update README & add sliding window example workling

fix wrong step count
remove video_formats from comfy folder_paths
2023-09-21 05:38:33 +07:00 · 2023-09-21 04:38:10 +07:00 · 2023-09-21 03:07:08 +07:00 · 2023-09-21 03:01:04 +07:00 · 2023-09-21 02:25:48 +07:00 · 2023-09-20 22:44:03 +07:00
18 changed files with 971 additions and 1832 deletions
@@ -1,201 +0,0 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.
@@ -11,53 +11,11 @@
 - Community modules: [manshoety/AD_Stabilized_Motion](https://huggingface.co/manshoety/AD_Stabilized_Motion) | [CiaraRowles/TemporalDiff](https://huggingface.co/CiaraRowles/TemporalDiff)
 - AnimateDiff v2 [mm_sd_v15_v2.ckpt](https://huggingface.co/guoyww/animatediff/blob/main/mm_sd_v15_v2.ckpt)

-## Update 2023/09/25
-
-#### **Motion LoRA** is now supported!
-
-Download [motion LoRAs](https://huggingface.co/guoyww/animatediff/tree/main) and put them under `comfyui-animatediff/loras/` folder.
-
-Note: LoRAs only work with **AnimateDiff v2** [mm_sd_v15_v2.ckpt](https://huggingface.co/guoyww/animatediff/blob/main/mm_sd_v15_v2.ckpt) module.
-
-#### New node: `AnimateDiffLoraLoader`
-
-<img width="370" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/7a9f62f7-702e-48a4-934c-bbfe1e23aff2">
-
-Example workflow:
-<img width="1280" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/93e7550f-4648-4482-9961-6cece5132dc9">
-
-Workflow: [lora.json](https://github.com/ArtVentureX/comfyui-animatediff/blob/main/workflows/lora.json)
-
-Samples:
-
-<table>
-<tr>
-<td>
-<img width="512" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/2c5aa25e-0682-481f-8842-066c5b988864">
-</td>
-</tr>
-<tr>
-<td>
-<img width="512" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/adfbad45-3ba5-42e3-9bee-d2b83f43989c">
-</td>
-</tr>
-<tr>
-<td>
-<img width="512" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/8e484c74-c691-4d1c-9514-719dbfe3a0b5">
-</td>
-</tr>
-<tr>
-<td>
-<img width="512" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/4921a335-9207-4a7b-9d66-61a5d76e3179">
-</td>
-</tr>
-</table>
-
 ## Update 2023/09/21

 #### **Sliding Window** is now available!

-The sliding window feature enables you to generate GIFs without a frame length limit. It divides frames into smaller batches with a slight overlap. This feature is activated automatically when generating more than 16 frames. To modify the trigger number and other settings, utilize the `SlidingWindowOptions` node. See the [sample workflow](#long-duration-with-sliding-window) bellow.
+Sliding window is trigged automatically when generating more than 16 frames. To adjust the trigger number and other options, use `SlidingWindowOptions` node. See the sample workflow bellow.

 ## Nodes

@@ -91,13 +49,7 @@ The sliding window feature enables you to generate GIFs without a frame length l
 Custom sliding window options

 - `context_length`: number of frame per _window_. Use **16** to get the best results. Reduce it if you have low VRAM.
- `context_stride`:
-  - 1: sampling every frame
-  - 2: sampling every frame then every second frame
-  - 3: sampling every frame then every second frame then every third frames
-  - ...
- `context_overlap`: overlap frames between each window slice
- `closed_loop`: make the GIF a closed loop, will add more sampling step
+- `closed_loop`: try to make the GIF a closed loop. Will take longer to render.

 <img width="370" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/6679a8dd-bf96-419f-8934-ea2b046dd23c">

@@ -131,19 +83,9 @@ Samples:
 Workflow: [sliding-window.json](https://github.com/ArtVentureX/comfyui-animatediff/blob/main/workflows/sliding-window.json)

 Samples:
+![AnimateDiff_00096_](https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/e1da7a66-e615-475d-9400-41eff484ad49)

-<table>
-<tr>
-<td>
-<img width="512" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/e1da7a66-e615-475d-9400-41eff484ad49">
-</td>
-</tr>
-<tr>
-<td>
-<img width="768" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/4faa7e5e-cdaa-49da-8759-46d779c0e0b6">
-</td>
-</tr>
-</table>
+![AnimateDiff_00099_](https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/4faa7e5e-cdaa-49da-8759-46d779c0e0b6)

 ### Latent upscale

@@ -216,10 +158,6 @@ Samples:

 ## Known Issues

-### CUDA error: invalid configuration argument
-
-It's an `xformers` bug accidentally triggered by the way the original AnimateDiff CrossAttention is passed in. The current workaround is to disable xformers with `--disable-xformers` when booting ComfyUI.
-
 ### GIF split into multiple scenes

 ![AnimateDiff_00007_](https://github.com/ArtVentureX/comfyui-animatediff/assets/8894763/e6cd53cb-9878-45da-a58a-a15851882386)
@@ -1,6 +1,5 @@
 import os
 import hashlib
-import torch
 from typing import Dict

 import folder_paths
@@ -12,7 +11,6 @@ from .motion_module import MotionWrapper


 motion_modules: Dict[str, MotionWrapper] = {}
-motion_loras: Dict[str, Dict[str, torch.Tensor]] = {}


 folder_paths.folder_names_and_paths["AnimateDiff"] = (
@@ -22,34 +20,19 @@ folder_paths.folder_names_and_paths["AnimateDiff"] = (
    ],
    folder_paths.supported_pt_extensions,
 )
-folder_paths.folder_names_and_paths["AnimateDiffLora"] = (
-    [
-        os.path.join(folder_paths.models_dir, "AnimateDiffLora"),
-        os.path.join(os.path.dirname(os.path.abspath(__file__)), "..", "loras"),
-    ],
-    folder_paths.supported_pt_extensions,
-)


 def get_available_models():
    return folder_paths.get_filename_list("AnimateDiff")


-def get_available_loras():
-    return folder_paths.get_filename_list("AnimateDiffLora")
-
-
 def get_model_path(model_name):
    return folder_paths.get_full_path("AnimateDiff", model_name)


-def get_lora_path(lora_name):
-    return folder_paths.get_full_path("AnimateDiffLora", lora_name)
-
-
 def get_model_hash(file_path):
    with open(file_path, "rb") as f:
-        bytes = f.read(1024 * 1024)  # read entire file as bytes
+        bytes = f.read()  # read entire file as bytes
        return hashlib.sha256(bytes).hexdigest()


@@ -71,30 +54,3 @@ def load_motion_module(model_name: str):
        motion_modules[model_hash] = motion_module

    return motion_modules[model_hash]
-
-
-def load_lora(lora_name: str):
-    lora_path = get_lora_path(lora_name)
-    lora_hash = get_model_hash(lora_path)
-    if lora_hash not in motion_modules:
-        logger.info(f"Loading lora {lora_name}")
-        state_dict = load_torch_file(lora_path)
-        updated_state_dict: Dict[str, torch.Tensor] = {}
-
-        for key in state_dict:
-            # only process lora down key
-            if "up." in key:
-                continue
-
-            up_key = key.replace(".down.", ".up.")
-            model_key = key.replace("processor.", "").replace("_lora", "").replace("down.", "").replace("up.", "")
-            model_key = model_key.replace("to_out.", "to_out.0.")
-            combined_key = ".".join(model_key.split(".")[:-1])
-
-            weight_down = state_dict[key]
-            weight_up = state_dict[up_key]
-            updated_state_dict[combined_key] = torch.mm(weight_up, weight_down).to("cpu")
-
-        motion_loras[lora_hash] = updated_state_dict
-
-    return motion_loras[lora_hash]
@@ -1,35 +1,11 @@
+import os
 import torch
 from torch import Tensor, nn

 import math
 from einops import rearrange, repeat

-import comfy.model_management as model_management
-from comfy.ldm.modules.attention import (
-    default,
-    FeedForward,
-    CrossAttention as ComfyCrossAttention,
-    attention_basic,
-    attention_pytorch,
-    attention_split,
-    attention_sub_quad,
-)
-from comfy.cli_args import args
-
-from .logger import logger
-
-attention = attention_basic
-
-if model_management.xformers_enabled():
-    logger.warn("xformers is enabled but it has a bug that can cause issue while using with AnimateDiff.")
-
-if model_management.pytorch_attention_enabled():
-    attention = attention_pytorch
-else:
-    if args.use_split_cross_attention:
-        attention = attention_split
-    else:
-        attention = attention_sub_quad
+from comfy.ldm.modules.attention import FeedForward, CrossAttention


 def zero_module(module):
@@ -56,24 +32,6 @@ def has_mid_block(mm_state_dict: dict[str, Tensor]):
    return False


-class CrossAttention(ComfyCrossAttention):
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-
-    def forward(self, x, context=None, value=None, mask=None):
-        q = self.to_q(x)
-        context = default(context, x)
-        k = self.to_k(context)
-        if value is not None:
-            v = self.to_v(value)
-            del value
-        else:
-            v = self.to_v(context)
-
-        out = attention(q, k, v, self.heads, mask)
-        return self.to_out(out)
-
-
 class MotionWrapper(nn.Module):
    def __init__(self, mm_type: str, encoding_max_len: int = 24, is_v2=False):
        super().__init__()
@@ -86,11 +44,17 @@ class MotionWrapper(nn.Module):
        self.encoding_max_len = encoding_max_len

        for c in (320, 640, 1280, 1280):
-            self.down_blocks.append(MotionModule(c, BlockType.DOWN, encoding_max_len=encoding_max_len))
+            self.down_blocks.append(
+                MotionModule(c, BlockType.DOWN, encoding_max_len=encoding_max_len)
+            )
        for c in (1280, 1280, 640, 320):
-            self.up_blocks.append(MotionModule(c, BlockType.UP, encoding_max_len=encoding_max_len))
+            self.up_blocks.append(
+                MotionModule(c, BlockType.UP, encoding_max_len=encoding_max_len)
+            )
        if is_v2:
-            self.mid_block = MotionModule(1280, BlockType.MID, encoding_max_len=encoding_max_len)
+            self.mid_block = MotionModule(
+                1280, BlockType.MID, encoding_max_len=encoding_max_len
+            )

