Merge branch 'master' into fix/node-replace-missing-class-type

comfy_api_nodes/apis/kling.py

@@ -134,6 +134,13 @@ class ImageToVideoWithAudioRequest(BaseModel):
     shot_type: str | None = Field(None)
 
 
+class KlingAvatarRequest(BaseModel):
+    image: str = Field(...)
+    sound_file: str = Field(...)
+    prompt: str | None = Field(None)
+    mode: str = Field(...)
+
+
 class MotionControlRequest(BaseModel):
     prompt: str = Field(...)
     image_url: str = Field(...)

comfy_api_nodes/nodes_kling.py

@@ -50,6 +50,7 @@ from comfy_api_nodes.apis import (
 )
 from comfy_api_nodes.apis.kling import (
     ImageToVideoWithAudioRequest,
+    KlingAvatarRequest,
     MotionControlRequest,
     MultiPromptEntry,
     OmniImageParamImage,
@@ -74,6 +75,7 @@ from comfy_api_nodes.util import (
     upload_image_to_comfyapi,
     upload_images_to_comfyapi,
     upload_video_to_comfyapi,
+    validate_audio_duration,
     validate_image_aspect_ratio,
     validate_image_dimensions,
     validate_string,
@@ -3139,6 +3141,103 @@ class KlingFirstLastFrameNode(IO.ComfyNode):
         return IO.NodeOutput(await download_url_to_video_output(final_response.data.task_result.videos[0].url))
 
 
+class KlingAvatarNode(IO.ComfyNode):
+
+    @classmethod
+    def define_schema(cls) -> IO.Schema:
+        return IO.Schema(
+            node_id="KlingAvatarNode",
+            display_name="Kling Avatar 2.0",
+            category="api node/video/Kling",
+            description="Generate broadcast-style digital human videos from a single photo and an audio file.",
+            inputs=[
+                IO.Image.Input(
+                    "image",
+                    tooltip="Avatar reference image. "
+                    "Width and height must be at least 300px. Aspect ratio must be between 1:2.5 and 2.5:1.",
+                ),
+                IO.Audio.Input(
+                    "sound_file",
+                    tooltip="Audio input. Must be between 2 and 300 seconds in duration.",
+                ),
+                IO.Combo.Input("mode", options=["std", "pro"]),
+                IO.String.Input(
+                    "prompt",
+                    multiline=True,
+                    default="",
+                    optional=True,
+                    tooltip="Optional prompt to define avatar actions, emotions, and camera movements.",
+                ),
+                IO.Int.Input(
+                    "seed",
+                    default=0,
+                    min=0,
+                    max=2147483647,
+                    display_mode=IO.NumberDisplay.number,
+                    control_after_generate=True,
+                    tooltip="Seed controls whether the node should re-run; "
+                    "results are non-deterministic regardless of seed.",
+                ),
+            ],
+            outputs=[
+                IO.Video.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=["mode"]),
+                expr="""
+                (
+                  $prices := {"std": 0.056, "pro": 0.112};
+                  {"type":"usd","usd": $lookup($prices, widgets.mode), "format":{"suffix":"/second"}}
+                )
+                """,
+            ),
+        )
+
+    @classmethod
+    async def execute(
+        cls,
+        image: Input.Image,
+        sound_file: Input.Audio,
+        mode: str,
+        seed: int,
+        prompt: str = "",
+    ) -> IO.NodeOutput:
+        validate_image_dimensions(image, min_width=300, min_height=300)
+        validate_image_aspect_ratio(image, (1, 2.5), (2.5, 1))
+        validate_audio_duration(sound_file, min_duration=2, max_duration=300)
+        response = await sync_op(
+            cls,
+            ApiEndpoint(path="/proxy/kling/v1/videos/avatar/image2video", method="POST"),
+            response_model=TaskStatusResponse,
+            data=KlingAvatarRequest(
+                image=await upload_image_to_comfyapi(cls, image),
+                sound_file=await upload_audio_to_comfyapi(
+                    cls, sound_file, container_format="mp3", codec_name="libmp3lame", mime_type="audio/mpeg"
+                ),
+                prompt=prompt or None,
+                mode=mode,
+            ),
+        )
+        if response.code:
+            raise RuntimeError(
+                f"Kling request failed. Code: {response.code}, Message: {response.message}, Data: {response.data}"
+            )
+        final_response = await poll_op(
+            cls,
+            ApiEndpoint(path=f"/proxy/kling/v1/videos/avatar/image2video/{response.data.task_id}"),
+            response_model=TaskStatusResponse,
+            status_extractor=lambda r: (r.data.task_status if r.data else None),
+            max_poll_attempts=800,
+        )
+        return IO.NodeOutput(await download_url_to_video_output(final_response.data.task_result.videos[0].url))
+
+
 class KlingExtension(ComfyExtension):
     @override
     async def get_node_list(self) -> list[type[IO.ComfyNode]]:
@@ -3167,6 +3266,7 @@ class KlingExtension(ComfyExtension):
             MotionControl,
             KlingVideoNode,
             KlingFirstLastFrameNode,
+            KlingAvatarNode,
         ]
 
