.2f}MP provided."
-                )
-            if "seedream-4-0" in model_id and out_num_pixels < 921_600:
-                raise ValueError(
-                    f"Minimum image resolution that the selected model can generate is 0.92MP, "
-                    f"but {mp_provided:.2f}MP provided."
-                )
-            if out_num_pixels > 16_777_216:
-                raise ValueError(
-                    f"Maximum image resolution for the selected model is 16.78MP, but {mp_provided:.2f}MP provided."
-                )
+        if ("seedream-4-5" in model_id or "seedream-5-0" in model_id) and out_num_pixels < 3686400:
+            raise ValueError(
+                f"Minimum image resolution for the selected model is 3.68MP, but {mp_provided:.2f}MP provided."
+            )
+        if "seedream-4-0" in model_id and out_num_pixels < 921600:
+            raise ValueError(
+                f"Minimum image resolution that the selected model can generate is 0.92MP, "
+                f"but {mp_provided:.2f}MP provided."
+            )
+        if out_num_pixels > 16_777_216:
+            raise ValueError(
+                f"Maximum image resolution for the selected model is 16.78MP, but {mp_provided:.2f}MP provided."
+            )
 
         image_tensors: list[Input.Image] = [t for t in images_dict.values() if t is not None]
         n_input_images = sum(get_number_of_images(t) for t in image_tensors)
@@ -1002,8 +950,8 @@ class ByteDanceSeedreamNodeV2(IO.ComfyNode):
                 image=reference_images_urls,
                 size=f"{w}x{h}",
                 seed=seed,
-                sequential_image_generation=None if is_pro else sequential_image_generation,
-                sequential_image_generation_options=None if is_pro else Seedream4Options(max_images=max_images),
+                sequential_image_generation=sequential_image_generation,
+                sequential_image_generation_options=Seedream4Options(max_images=max_images),
                 watermark=watermark,
             ),
         )

openapi.yaml

@@ -3297,6 +3297,12 @@ paths:
                             schema:
                                 $ref: '#/components/schemas/ErrorResponse'
                     description: Invalid request parameters
+                "401":
+                    content:
+                        application/json:
+                            schema:
+                                $ref: '#/components/schemas/ErrorResponse'
+                    description: Unauthorized - Authentication required
                 "500":
                     content:
                         application/json:

requirements.txt

@@ -1,5 +1,5 @@
 comfyui-frontend-package==1.45.20
-comfyui-workflow-templates==0.11.6
+comfyui-workflow-templates==0.11.2
 comfyui-embedded-docs==0.5.7
 torch
 torchsde