    @classmethod
    def from_state_dict(cls, mm_state_dict: dict[str, Tensor], mm_type: str):
@@ -127,7 +91,9 @@ class MotionModule(nn.Module):
        self.block_type = block_type

        if block_type == BlockType.MID:
-            self.motion_modules = nn.ModuleList([get_motion_module(in_channels, encoding_max_len)])
+            self.motion_modules = nn.ModuleList(
+                [get_motion_module(in_channels, encoding_max_len)]
+            )
        else:
            self.motion_modules = nn.ModuleList(
                [
@@ -136,7 +102,9 @@ class MotionModule(nn.Module):
                ]
            )
            if block_type == BlockType.UP:
-                self.motion_modules.append(get_motion_module(in_channels, encoding_max_len))
+                self.motion_modules.append(
+                    get_motion_module(in_channels, encoding_max_len)
+                )

    def set_video_length(self, video_length: int):
        for motion_module in self.motion_modules:
@@ -144,7 +112,9 @@ class MotionModule(nn.Module):


 def get_motion_module(in_channels, max_len):
-    return VanillaTemporalModule(in_channels=in_channels, temporal_position_encoding_max_len=max_len)
+    return VanillaTemporalModule(
+        in_channels=in_channels, temporal_position_encoding_max_len=max_len
+    )


 class VanillaTemporalModule(nn.Module):
@@ -165,7 +135,9 @@ class VanillaTemporalModule(nn.Module):
        self.temporal_transformer = TemporalTransformer3DModel(
            in_channels=in_channels,
            num_attention_heads=num_attention_heads,
-            attention_head_dim=in_channels // num_attention_heads // temporal_attention_dim_div,
+            attention_head_dim=in_channels
+            // num_attention_heads
+            // temporal_attention_dim_div,
            num_layers=num_transformer_block,
            attention_block_types=attention_block_types,
            cross_frame_attention_mode=cross_frame_attention_mode,
@@ -174,13 +146,17 @@ class VanillaTemporalModule(nn.Module):
        )

        if zero_initialize:
-            self.temporal_transformer.proj_out = zero_module(self.temporal_transformer.proj_out)
+            self.temporal_transformer.proj_out = zero_module(
+                self.temporal_transformer.proj_out
+            )

    def set_video_length(self, video_length: int):
        self.temporal_transformer.set_video_length(video_length)

-    def forward(self, input_tensor, encoder_hidden_states=None, attention_mask=None):
-        return self.temporal_transformer(input_tensor, encoder_hidden_states, attention_mask)
+    def forward(self, input_tensor, encoder_hidden_states, attention_mask=None):
+        return self.temporal_transformer(
+            input_tensor, encoder_hidden_states, attention_mask
+        )


 class TemporalTransformer3DModel(nn.Module):
@@ -208,7 +184,9 @@ class TemporalTransformer3DModel(nn.Module):

        inner_dim = num_attention_heads * attention_head_dim

-        self.norm = torch.nn.GroupNorm(num_groups=norm_num_groups, num_channels=in_channels, eps=1e-6, affine=True)
+        self.norm = torch.nn.GroupNorm(
+            num_groups=norm_num_groups, num_channels=in_channels, eps=1e-6, affine=True
+        )
        self.proj_in = nn.Linear(in_channels, inner_dim)

        self.transformer_blocks = nn.ModuleList(
@@ -243,7 +221,9 @@ class TemporalTransformer3DModel(nn.Module):

        hidden_states = self.norm(hidden_states)
        inner_dim = hidden_states.shape[1]
-        hidden_states = hidden_states.permute(0, 2, 3, 1).reshape(batch, height * weight, inner_dim)
+        hidden_states = hidden_states.permute(0, 2, 3, 1).reshape(
+            batch, height * weight, inner_dim
+        )
        hidden_states = self.proj_in(hidden_states)

        # Transformer Blocks
@@ -256,7 +236,11 @@ class TemporalTransformer3DModel(nn.Module):

        # output
        hidden_states = self.proj_out(hidden_states)
-        hidden_states = hidden_states.reshape(batch, height, weight, inner_dim).permute(0, 3, 1, 2).contiguous()
+        hidden_states = (
+            hidden_states.reshape(batch, height, weight, inner_dim)
+            .permute(0, 3, 1, 2)
+            .contiguous()
+        )

        output = hidden_states + residual

@@ -292,7 +276,9 @@ class TemporalTransformerBlock(nn.Module):
            attention_blocks.append(
                VersatileAttention(
                    attention_mode=block_name.split("_")[0],
-                    context_dim=cross_attention_dim if block_name.endswith("_Cross") else None,
+                    context_dim=cross_attention_dim
+                    if block_name.endswith("_Cross")
+                    else None,
                    query_dim=dim,
                    heads=num_attention_heads,
                    dim_head=attention_head_dim,
@@ -324,7 +310,9 @@ class TemporalTransformerBlock(nn.Module):
            hidden_states = (
                attention_block(
                    norm_hidden_states,
-                    encoder_hidden_states=encoder_hidden_states if attention_block.is_cross_attention else None,
+                    encoder_hidden_states=encoder_hidden_states
+                    if attention_block.is_cross_attention
+                    else None,
                    video_length=video_length,
                )
                + hidden_states
@@ -341,7 +329,9 @@ class PositionalEncoding(nn.Module):
        super().__init__()
        self.dropout = nn.Dropout(p=dropout)
        position = torch.arange(max_len).unsqueeze(1)
-        div_term = torch.exp(torch.arange(0, d_model, 2) * (-math.log(10000.0) / d_model))
+        div_term = torch.exp(
+            torch.arange(0, d_model, 2) * (-math.log(10000.0) / d_model)
+        )
        pe = torch.zeros(1, max_len, d_model)
        pe[0, :, 0::2] = torch.sin(position * div_term)
        pe[0, :, 1::2] = torch.cos(position * div_term)
@@ -393,7 +383,9 @@ class VersatileAttention(CrossAttention):
            raise NotImplementedError

        d = hidden_states.shape[1]
-        hidden_states = rearrange(hidden_states, "(b f) d c -> (b d) f c", f=video_length)
+        hidden_states = rearrange(
+            hidden_states, "(b f) d c -> (b d) f c", f=video_length
+        )

        if self.pos_encoder is not None:
            hidden_states = self.pos_encoder(hidden_states)
@@ -3,18 +3,16 @@ import json
 import torch
 import numpy as np
 import hashlib
-from typing import List, Dict, Tuple
+from typing import List
 from torch import Tensor
 from PIL import Image, ImageSequence
 from PIL.PngImagePlugin import PngInfo

 import folder_paths

-from .motion_module import MotionWrapper
-from .model_utils import get_available_models, load_motion_module, get_available_loras, load_lora
-from .utils import pil2tensor, ensure_opencv
+from .model_utils import get_available_models, load_motion_module
+from .utils import pil2tensor
 from .sampler import AnimateDiffSampler, AnimateDiffSlidingWindowOptions
-from .logger import logger


 SLIDING_CONTEXT_LENGTH = 16
@@ -30,99 +28,21 @@ class AnimateDiffModuleLoader:
            "required": {
                "model_name": (get_available_models(),),
            },
-            "optional": {
-                "lora_stack": ("MOTION_LORA_STACK",),
-            },
        }

    RETURN_TYPES = ("MOTION_MODULE",)
    CATEGORY = "Animate Diff"
    FUNCTION = "load_motion_module"

-    def inject_loras(self, motion_module: MotionWrapper, lora_stack: List[Tuple[Dict[str, Tensor], float]]):
-        for lora in lora_stack:
-            (state_dict, alpha) = lora
-
-            for key in state_dict:
-                layer_infos = key.split(".")
-
-                curr_layer = motion_module
-                while len(layer_infos) > 0:
-                    temp_name = layer_infos.pop(0)
-                    curr_layer = curr_layer.__getattr__(temp_name)
-
-                curr_layer.weight.data += alpha * state_dict[key].to(curr_layer.weight.data.device)
-
-    def eject_loras(self, motion_module: MotionWrapper, lora_stack: List[Tuple[float, Dict[str, Tensor]]]):
-        lora_stack.reverse() # should not matter but just in case
-        for lora in lora_stack:
-            (state_dict, alpha) = lora
-
-            for key in state_dict:
-                layer_infos = key.split(".")
-
-                curr_layer = motion_module
-                while len(layer_infos) > 0:
-                    temp_name = layer_infos.pop(0)
-                    curr_layer = curr_layer.__getattr__(temp_name)
-
-                curr_layer.weight.data -= alpha * state_dict[key].to(curr_layer.weight.data.device)
-
    def load_motion_module(
        self,
        model_name: str,
-        lora_stack: List = None,
    ):
        motion_module = load_motion_module(model_name)

-        # inject loras
-        if motion_module.is_v2:
-            if hasattr(motion_module, "lora_stack") and isinstance(motion_module.lora_stack, list):
-                self.eject_loras(motion_module, motion_module.lora_stack)
-                delattr(motion_module, "lora_stack")
-
-            if isinstance(lora_stack, list):
-                self.inject_loras(motion_module, lora_stack)
-                setattr(motion_module, "lora_stack", lora_stack)
-
-        elif isinstance(lora_stack, list):
-            logger.warning("LoRA is provided but only motion module v2 is supported.")
-
        return (motion_module,)