 

comfy_extras/nodes_images.py

@@ -6,6 +6,7 @@ import folder_paths
 import json
 import os
 import re
+import math
 import torch
 import comfy.utils
 
@@ -682,6 +683,172 @@ class ImageScaleToMaxDimension(IO.ComfyNode):
     upscale = execute    # TODO: remove
 
 
+class SplitImageToTileList(IO.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="SplitImageToTileList",
+            category="image/batch",
+            search_aliases=["split image", "tile image", "slice image"],
+            display_name="Split Image into List of Tiles",
+            description="Splits an image into a batched list of tiles with a specified overlap.",
+            inputs=[
+                IO.Image.Input("image"),
+                IO.Int.Input("tile_width", default=1024, min=64, max=MAX_RESOLUTION),
+                IO.Int.Input("tile_height", default=1024, min=64, max=MAX_RESOLUTION),
+                IO.Int.Input("overlap", default=128, min=0, max=4096),
+            ],
+            outputs=[
+                IO.Image.Output(is_output_list=True),
+            ],
+        )
+
+    @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, tile_width, tile_height, overlap):
+        b, h, w, c = image.shape
+        coords = cls.get_grid_coords(w, h, tile_width, tile_height, overlap)
+
+        output_list = []
+        for (x_start, y_start, x_end, y_end) in coords:
+            tile = image[:, y_start:y_end, x_start:x_end, :]
+            output_list.append(tile)
+
+        return IO.NodeOutput(output_list)
+
+
+class ImageMergeTileList(IO.ComfyNode):
+    @classmethod
+    def define_schema(cls):
+        return IO.Schema(
+            node_id="ImageMergeTileList",
+            display_name="Merge List of Tiles to Image",
+            category="image/batch",
+            search_aliases=["split image", "tile image", "slice image"],
+            is_input_list=True,
+            inputs=[
+                IO.Image.Input("image_list"),
+                IO.Int.Input("final_width", default=1024, min=64, max=32768),
+                IO.Int.Input("final_height", default=1024, min=64, max=32768),
+                IO.Int.Input("overlap", default=128, min=0, max=4096),
+            ],
+            outputs=[
+                IO.Image.Output(is_output_list=False),
+            ],
+        )
+
+    @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]
+        h = final_height[0]
+        ovlp = overlap[0]
+        feather_str = 1.0
+
+        first_tile = image_list[0]
+        b, t_h, t_w, c = first_tile.shape
+        device = first_tile.device
+        dtype = first_tile.dtype
+
+        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)
+
+        if ovlp > 0:
+            y_w = torch.sin(math.pi * torch.linspace(0, 1, t_h, device=device, dtype=dtype))
+            x_w = torch.sin(math.pi * torch.linspace(0, 1, t_w, device=device, dtype=dtype))
+            y_w = torch.clamp(y_w, min=1e-5)
+            x_w = torch.clamp(x_w, min=1e-5)
+
+            sine_mask = (y_w.unsqueeze(1) * x_w.unsqueeze(0)).unsqueeze(0).unsqueeze(-1)
+            flat_mask = torch.ones_like(sine_mask)
+
+            weight_mask = torch.lerp(flat_mask, sine_mask, feather_str)
+        else:
+            weight_mask = torch.ones((1, t_h, t_w, 1), device=device, dtype=dtype)
+
+        for i, (x_start, y_start, x_end, y_end) in enumerate(coords):
+            if i >= len(image_list):
+                break
+
+            tile = image_list[i]
+
+            region_h = y_end - y_start
+            region_w = x_end - x_start
+
+            real_h = min(region_h, tile.shape[1])
+            real_w = min(region_w, tile.shape[2])
+
+            y_end_actual = y_start + real_h
+            x_end_actual = x_start + real_w
+
+            tile_crop = tile[:, :real_h, :real_w, :]
+            mask_crop = weight_mask[:, :real_h, :real_w, :]
+
+            canvas[:, y_start:y_end_actual, x_start:x_end_actual, :] += tile_crop * mask_crop
+            weights[:, y_start:y_end_actual, x_start:x_end_actual, :] += mask_crop
+
+        weights[weights == 0] = 1.0
+        merged_image = canvas / weights
+
+        return IO.NodeOutput(merged_image)
+
+
 class ImagesExtension(ComfyExtension):
     @override
     async def get_node_list(self) -> list[type[IO.ComfyNode]]:
@@ -701,6 +868,8 @@ class ImagesExtension(ComfyExtension):
             ImageRotate,
             ImageFlip,
             ImageScaleToMaxDimension,
+            SplitImageToTileList,
+            ImageMergeTileList,
         ]
 
 

requirements.txt

@@ -1,5 +1,5 @@
 comfyui-frontend-package==1.39.14
-comfyui-workflow-templates==0.8.43
+comfyui-workflow-templates==0.9.2
 comfyui-embedded-docs==0.4.1
 torch
 torchsde