-class AnimateDiffLoraLoader:
-    @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-                "lora_name": (get_available_loras(),),
-                "alpha": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.001}),
-            },
-            "optional": {
-                "lora_stack": ("MOTION_LORA_STACK",),
-            },
-        }
-
-    RETURN_TYPES = ("MOTION_LORA_STACK",)
-    CATEGORY = "Animate Diff"
-    FUNCTION = "load_lora"
-
-    def load_lora(
-        self,
-        lora_name: str,
-        alpha: float,
-        lora_stack: List = None,
-    ):
-        if not lora_stack:
-            lora_stack = []
-
-        lora = load_lora(lora_name)
-        lora_stack.append((lora, alpha))
-
-        return (lora_stack,)
-
-
 class AnimateDiffCombine:
    @classmethod
    def INPUT_TYPES(s):
@@ -302,7 +222,6 @@ class LoadVideo:
        return frames

    def load_video(self, video_path, frame_start: int, frame_limit: int):
-        ensure_opencv()
        import cv2

        video = cv2.VideoCapture(video_path)
@@ -330,12 +249,12 @@ class LoadVideo:

        if ext.lower() in {".gif", ".webp"}:
            frames = self.load_gif(video_path, frame_start, frame_limit)
-        elif ext.lower() in {".webp", ".mp4", ".mov", ".avi", ".webm"}:
+        elif ext.lower() in {".webp", ".mp4", ".mov", ".avi"}:
            frames = self.load_video(video_path, frame_start, frame_limit)
        else:
            raise ValueError(f"Unsupported video format: {ext}")

-        return (torch.cat(frames, dim=0), len(frames))
+        return (torch.cat(frames, dim=0),)

    @classmethod
    def IS_CHANGED(s, image, *args, **kwargs):
@@ -404,7 +323,6 @@ class ImageChunking:

 NODE_CLASS_MAPPINGS = {
    "AnimateDiffModuleLoader": AnimateDiffModuleLoader,
-    "AnimateDiffLoraLoader": AnimateDiffLoraLoader,
    "AnimateDiffCombine": AnimateDiffCombine,
    "AnimateDiffSampler": AnimateDiffSampler,
    "AnimateDiffSlidingWindowOptions": AnimateDiffSlidingWindowOptions,
@@ -413,7 +331,6 @@ NODE_CLASS_MAPPINGS = {
 }
 NODE_DISPLAY_NAME_MAPPINGS = {
    "AnimateDiffModuleLoader": "Animate Diff Module Loader",
-    "AnimateDiffLoraLoader": "Animate Diff Lora Loader",
    "AnimateDiffSampler": "Animate Diff Sampler",
    "AnimateDiffSlidingWindowOptions": "Sliding Window Options",
    "AnimateDiffCombine": "Animate Diff Combine",
@@ -4,7 +4,9 @@ from torch.nn.functional import group_norm
 from einops import rearrange

 import comfy.ldm.modules.diffusionmodules.openaimodel as openaimodel
-from comfy.model_base import BaseModel, model_sampling
+import comfy.model_management as model_management
+from comfy.model_base import BaseModel
+from comfy.ldm.modules.attention import SpatialTransformer
 from nodes import KSampler

 from .logger import logger
@@ -16,19 +18,19 @@ from .sliding_context_sampling import SlidingContext, inject_sampling_function,
 SLIDING_CONTEXT_LENGTH = 16


-class ModelSamplingConfig:
-    def __init__(self, beta_schedule: str):
-        self.sampling_settings = {}
-        self.sampling_settings["beta_schedule"] = beta_schedule
-
-
-def forward_timestep_embed(ts, x, emb, context=None, *args, **kwargs):
+def forward_timestep_embed(ts, x, emb, context=None, transformer_options={}, output_shape=None):
    for layer in ts:
-        if isinstance(layer, VanillaTemporalModule):
+        if isinstance(layer, openaimodel.TimestepBlock):
+            x = layer(x, emb)
+        elif isinstance(layer, VanillaTemporalModule):
            x = layer(x, context)
+        elif isinstance(layer, SpatialTransformer):
+            x = layer(x, context, transformer_options)
+            transformer_options["current_index"] += 1
+        elif isinstance(layer, openaimodel.Upsample):
+            x = layer(x, output_shape=output_shape)
        else:
-            x = orig_forward_timestep_embed([layer], x, emb, context, *args, **kwargs)
-
+            x = layer(x)
    return x


@@ -47,6 +49,7 @@ def groupnorm_mm_factory(video_length: int):


 orig_forward_timestep_embed = openaimodel.forward_timestep_embed
+orig_maximum_batch_area = model_management.maximum_batch_area
 orig_groupnorm_forward = torch.nn.GroupNorm.forward


@@ -135,7 +138,7 @@ class AnimateDiffSlidingWindowOptions:
                "context_length": ("INT", {"default": SLIDING_CONTEXT_LENGTH, "min": 2, "max": 32}),
                "context_stride": ("INT", {"default": 1, "min": 1, "max": 32}),
                "context_overlap": ("INT", {"default": 4, "min": 0, "max": 32}),
-                "context_schedule": (ContextSchedules.CONTEXT_SCHEDULE_LIST, {"default": ContextSchedules.UNIFORM}),
+                "context_schedule": (ContextSchedules.CONTEXT_SCHEDULE_LIST,),
                "closed_loop": ("BOOLEAN", {"default": False}),
            }
        }
@@ -178,17 +181,32 @@ class AnimateDiffSampler(KSampler):

    def __init__(self) -> None:
        super().__init__()
-        self.model_sampling = None
+        self.prev_beta = None
+        self.prev_linear_start = None
+        self.prev_linear_end = None

    def override_beta_schedule(self, model: BaseModel):
-        self.model_sampling = model.model_sampling
-        model.model_sampling = model_sampling(
-            ModelSamplingConfig(beta_schedule="sqrt_linear"), model_type=model.model_type
+        self.prev_beta = model.get_buffer("betas").cpu().clone().detach()
+        self.prev_linear_start = model.linear_start
+        self.prev_linear_end = model.linear_end
+        model.register_schedule(
+            given_betas=None,
+            beta_schedule="sqrt_linear",
+            timesteps=1000,
+            linear_start=0.00085,
+            linear_end=0.012,
+            cosine_s=8e-3,
        )

    def restore_beta_schedule(self, model: BaseModel):
-        model.model_sampling = self.model_sampling
-        self.model_sampling = None
+        model.register_schedule(
+            given_betas=self.prev_beta,
+            linear_start=self.prev_linear_start,
+            linear_end=self.prev_linear_end,
+        )
+        self.prev_beta = None
+        self.prev_linear_start = None
+        self.prev_linear_end = None

    def inject_motion_module(self, model, motion_module: MotionWrapper, inject_method: str, frame_number: int):
        model = model.clone()
@@ -1,7 +1,6 @@
-import math
 import torch
 from torch import Tensor
-from typing import List, Dict
+import math

 import comfy.utils
 import comfy.sample
@@ -18,10 +17,6 @@ orig_comfy_sample = comfy.sample.sample
 orig_sampling_function = comfy_samplers.sampling_function


-def lcm(a, b):
-    return abs(a * b) // math.gcd(a, b)
-
-
 class SlidingContext:
    def __init__(
        self,
@@ -75,34 +70,47 @@ def __sliding_sample_factory(ctx: SlidingContext):

            ctx.current_step = start_step + step + 1

-        return orig_comfy_sample(model, *args, **kwargs, callback=callback)
+        try:
+            return orig_comfy_sample(model, *args, **kwargs, callback=callback)
+        except RuntimeError as e:
+            if str(e).startswith("CUDA error: invalid configuration argument"):
+                raise RuntimeError(
+                    f"An xformers bug was encountered in AnimateDiff - to run your workflow, \
+                                    disable xformers in ComfyUI using '--disable-xformers' startup argument."
+                )
+            raise

-    def sampling_function(model, x, timestep, uncond, cond, cond_scale, model_options={}, seed=None):
-        def get_area_and_mult(conds, x_in, timestep_in):
+    def sampling_function(
+        model_function, x, timestep, uncond, cond, cond_scale, cond_concat=None, model_options={}, seed=None
+    ):
+        def get_area_and_mult(cond, x_in, cond_concat_in, timestep_in):
            area = (x_in.shape[2], x_in.shape[3], 0, 0)
            strength = 1.0
-
-            if "timestep_start" in conds:
-                timestep_start = conds["timestep_start"]
+            if "timestep_start" in cond[1]:
+                timestep_start = cond[1]["timestep_start"]
                if timestep_in[0] > timestep_start:
                    return None
-            if "timestep_end" in conds:
-                timestep_end = conds["timestep_end"]
+            if "timestep_end" in cond[1]:
+                timestep_end = cond[1]["timestep_end"]
                if timestep_in[0] < timestep_end:
                    return None
-            if "area" in conds:
-                area = conds["area"]
-            if "strength" in conds:
-                strength = conds["strength"]
+            if "area" in cond[1]:
+                area = cond[1]["area"]
+            if "strength" in cond[1]:
+                strength = cond[1]["strength"]
+
+            adm_cond = None
+            if "adm_encoded" in cond[1]:
+                adm_cond = cond[1]["adm_encoded"]

            input_x = x_in[:, :, area[2] : area[0] + area[2], area[3] : area[1] + area[3]]
-            if "mask" in conds:
+            if "mask" in cond[1]:
                # Scale the mask to the size of the input
                # The mask should have been resized as we began the sampling process
                mask_strength = 1.0
-                if "mask_strength" in conds:
-                    mask_strength = conds["mask_strength"]
-                mask = conds["mask"]
+                if "mask_strength" in cond[1]:
+                    mask_strength = cond[1]["mask_strength"]
+                mask = cond[1]["mask"]
                assert mask.shape[1] == x_in.shape[2]
                assert mask.shape[2] == x_in.shape[3]
                mask = mask[:, area[2] : area[0] + area[2], area[3] : area[1] + area[3]] * mask_strength
@@ -111,7 +119,7 @@ def __sliding_sample_factory(ctx: SlidingContext):
                mask = torch.ones_like(input_x)
            mult = mask * strength

-            if "mask" not in conds:
+            if "mask" not in cond[1]:
                rr = 8
                if area[2] != 0:
                    for t in range(rr):
@@ -127,17 +135,24 @@ def __sliding_sample_factory(ctx: SlidingContext):
                        mult[:, :, :, area[1] - 1 - t : area[1] - t] *= (1.0 / rr) * (t + 1)

            conditionning = {}
-            model_conds = conds["model_conds"]
-            for c in model_conds:
-                conditionning[c] = model_conds[c].process_cond(batch_size=x_in.shape[0], device=x_in.device, area=area)
+            conditionning["c_crossattn"] = cond[0]
+            if cond_concat_in is not None and len(cond_concat_in) > 0:
+                cropped = []
+                for x in cond_concat_in:
+                    cr = x[:, :, area[2] : area[0] + area[2], area[3] : area[1] + area[3]]
+                    cropped.append(cr)
+                conditionning["c_concat"] = torch.cat(cropped, dim=1)
+
+            if adm_cond is not None:
+                conditionning["c_adm"] = adm_cond

            control = None
-            if "control" in conds:
-                control = conds["control"]
+            if "control" in cond[1]:
+                control = cond[1]["control"]

            patches = None
-            if "gligen" in conds:
-                gligen = conds["gligen"]
+            if "gligen" in cond[1]:
+                gligen = cond[1]["gligen"]
                patches = {}
                gligen_type = gligen[0]
                gligen_model = gligen[1]
@@ -155,8 +170,24 @@ def __sliding_sample_factory(ctx: SlidingContext):
                return True
            if c1.keys() != c2.keys():
                return False
-            for k in c1:
-                if not c1[k].can_concat(c2[k]):
+            if "c_crossattn" in c1:
+                s1 = c1["c_crossattn"].shape
+                s2 = c2["c_crossattn"].shape
+                if s1 != s2:
+                    if s1[0] != s2[0] or s1[2] != s2[2]:  # these 2 cases should not happen
+                        return False
+
+                    mult_min = comfy_samplers.lcm(s1[1], s2[1])
+                    diff = mult_min // min(s1[1], s2[1])
+                    if (
+                        diff > 4
+                    ):  # arbitrary limit on the padding because it's probably going to impact performance negatively if it's too much
+                        return False
+            if "c_concat" in c1:
+                if c1["c_concat"].shape != c2["c_concat"].shape:
+                    return False
+            if "c_adm" in c1:
+                if c1["c_adm"].shape != c2["c_adm"].shape:
                    return False
            return True

@@ -185,41 +216,55 @@ def __sliding_sample_factory(ctx: SlidingContext):
            c_concat = []
            c_adm = []
            crossattn_max_len = 0
-
-            temp = {}
            for x in c_list:
-                for k in x:
-                    cur = temp.get(k, [])
-                    cur.append(x[k])
-                    temp[k] = cur
-
+                if "c_crossattn" in x:
+                    c = x["c_crossattn"]
+                    if crossattn_max_len == 0:
+                        crossattn_max_len = c.shape[1]
+                    else:
+                        crossattn_max_len = comfy_samplers.lcm(crossattn_max_len, c.shape[1])
+                    c_crossattn.append(c)
+                if "c_concat" in x:
+                    c_concat.append(x["c_concat"])
+                if "c_adm" in x:
+                    c_adm.append(x["c_adm"])
            out = {}
-            for k in temp:
-                conds = temp[k]
-                out[k] = conds[0].concat(conds[1:])
+            c_crossattn_out = []
+            for c in c_crossattn:
+                if c.shape[1] < crossattn_max_len:
+                    c = c.repeat(1, crossattn_max_len // c.shape[1], 1)  # padding with repeat doesn't change result
+                c_crossattn_out.append(c)

+            if len(c_crossattn_out) > 0:
+                out["c_crossattn"] = torch.cat(c_crossattn_out)
+            if len(c_concat) > 0:
+                out["c_concat"] = torch.cat(c_concat)
+            if len(c_adm) > 0:
+                out["c_adm"] = torch.cat(c_adm)
            return out

-        def calc_cond_uncond_batch(model, cond, uncond, x_in, timestep, model_options):
+        def calc_cond_uncond_batch(
+            model_function, cond, uncond, x_in, timestep, max_total_area, cond_concat_in, model_options
+        ):
            out_cond = torch.zeros_like(x_in)
-            out_count = torch.ones_like(x_in) * 1e-37
+            out_count = torch.ones_like(x_in) / 100000.0

            out_uncond = torch.zeros_like(x_in)
-            out_uncond_count = torch.ones_like(x_in) * 1e-37
+            out_uncond_count = torch.ones_like(x_in) / 100000.0

            COND = 0
            UNCOND = 1

            to_run = []
            for x in cond:
-                p = get_area_and_mult(x, x_in, timestep)
+                p = get_area_and_mult(x, x_in, cond_concat_in, timestep)
                if p is None:
                    continue

                to_run += [(p, COND)]
            if uncond is not None:
                for x in uncond:
-                    p = get_area_and_mult(x, x_in, timestep)
+                    p = get_area_and_mult(x, x_in, cond_concat_in, timestep)
                    if p is None:
                        continue

@@ -236,11 +281,9 @@ def __sliding_sample_factory(ctx: SlidingContext):
                to_batch_temp.reverse()
                to_batch = to_batch_temp[:1]

-                free_memory = model_management.get_free_memory(x_in.device)
                for i in range(1, len(to_batch_temp) + 1):
                    batch_amount = to_batch_temp[: len(to_batch_temp) // i]
-                    input_shape = [len(batch_amount) * first_shape[0]] + list(first_shape)[1:]
-                    if model.memory_required(input_shape) < free_memory:
+                    if len(batch_amount) * first_shape[0] * first_shape[2] * first_shape[3] < max_total_area:
                        to_batch = batch_amount
                        break

@@ -290,11 +333,11 @@ def __sliding_sample_factory(ctx: SlidingContext):

                if "model_function_wrapper" in model_options:
                    output = model_options["model_function_wrapper"](
-                        model.apply_model,
+                        model_function,
                        {"input": input_x, "timestep": timestep_, "c": c, "cond_or_uncond": cond_or_uncond},
                    ).chunk(batch_chunks)
                else:
-                    output = model.apply_model(input_x, timestep_, **c).chunk(batch_chunks)
+                    output = model_function(input_x, timestep_, **c).chunk(batch_chunks)
                del input_x

                for o in range(batch_chunks):
@@ -318,11 +361,14 @@ def __sliding_sample_factory(ctx: SlidingContext):
            del out_count
            out_uncond /= out_uncond_count
            del out_uncond_count
+
            return out_cond, out_uncond

        # sliding_calc_cond_uncond_batch inspired by ashen's initial hack for 16-frame sliding context:
        # https://github.com/comfyanonymous/ComfyUI/compare/master...ashen-sensored:ComfyUI:master
-        def sliding_calc_cond_uncond_batch(model, cond, uncond, x_in, timestep, model_options):
+        def sliding_calc_cond_uncond_batch(
+            model_function, cond, uncond, x_in, timestep, max_total_area, cond_concat_in, model_options
+        ):
            # figure out how input is split
            axes_factor = x.size(0) // ctx.video_length

@@ -338,29 +384,37 @@ def __sliding_sample_factory(ctx: SlidingContext):
                control.full_latent_length = ctx.video_length
                control.context_length = ctx.context_length

-            def get_resized_cond(cond_in: List[Dict], full_idxs) -> list:
+            def get_resized_cond(cond_in, full_idxs) -> list:
                # reuse or resize cond items to match context requirements
                resized_cond = []
                # cond object is a list containing a list - outer list is irrelevant, so just loop through it
                for actual_cond in cond_in:
-                    new_cond_item = actual_cond.copy()
-                    for key, cond_item in new_cond_item.items():
+                    resized_actual_cond = []
+                    # now we are in the inner list - index 0 is tensor, index 1 is dictionary
+                    for cond_idx, cond_item in enumerate(actual_cond):
                        if isinstance(cond_item, Tensor):
                            # check that tensor is the expected length - x.size(0)
                            if cond_item.size(0) == x.size(0):
+                                pass
                                # if so, it's subsetting time - tell controls the expected indeces so they can handle them
                                actual_cond_item = cond_item[full_idxs]
-                                new_cond_item[key] = actual_cond_item
-                        elif key == "control":
-                            control_item = cond_item
-                            if hasattr(control_item, "sub_idxs"):
-                                prepare_control_objects(control_item, full_idxs)
+                                resized_actual_cond.append(actual_cond_item)
                            else:
-                                raise ValueError(
-                                    f"Control type {type(control_item).__name__} may not support required features for sliding context window; use Control objects from Kosinkadink/Advanced-ControlNet nodes."
-                                )
-                            new_cond_item[key] = cond_item
-                    resized_cond.append(new_cond_item)
+                                resized_actual_cond.append(cond_item)
+                        elif isinstance(cond_item, dict):
+                            # when in dictionary, look for control
+                            if "control" in cond_item:
+                                control_item = cond_item["control"]
+                                if hasattr(control_item, "sub_idxs"):
+                                    prepare_control_objects(control_item, full_idxs)
+                                else:
+                                    raise ValueError(
+                                        f"Control type {type(control_item).__name__} may not support required features for sliding context window; use Control objects from Kosinkadink/Advanced-ControlNet nodes."
+                                    )
+                            resized_actual_cond.append(cond_item)
+                        else:
+                            resized_actual_cond.append(cond_item)
+                    resized_cond.append(resized_actual_cond)
                return resized_cond

            # perform calc_cond_uncond_batch per context window
@@ -383,13 +437,16 @@ def __sliding_sample_factory(ctx: SlidingContext):
                sub_timestep = timestep[full_idxs]
                sub_cond = get_resized_cond(cond, full_idxs) if cond is not None else None
                sub_uncond = get_resized_cond(uncond, full_idxs) if uncond is not None else None
+                sub_cond_concat = get_resized_cond(cond_concat, full_idxs) if cond_concat is not None else None

                sub_cond_out, sub_uncond_out = calc_cond_uncond_batch(
-                    model,
+                    model_function,
                    sub_cond,
                    sub_uncond,
                    sub_x,
                    sub_timestep,
+                    max_total_area,
+                    sub_cond_concat,
                    model_options,
                )

@@ -402,21 +459,17 @@ def __sliding_sample_factory(ctx: SlidingContext):
            uncond_final /= out_count_final
            return cond_final, uncond_final

+        max_total_area = model_management.maximum_batch_area()
        if math.isclose(cond_scale, 1.0):
            uncond = None

-        cond, uncond = sliding_calc_cond_uncond_batch(model, cond, uncond, x, timestep, model_options)
+        cond, uncond = sliding_calc_cond_uncond_batch(
+            model_function, cond, uncond, x, timestep, max_total_area, cond_concat, model_options
+        )

        if "sampler_cfg_function" in model_options:
-            args = {
-                "cond": x - cond,
-                "uncond": x - uncond,
-                "cond_scale": cond_scale,
-                "timestep": timestep,
-                "input": x,
-                "sigma": timestep,
-            }
-            return x - model_options["sampler_cfg_function"](args)
+            args = {"cond": cond, "uncond": uncond, "cond_scale": cond_scale, "timestep": timestep}
+            return model_options["sampler_cfg_function"](args)
        else:
            return uncond + (cond - uncond) * cond_scale

@@ -424,10 +477,6 @@ def __sliding_sample_factory(ctx: SlidingContext):


 def inject_sampling_function(ctx: SlidingContext):
-    global orig_comfy_sample, orig_sampling_function
-    orig_comfy_sample = comfy.sample.sample
-    orig_sampling_function = comfy_samplers.sampling_function
-
    (sample, sampling_function) = __sliding_sample_factory(ctx)
    comfy.sample.sample = sample
    comfy_samplers.sampling_function = sampling_function
@@ -9,7 +9,7 @@ class ContextSchedules:
    UNIFORM_CONSTANT = "uniform_constant"
    UNIFORM_V2 = "uniform v2"

-    CONTEXT_SCHEDULE_LIST = [UNIFORM]
+    CONTEXT_SCHEDULE_LIST = [UNIFORM, UNIFORM_V2]


 # Returns fraction that has denominator that is a power of 2
@@ -142,12 +142,14 @@ def uniform_constant(
            # yield if not skipped
            yield to_yield

+
 def get_context_scheduler(name: str) -> Callable:
-    if name == ContextSchedules.UNIFORM:
-        return uniform
-    elif name == ContextSchedules.UNIFORM_CONSTANT:
-        return uniform_constant
-    elif name == ContextSchedules.UNIFORM_V2:
-        return uniform_v2
-    else:
-        raise ValueError(f"Unknown context_overlap policy {name}")
+    match name:
+        case ContextSchedules.UNIFORM:
+            return uniform
+        case ContextSchedules.UNIFORM_CONSTANT:
+            return uniform_constant
+        case ContextSchedules.UNIFORM_V2:
+            return uniform_v2
+        case _:
+            raise ValueError(f"Unknown context_overlap policy {name}")
@@ -1,32 +1,13 @@
-import sys
 import torch
 import numpy as np
-import subprocess
 from PIL import Image

-
-from .logger import logger
-
 # Tensor to PIL
 def tensor2pil(image):
-    return Image.fromarray(np.clip(255.0 * image.cpu().numpy().squeeze(), 0, 255).astype(np.uint8))
-
+    return Image.fromarray(
+        np.clip(255.0 * image.cpu().numpy().squeeze(), 0, 255).astype(np.uint8)
+    )

 # Convert PIL to Tensor
 def pil2tensor(image):
    return torch.from_numpy(np.array(image).astype(np.float32) / 255.0).unsqueeze(0)
-
-
-def ensure_opencv():
-    if "python_embeded" in sys.executable or "python_embedded" in sys.executable:
-        pip_install = [sys.executable, "-s", "-m", "pip", "install"]
-    else:
-        pip_install = [sys.executable, "-m", "pip", "install"]
-
-    try:
-        import cv2
-    except Exception as e:
-        try:
-            subprocess.check_call(pip_install + ['opencv-python'])
-        except:
-            logger.error(f"Failed to install 'opencv-python'. Please, install manually.")
@@ -1 +0,0 @@
-opencv-python
@@ -1,245 +1,162 @@
-import { app, ANIM_PREVIEW_WIDGET } from '../../../scripts/app.js';
+import { app } from "../../../scripts/app.js";
 import { api } from "../../../scripts/api.js";
-import { $el } from '../../../scripts/ui.js';
-import { createImageHost } from "../../../scripts/ui/imagePreview.js"

-const URL_REGEX = /^(https?:\/\/|\/view\?|data:image\/)/;
+function offsetDOMWidget(widget, ctx, node, widgetWidth, widgetY, height) {
+  const margin = 10;
+  const elRect = ctx.canvas.getBoundingClientRect();
+  const transform = new DOMMatrix()
+    .scaleSelf(
+      elRect.width / ctx.canvas.width,
+      elRect.height / ctx.canvas.height
+    )
+    .multiplySelf(ctx.getTransform())
+    .translateSelf(0, widgetY + margin);

-const style = `
-.comfy-img-preview video {
-  object-fit: contain;
-  width: var(--comfy-img-preview-width);
-  height: var(--comfy-img-preview-height);
-}
-`;
-
-export function chainCallback(object, property, callback) {
-  if (object == undefined) {
-    //This should not happen.
-    console.error("Tried to add callback to non-existant object");
-    return;
-  }
-  if (property in object) {
-    const callback_orig = object[property];
-    object[property] = function () {
-      const r = callback_orig.apply(this, arguments);
-      callback.apply(this, arguments);
-      return r;
-    };
-  } else {
-    object[property] = callback;
-  }
-};
-
-export function formatUploadedUrl(params) {
-  if (params.url) {
-    return params.url;
-  }
-
-  params = { ...params };
-
-  if (!params.filename && params.name) {
-    params.filename = params.name;
-    delete params.name;
-  }
-
-  return api.apiURL("/view?" + new URLSearchParams(params));
-};
-
-export function addVideoPreview(nodeType, options = {}) {
-  const createVideoNode = (url) => {
-    return new Promise((cb) => {
-      const videoEl = document.createElement('video');
-      Object.defineProperty(videoEl, 'naturalWidth', {
-        get: () => {
-          return videoEl.videoWidth;
-        },
-      });
-      Object.defineProperty(videoEl, 'naturalHeight', {
-        get: () => {
-          return videoEl.videoHeight;
-        },
-      });
-      videoEl.addEventListener('loadedmetadata', () => {
-        videoEl.controls = false;
-        videoEl.loop = true;
-        videoEl.muted = true;
-        cb(videoEl);
-      });
-      videoEl.addEventListener('error', () => {
-        cb();
-      });
-      videoEl.src = url;
-    });
-  };
-
-  const createImageNode = (url) => {
-    return new Promise((cb) => {
-      const imgEl = document.createElement('img');
-      imgEl.onload = () => {
-        cb(imgEl);
-      };
-      imgEl.addEventListener('error', () => {
-        cb();
-      });
-      imgEl.src = url;
-    });
-  };
-
-  nodeType.prototype.onDrawBackground = function (ctx) {
-    if (this.flags.collapsed) return;
-
-    let imageURLs = (this.images ?? []).map((i) =>
-      typeof i === 'string' ? i : formatUploadedUrl(i),
-    );
-    let imagesChanged = false;
-
-    if (JSON.stringify(this.displayingImages) !== JSON.stringify(imageURLs)) {
-      this.displayingImages = imageURLs;
-      imagesChanged = true;
-    }
-
-    if (!imagesChanged) return;
-    if (!imageURLs.length) {
-      this.imgs = null;
-      this.animatedImages = false;
-      return;
-    }
-
-    const promises = imageURLs.map((url) => {
-      if (url.startsWith('/view')) {
-        url = window.location.origin + url;
-      }
-
-      const u = new URL(url);
-      const filename =
-        u.searchParams.get('filename') || u.searchParams.get('name') || u.pathname.split('/').pop();
-      const ext = filename.split('.').pop();
-      const format = ['gif', 'webp', 'avif'].includes(ext) ? 'image' : 'video';
-      if (format === 'video') {
-        return createVideoNode(url);
-      } else {
-        return createImageNode(url);
-      }
-    });
-
-    Promise.all(promises)
-      .then((imgs) => {
-        this.imgs = imgs.filter(Boolean);
-      })
-      .then(() => {
-        if (!this.imgs.length) return;
-
-        this.animatedImages = true;
-        const widgetIdx = this.widgets?.findIndex((w) => w.name === ANIM_PREVIEW_WIDGET);
-
-        // Instead of using the canvas we'll use a IMG
-        if (widgetIdx > -1) {
-          // Replace content
-          const widget = this.widgets[widgetIdx];
-          widget.options.host.updateImages(this.imgs);
-        } else {
-          const host = createImageHost(this);
-          this.setSizeForImage(true);
-          const widget = this.addDOMWidget(ANIM_PREVIEW_WIDGET, 'img', host.el, {
-            host,
-            getHeight: host.getHeight,
-            onDraw: host.onDraw,
-            hideOnZoom: false,
-          });
-          widget.serializeValue = () => ({
-            height: host.el.clientHeight,
-          });
-          // widget.computeSize = (w) => ([w, 220]);
-
-          widget.options.host.updateImages(this.imgs);
-        }
-
-        this.imgs.forEach((img) => {
-          if (img instanceof HTMLVideoElement) {
-            img.muted = true;
-            img.autoplay = true;
-            img.play();
-          }
-        });
-      });
-  };
-
-  const { textWidget, comboWidget } = options;
-
-  if (textWidget) {
-    chainCallback(nodeType.prototype, 'onNodeCreated', function () {
-      const pathWidget = this.widgets.find((w) => w.name === textWidget);
-      pathWidget._value = pathWidget.value;
-      Object.defineProperty(pathWidget, 'value', {
-        set: (value) => {
-          pathWidget._value = value;
-          pathWidget.inputEl.value = value;
-          this.images = (value ?? '').split('\n').filter((url) => URL_REGEX.test(url));
-        },
-        get: () => {
-          return pathWidget._value;
-        },
-      });
-      pathWidget.inputEl.addEventListener('change', (e) => {
-        const value = e.target.value;
-        pathWidget._value = value;
-        this.images = (value ?? '').split('\n').filter((url) => URL_REGEX.test(url));
-      });
-
-      // Set value to ensure preview displays on initial add.
-      pathWidget.value = pathWidget._value;
-    });
-  }
-
-  if (comboWidget) {
-    chainCallback(nodeType.prototype, 'onNodeCreated', function () {
-      const pathWidget = this.widgets.find((w) => w.name === comboWidget);
-      pathWidget._value = pathWidget.value;
-      Object.defineProperty(pathWidget, 'value', {
-        set: (value) => {
-          pathWidget._value = value;
-          if (!value) {
-            return this.images = []
-          }
-
-          const parts = value.split("/")
-          const filename = parts.pop()
-          const subfolder = parts.join("/")
-          const extension = filename.split(".").pop();
-          const format = (["gif", "webp", "avif"].includes(extension)) ? 'image' : 'video'
-          this.images = [formatUploadedUrl({ filename, subfolder, type: "input", format: format })]
-        },
-        get: () => {
-          return pathWidget._value;
-        },
-      });
-
-      // Set value to ensure preview displays on initial add.
-      pathWidget.value = pathWidget._value;
-    });
-  }
-
-  chainCallback(nodeType.prototype, "onExecuted", function (message) {
-    if (message?.videos) {
-      this.images = message?.videos.map(formatUploadedUrl);
-    }
+  const scale = new DOMMatrix().scaleSelf(transform.a, transform.d);
+  Object.assign(widget.inputEl.style, {
+    transformOrigin: "0 0",
+    transform: scale,
+    left: `${transform.e}px`,
+    top: `${transform.d + transform.f}px`,
+    width: `${widgetWidth}px`,
+    height: `${(height || widget.parent?.inputHeight || 32) - margin}px`,
+    position: "absolute",
+    background: !node.color ? "" : node.color,
+    color: !node.color ? "" : "white",
+    zIndex: 5, //app.graph._nodes.indexOf(node),
  });
 }

-app.registerExtension({
-  name: "AnimateDiff.VideoPreview",
-  init() {
-    $el('style', {
-      textContent: style,
-      parent: document.head,
-    });
-  },
-  async beforeRegisterNodeDef(nodeType, nodeData) {
-    if (nodeData.name !== "AnimateDiffCombine") {
-      return;
-    }
+export const hasWidgets = (node) => {
+  if (!node.widgets || !node.widgets?.[Symbol.iterator]) {
+    return false;
+  }
+  return true;
+};

-    addVideoPreview(nodeType);
+export const cleanupNode = (node) => {
+  if (!hasWidgets(node)) {
+    return;
+  }
+
+  for (const w of node.widgets) {
+    if (w.canvas) {
+      w.canvas.remove();
+    }
+    if (w.inputEl) {
+      w.inputEl.remove();
+    }
+    // calls the widget remove callback
+    w.onRemoved?.();
+  }
+};
+
+export const CreatePreviewElement = (name, val, format, callback) => {
+  const [type] = format.split("/");
+
+  const w = {
+    name,
+    type,
+    value: val,
+    draw: function (ctx, node, widgetWidth, widgetY, height) {
+      const [cw, ch] = this.computeSize(widgetWidth);
+      offsetDOMWidget(this, ctx, node, widgetWidth, widgetY, ch);
+    },
+    computeSize: function (_) {
+      const ratio = this.inputRatio || 1;
+      const width = Math.max(220, this.parent.size[0]);
+      return [width, width / ratio + 10];
+    },
+    onRemoved: function () {
+      if (this.inputEl) {
+        this.inputEl.remove();
+      }
+    },
+  };
+
+  w.inputEl = document.createElement(type === "video" ? "video" : "img");
+  w.inputEl.src = w.value;
+  if (type === "video") {
+    w.inputEl.setAttribute("type", "video/webm");
+    w.inputEl.autoplay = true;
+    w.inputEl.loop = true;
+    w.inputEl.controls = false;
+  }
+  w.inputEl.onload = function () {
+    w.inputRatio = w.inputEl.naturalWidth / w.inputEl.naturalHeight;
+    callback?.();
+  };
+  document.body.appendChild(w.inputEl);
+  return w;
+};
+
+const videoPreview = {
+  name: "AnimateDiff.VideoPreview",
+  async beforeRegisterNodeDef(nodeType, nodeData, app) {
+    const onExecuted = nodeType.prototype.onExecuted;
+    nodeType.prototype.onExecuted = function (message) {
+      const r = onExecuted ? onExecuted.apply(this, message) : undefined;
+
+      if (message?.videos) {
+        this.videos = message.videos;
+      }
+
+      return r;
+    };
+
+    const onDrawBackground = nodeType.prototype.onDrawBackground;
+    nodeType.prototype.onDrawBackground = function (ctx) {
+      const r = onDrawBackground ? onDrawBackground.apply(this, arguments) : undefined;
+      const node = this;
+      const prefix = "ad_video_preview_";
+
+      if (node.videos_rendered === node.videos) {
+        return r;
+      }
+
+      if (node.widgets) {
+        const pos = node.widgets.findIndex((w) => w.name === `${prefix}_0`);
+        if (pos !== -1) {
+          for (let i = pos; i < node.widgets.length; i++) {
+            node.widgets[i].onRemoved?.();
+          }
+          node.widgets.length = pos;
+        }
+      }
+      if (node.videos) {
+        node.videos.forEach((params, i) => {
+          const previewUrl = api.apiURL(
+            "/view?" + new URLSearchParams(params).toString()
+          );
+          const w = node.addCustomWidget(
+            CreatePreviewElement(
+              `${prefix}_${i}`,
+              previewUrl,
+              params.format || "image/gif",
+              node.computeSizeKeepWidth.bind(node)
+            )
+          );
+          w.parent = node;
+        });
+        node.videos_rendered = node.videos;
+      }
+
+      return r;
+    };
+
+    const onRemoved = nodeType.prototype.onRemoved;
+    nodeType.prototype.onRemoved = function () {
+      cleanupNode(this);
+      return onRemoved ? onRemoved.apply(this, arguments) : undefined;
+    };
+
+    nodeType.prototype.computeSizeKeepWidth = function () {
+      this.setSize([
+        this.size[0],
+        this.computeSize([this.size[0], this.size[1]])[1],
+      ]);
+    };
  },
-});
+};
+
+app.registerExtension(videoPreview);
@@ -1,90 +1,188 @@
 import { app } from "../../../scripts/app.js";
 import { api } from "../../../scripts/api.js";
+import { ComfyWidgets } from "../../../scripts/widgets.js";

-import {
-  chainCallback,
-  addVideoPreview,
-} from "./vid_preview.js";
+const supportedVideoTypes = [
+  "image/gif",
+  "video/webm",
+  "video/mp4",
+  "video/mov",
+];

-async function uploadFile(file) {
-  try {
-    // Wrap file in formdata so it includes filename
-    const body = new FormData();
-    const new_file = new File([file], file.name, {
-      type: file.type,
-      lastModified: file.lastModified,
-    });
-    body.append("image", new_file);
-    body.append("subfolder", "video");
-    const resp = await api.fetchApi("/upload/image", {
-      method: "POST",
-      body,
-    });
+const VIDEOUPLOAD = (node, inputName, inputData, app) => {
+  const previewWidget = "ad_video_preview";
+  const videoWidget = node.widgets.find((w) => w.name === "video");
+  let uploadWidget;

-    if (resp.status === 200 || resp.status === 201) {
-      return resp.json();
-    } else {
-      alert(`Upload failed: ${resp.statusText}`);
+  const showVideo = (name) => {
+    let folder_separator = name.lastIndexOf("/");
+    let subfolder = "";
+    if (folder_separator > -1) {
+      subfolder = name.substring(0, folder_separator);
+      name = name.substring(folder_separator + 1);
    }
-  } catch (error) {
-    alert(`Upload failed: ${error}`);
-  }
-}
-
-function addUploadWidget(nodeType, widgetName) {
-  chainCallback(nodeType.prototype, "onNodeCreated", function () {
-    const pathWidget = this.widgets.find((w) => w.name === widgetName);
-    if (pathWidget.element) {
-      pathWidget.options.getMinHeight = () => 50;
-      pathWidget.options.getMaxHeight = () => 150;
-    }
-
-    const fileInput = document.createElement("input");
-    chainCallback(this, "onRemoved", () => {
-      fileInput?.remove();
-    });
-
-    Object.assign(fileInput, {
-      type: "file",
-      accept: "video/webm,video/mp4,video/mkv,image/gif,image/webp",
-      style: "display: none",
-      onchange: async () => {
-        if (fileInput.files.length) {
-          const params = await uploadFile(fileInput.files[0]);
-          if (!params) {
-            // upload failed and file can not be added to options
-            return;
-          }
-
-          fileInput.value = "";
-          const filename = [params.subfolder, params.name || params.filename].filter(Boolean).join('/')
-          pathWidget.value = filename;
-          pathWidget.options.values.push(filename);
-        }
+    const ext = name.substring(name.lastIndexOf(".") + 1);
+    const format = supportedVideoTypes.find((t) => t.endsWith(ext));
+    node.videos = [
+      {
+        filename: name,
+        type: "input",
+        subfolder: subfolder,
+        format,
      },
-    });
+    ];
+  };

-    document.body.append(fileInput);
-    let uploadWidget = this.addWidget(
-      "button",
-      "choose video to upload",
-      "image",
-      () => {
-        app.canvas.node_widget = null;
-        fileInput.click();
+  var default_value = videoWidget.value;
+  Object.defineProperty(videoWidget, "value", {
+    set: function (value) {
+      this._real_value = value;
+    },
+
+    get: function () {
+      let value = "";
+      if (this._real_value) {
+        value = this._real_value;
+      } else {
+        return default_value;
      }
-    );
-    uploadWidget.options.serialize = false;
+
+      if (value.filename) {
+        let real_value = value;
+        value = "";
+        if (real_value.subfolder) {
+          value = real_value.subfolder + "/";
+        }
+
+        value += real_value.filename;
+
+        if (real_value.type && real_value.type !== "input")
+          value += ` [${real_value.type}]`;
+      }
+      return value;
+    },
  });
-}
+
+  // Add our own callback to the combo widget to render an image when it changes
+  const cb = node.callback;
+  videoWidget.callback = function () {
+    showVideo(videoWidget.value);
+    if (cb) {
+      return cb.apply(this, arguments);
+    }
+  };
+
+  // On load if we have a value then render the image
+  // The value isnt set immediately so we need to wait a moment
+  // No change callbacks seem to be fired on initial setting of the value
+  requestAnimationFrame(() => {
+    if (videoWidget.value) {
+      showVideo(videoWidget.value);
+    }
+  });
+
+  async function uploadFile(file, updateNode, pasted = false) {
+    try {
+      // Wrap file in formdata so it includes filename
+      const body = new FormData();
+      body.append("image", file);
+      body.append("subfolder", "video");
+      const resp = await api.fetchApi("/upload/image", {
+        method: "POST",
+        body,
+      });
+
+      if (resp.status === 200) {
+        const data = await resp.json();
+        // Add the file to the dropdown list and update the widget value
+        let path = data.name;
+        if (data.subfolder) path = data.subfolder + "/" + path;
+
+        if (!videoWidget.options.values.includes(path)) {
+          videoWidget.options.values.push(path);
+        }
+
+        if (updateNode) {
+          showVideo(path);
+          videoWidget.value = path;
+        }
+      } else {
+        alert(resp.status + " - " + resp.statusText);
+      }
+    } catch (error) {
+      alert(error);
+    }
+  }
+
+  const fileInput = document.createElement("input");
+  Object.assign(fileInput, {
+    type: "file",
+    accept: supportedVideoTypes.join(","),
+    style: "display: none",
+    onchange: async () => {
+      if (fileInput.files.length) {
+        await uploadFile(fileInput.files[0], true);
+      }
+    },
+  });
+  document.body.append(fileInput);
+
+  // Create the button widget for selecting the files
+  uploadWidget = node.addWidget(
+    "button",
+    "choose file to upload",
+    "image",
+    () => {
+      fileInput.click();
+    }
+  );
+  uploadWidget.serialize = false;
+
+  // Add handler to check if an image is being dragged over our node
+  node.onDragOver = function (e) {
+    if (e.dataTransfer && e.dataTransfer.items) {
+      const image = [...e.dataTransfer.items].find((f) => f.kind === "file");
+      return !!image;
+    }
+
+    return false;
+  };
+
+  // On drop upload files
+  node.onDragDrop = function (e) {
+    console.log("onDragDrop called");
+    let handled = false;
+    for (const file of e.dataTransfer.files) {
+      if (file.type.startsWith("image/")) {
+        uploadFile(file, !handled); // Dont await these, any order is fine, only update on first one
+        handled = true;
+      }
+    }
+
+    return handled;
+  };
+
+  node.pasteFile = function (file) {
+    if (supportedVideoTypes.indexOf(file.type) > -1) {
+      const is_pasted =
+        file.name === "image.png" && file.lastModified - Date.now() < 2000;
+      uploadFile(file, true, is_pasted);
+      return true;
+    }
+    return false;
+  };
+
+  return { widget: uploadWidget };
+};
+
+ComfyWidgets["VIDEOUPLOAD"] = VIDEOUPLOAD;

 // Adds an upload button to the nodes
 app.registerExtension({
  name: "AnimateDiff.UploadVideo",
  async beforeRegisterNodeDef(nodeType, nodeData, app) {
    if (nodeData?.input?.required?.video?.[1]?.video_upload === true) {
-      addUploadWidget(nodeType, 'video');
-      addVideoPreview(nodeType, { comboWidget: 'video' });
+      nodeData.input.required.upload = ["VIDEOUPLOAD"];
    }
  },
 });
@@ -738,10 +738,10 @@
        60,
        140
      ],
-      "size": {
-        "0": 340,
-        "1": 110
-      },
+      "size": [
+        340,
+        110
+      ],
      "flags": {},
      "order": 10,
      "mode": 0,
@@ -780,7 +780,7 @@
      ],
      "size": {
        "0": 310,
-        "1": 350
+        "1": 330
      },
      "flags": {},
      "order": 30,
@@ -812,11 +812,6 @@
          "name": "latent_image",
          "type": "LATENT",
          "link": 80
-        },
-        {
-          "name": "sliding_window_opts",
-          "type": "SLIDING_WINDOW_OPTS",
-          "link": null
        }
      ],
      "outputs": [
@@ -1044,10 +1039,10 @@
        2140,
        140
      ],
-      "size": {
-        "0": 360,
-        "1": 552
-      },
+      "size": [
+        360,
+        552
+      ],
      "flags": {},
      "order": 32,
      "mode": 0,
@@ -1075,7 +1070,8 @@
        true,
        "AnimateDiff",
        "image/gif",
-        true
+        true,
+        "/view?filename=AnimateDiff_00090_.gif&subfolder=&type=output&format=image%2Fgif"
      ]
    },
    {
@@ -1114,6 +1110,49 @@
      "color": "#1a572e",
      "bgcolor": "#2e6b42"
    },
+    {
+      "id": 44,
+      "type": "VAEDecode",
+      "pos": [
+        1900,
+        520
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 31,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 81
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 82
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            172
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      },
+      "color": "#2e571a",
+      "bgcolor": "#426b2e"
+    },
    {
      "id": 4,
      "type": "CheckpointLoaderSimple",
@@ -1169,10 +1208,10 @@
        420,
        530
      ],
-      "size": {
-        "0": 260,
-        "1": 170
-      },
+      "size": [
+        260,
+        170
+      ],
      "flags": {},
      "order": 28,
      "mode": 0,
@@ -1439,49 +1478,6 @@
      ],
      "color": "#1a572e",
      "bgcolor": "#2e6b42"
-    },
-    {
-      "id": 44,
-      "type": "VAEDecode",
-      "pos": [
-        1898,
-        541
-      ],
-      "size": {
-        "0": 210,
-        "1": 46
-      },
-      "flags": {},
-      "order": 31,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "samples",
-          "type": "LATENT",
-          "link": 81
-        },
-        {
-          "name": "vae",
-          "type": "VAE",
-          "link": 82
-        }
-      ],
-      "outputs": [
-        {
-          "name": "IMAGE",
-          "type": "IMAGE",
-          "links": [
-            172
-          ],
-          "shape": 3,
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "VAEDecode"
-      },
-      "color": "#2e571a",
-      "bgcolor": "#426b2e"
    }
  ],
  "links": [
@@ -1,6 +1,6 @@
 {
-  "last_node_id": 107,
-  "last_link_id": 199,
+  "last_node_id": 106,
+  "last_link_id": 189,
  "nodes": [
    {
      "id": 16,
@@ -21,7 +21,7 @@
          "name": "MOTION_MODULE",
          "type": "MOTION_MODULE",
          "links": [
-            193
+            78
          ],
          "shape": 3,
          "slot_index": 0
@@ -77,10 +77,10 @@
        1240,
        140
      ],
-      "size": {
-        "0": 360,
-        "1": 732
-      },
+      "size": [
+        360,
+        732
+      ],
      "flags": {},
      "order": 13,
      "mode": 0,
@@ -108,7 +108,8 @@
        true,
        "AnimateDiff",
        "image/gif",
-        true
+        true,
+        "/view?filename=AnimateDiff_00092_.gif&subfolder=&type=output&format=image%2Fgif"
      ]
    },
    {
@@ -130,7 +131,7 @@
          "name": "MODEL",
          "type": "MODEL",
          "links": [
-            194
+            79
          ],
          "slot_index": 0
        },
@@ -166,10 +167,10 @@
        60,
        300
      ],
-      "size": {
-        "0": 310,
-        "1": 100
-      },
+      "size": [
+        310,
+        100
+      ],
      "flags": {},
      "order": 6,
      "mode": 0,
@@ -206,10 +207,10 @@
        60,
        140
      ],
-      "size": {
-        "0": 310,
-        "1": 110
-      },
+      "size": [
+        310,
+        110
+      ],
      "flags": {},
      "order": 5,
      "mode": 0,
@@ -239,6 +240,94 @@
      "color": "#572e1a",
      "bgcolor": "#6b422e"
    },
+    {
+      "id": 41,
+      "type": "AnimateDiffSampler",
+      "pos": [
+        900,
+        140
+      ],
+      "size": [
+        310,
+        330
+      ],
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "motion_module",
+          "type": "MOTION_MODULE",
+          "link": 78,
+          "slot_index": 0
+        },
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 79,
+          "slot_index": 1
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 176
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 180
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 80
+        },
+        {
+          "name": "frame_number",
+          "type": "INT",
+          "link": 185,
+          "widget": {
+            "name": "frame_number",
+            "config": [
+              "INT",
+              {
+                "default": 16,
+                "min": 2,
+                "max": 32,
+                "step": 1
+              }
+            ]
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            81
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AnimateDiffSampler"
+      },
+      "widgets_values": [
+        "default",
+        16,
+        345029849956754,
+        "fixed",
+        20,
+        8,
+        "euler",
+        "normal",
+        1
+      ],
+      "color": "#57571a",
+      "bgcolor": "#6b6b2e"
+    },
    {
      "id": 39,
      "type": "ControlNetApplyAdvanced",
@@ -246,10 +335,10 @@
        471,
        275
      ],
-      "size": {
-        "0": 300,
-        "1": 170
-      },
+      "size": [
+        300,
+        170
+      ],
      "flags": {},
      "order": 9,
      "mode": 0,
@@ -280,7 +369,7 @@
          "name": "positive",
          "type": "CONDITIONING",
          "links": [
-            195
+            176
          ],
          "shape": 3,
          "slot_index": 0
@@ -289,7 +378,7 @@
          "name": "negative",
          "type": "CONDITIONING",
          "links": [
-            196
+            180
          ],
          "shape": 3,
          "slot_index": 1
@@ -306,6 +395,50 @@
      "color": "#43571a",
      "bgcolor": "#576b2e"
    },
+    {
+      "id": 44,
+      "type": "VAEDecode",
+      "pos": [
+        1000,
+        520
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 81
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 82
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            172,
+            187
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      },
+      "color": "#2e571a",
+      "bgcolor": "#426b2e"
+    },
    {
      "id": 103,
      "type": "LoadVideo",
@@ -357,10 +490,10 @@
        520,
        630
      ],
-      "size": {
-        "0": 210,
-        "1": 80
-      },
+      "size": [
+        210,
+        80
+      ],
      "flags": {},
      "order": 10,
      "mode": 0,
@@ -368,7 +501,7 @@
        {
          "name": "width",
          "type": "INT",
-          "link": 190,
+          "link": 189,
          "widget": {
            "name": "width",
            "config": [
@@ -385,7 +518,7 @@
        {
          "name": "height",
          "type": "INT",
-          "link": 191,
+          "link": 188,
          "widget": {
            "name": "height",
            "config": [
@@ -405,7 +538,7 @@
          "name": "LATENT",
          "type": "LATENT",
          "links": [
-            197
+            80
          ],
          "shape": 3,
          "slot_index": 0
@@ -422,6 +555,62 @@
      "color": "#1a572e",
      "bgcolor": "#2e6b42"
    },
+    {
+      "id": 104,
+      "type": "ImageSizeAndBatchSize",
+      "pos": [
+        300,
+        630
+      ],
+      "size": [
+        190,
+        80
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 182
+        }
+      ],
+      "outputs": [
+        {
+          "name": "width",
+          "type": "INT",
+          "links": [
+            188
+          ],
+          "shape": 3,
+          "slot_index": 0
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": [
+            189
+          ],
+          "shape": 3,
+          "slot_index": 1
+        },
+        {
+          "name": "batch_size",
+          "type": "INT",
+          "links": [
+            185
+          ],
+          "shape": 3,
+          "slot_index": 2
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageSizeAndBatchSize"
+      },
+      "color": "#1a5757",
+      "bgcolor": "#2e6b6b"
+    },
    {
      "id": 36,
      "type": "ControlNetLoaderAdvanced",
@@ -429,10 +618,10 @@
        -280,
        540
      ],
-      "size": {
-        "0": 310,
-        "1": 60
-      },
+      "size": [
+        310,
+        60
+      ],
      "flags": {},
      "order": 4,
      "mode": 0,
@@ -471,10 +660,10 @@
        70,
        830
      ],
-      "size": {
-        "0": 530,
-        "1": 420
-      },
+      "size": [
+        530,
+        420
+      ],
      "flags": {},
      "order": 8,
      "mode": 0,
@@ -498,10 +687,10 @@
        670,
        830
      ],
-      "size": {
-        "0": 530,
-        "1": 420
-      },
+      "size": [
+        530,
+        420
+      ],
      "flags": {},
      "order": 14,
      "mode": 0,
@@ -517,195 +706,6 @@
      },
      "color": "#1a5757",
      "bgcolor": "#2e6b6b"
-    },
-    {
-      "id": 104,
-      "type": "ImageSizeAndBatchSize",
-      "pos": [
-        258,
-        631
-      ],
-      "size": {
-        "0": 226.8000030517578,
-        "1": 80
-      },
-      "flags": {},
-      "order": 7,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "image",
-          "type": "IMAGE",
-          "link": 182
-        }
-      ],
-      "outputs": [
-        {
-          "name": "width",
-          "type": "INT",
-          "links": [
-            190
-          ],
-          "shape": 3,
-          "slot_index": 0
-        },
-        {
-          "name": "height",
-          "type": "INT",
-          "links": [
-            191
-          ],
-          "shape": 3,
-          "slot_index": 1
-        },
-        {
-          "name": "batch_size",
-          "type": "INT",
-          "links": [
-            198
-          ],
-          "shape": 3,
-          "slot_index": 2
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "ImageSizeAndBatchSize"
-      },
-      "color": "#1a5757",
-      "bgcolor": "#2e6b6b"
-    },
-    {
-      "id": 44,
-      "type": "VAEDecode",
-      "pos": [
-        1000,
-        548
-      ],
-      "size": {
-        "0": 210,
-        "1": 46
-      },
-      "flags": {},
-      "order": 12,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "samples",
-          "type": "LATENT",
-          "link": 199
-        },
-        {
-          "name": "vae",
-          "type": "VAE",
-          "link": 82
-        }
-      ],
-      "outputs": [
-        {
-          "name": "IMAGE",
-          "type": "IMAGE",
-          "links": [
-            172,
-            187
-          ],
-          "shape": 3,
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "VAEDecode"
-      },
-      "color": "#2e571a",
-      "bgcolor": "#426b2e"
-    },
-    {
-      "id": 107,
-      "type": "AnimateDiffSampler",
-      "pos": [
-        881,
-        141
-      ],
-      "size": [
-        330,
-        350
-      ],
-      "flags": {},
-      "order": 11,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "motion_module",
-          "type": "MOTION_MODULE",
-          "link": 193
-        },
-        {
-          "name": "model",
-          "type": "MODEL",
-          "link": 194
-        },
-        {
-          "name": "positive",
-          "type": "CONDITIONING",
-          "link": 195
-        },
-        {
-          "name": "negative",
-          "type": "CONDITIONING",
-          "link": 196
-        },
-        {
-          "name": "latent_image",
-          "type": "LATENT",
-          "link": 197
-        },
-        {
-          "name": "sliding_window_opts",
-          "type": "SLIDING_WINDOW_OPTS",
-          "link": null
-        },
-        {
-          "name": "frame_number",
-          "type": "INT",
-          "link": 198,
-          "widget": {
-            "name": "frame_number",
-            "config": [
-              "INT",
-              {
-                "default": 16,
-                "min": 2,
-                "max": 10000,
-                "step": 1
-              }
-            ]
-          }
-        }
-      ],
-      "outputs": [
-        {
-          "name": "LATENT",
-          "type": "LATENT",
-          "links": [
-            199
-          ],
-          "shape": 3,
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "AnimateDiffSampler"
-      },
-      "widgets_values": [
-        "default",
-        16,
-        0,
-        "randomize",
-        20,
-        8,
-        "euler",
-        "normal",
-        1
-      ]
    }
  ],
  "links": [
@@ -749,6 +749,38 @@
      1,
      "CONDITIONING"
    ],
+    [
+      78,
+      16,
+      0,
+      41,
+      0,
+      "MOTION_MODULE"
+    ],
+    [
+      79,
+      4,
+      0,
+      41,
+      1,
+      "MODEL"
+    ],
+    [
+      80,
+      20,
+      0,
+      41,
+      4,
+      "LATENT"
+    ],
+    [
+      81,
+      41,
+      0,
+      44,
+      0,
+      "LATENT"
+    ],
    [
      82,
      13,
@@ -765,6 +797,22 @@
      0,
      "IMAGE"
    ],
+    [
+      176,
+      39,
+      0,
+      41,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      180,
+      39,
+      1,
+      41,
+      3,
+      "CONDITIONING"
+    ],
    [
      181,
      103,
@@ -781,6 +829,14 @@
      0,
      "IMAGE"
    ],
+    [
+      185,
+      104,
+      2,
+      41,
+      5,
+      "INT"
+    ],
    [
      186,
      103,
@@ -798,76 +854,20 @@
      "IMAGE"
    ],
    [
-      190,
+      188,
      104,
      0,
      20,
-      0,
-      "INT"
-    ],
-    [
-      191,
-      104,
-      1,
-      20,
      1,
      "INT"
    ],
    [
-      193,
-      16,
-      0,
-      107,
-      0,
-      "MOTION_MODULE"
-    ],
-    [
-      194,
-      4,
-      0,
-      107,
+      189,
+      104,
      1,
-      "MODEL"
-    ],
-    [
-      195,
-      39,
-      0,
-      107,
-      2,
-      "CONDITIONING"
-    ],
-    [
-      196,
-      39,
-      1,
-      107,
-      3,
-      "CONDITIONING"
-    ],
-    [
-      197,
      20,
      0,
-      107,
-      4,
-      "LATENT"
-    ],
-    [
-      198,
-      104,
-      2,
-      107,
-      6,
      "INT"
-    ],
-    [
-      199,
-      107,
-      0,
-      44,
-      0,
-      "LATENT"
    ]
  ],
  "groups": [],
@@ -195,10 +195,10 @@
        571,
        712
      ],
-      "size": {
-        "0": 275.35137939453125,
-        "1": 82
-      },
+      "size": [
+        275.35137939453125,
+        82
+      ],
      "flags": {},
      "order": 11,
      "mode": 0,
@@ -315,7 +315,7 @@
      ],
      "size": {
        "0": 315,
-        "1": 350
+        "1": 330
      },
      "flags": {},
      "order": 12,
@@ -347,11 +347,6 @@
          "name": "latent_image",
          "type": "LATENT",
          "link": 47
-        },
-        {
-          "name": "sliding_window_opts",
-          "type": "SLIDING_WINDOW_OPTS",
-          "link": null
        }
      ],
      "outputs": [
@@ -429,7 +424,7 @@
      ],
      "size": {
        "0": 315,
-        "1": 350
+        "1": 330
      },
      "flags": {},
      "order": 6,
@@ -461,11 +456,6 @@
          "name": "latent_image",
          "type": "LATENT",
          "link": 35
-        },
-        {
-          "name": "sliding_window_opts",
-          "type": "SLIDING_WINDOW_OPTS",
-          "link": null
        }
      ],
      "outputs": [
@@ -528,6 +518,48 @@
        "klF8Anime2.ckpt"
      ]
    },
+    {
+      "id": 12,
+      "type": "AnimateDiffCombine",
+      "pos": [
+        1504,
+        481
+      ],
+      "size": [
+        325.7265625,
+        517.7265625
+      ],
+      "flags": {},
+      "order": 14,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 19
+        }
+      ],
+      "outputs": [
+        {
+          "name": "GIF",
+          "type": "GIF",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AnimateDiffCombine"
+      },
+      "widgets_values": [
+        8,
+        0,
+        true,
+        "AnimateDiff",
+        "image/webp",
+        false,
+        "/view?filename=AnimateDiff_00033_.webp&subfolder=&type=output&format=image%2Fwebp"
+      ]
+    },
    {
      "id": 27,
      "type": "VAEDecode",
@@ -572,13 +604,13 @@
      "id": 28,
      "type": "AnimateDiffCombine",
      "pos": [
-        1505,
-        -72
+        1506,
+        -60
+      ],
+      "size": [
+        321.19170831298857,
+        513.0408935546875
      ],
-      "size": {
-        "0": 321.19171142578125,
-        "1": 513.0408935546875
-      },
      "flags": {},
      "order": 10,
      "mode": 0,
@@ -605,49 +637,9 @@
        0,
        true,
        "AnimateDiff",
-        "image/gif",
-        false
-      ]
-    },
-    {
-      "id": 12,
-      "type": "AnimateDiffCombine",
-      "pos": [
-        1504,
-        481
-      ],
-      "size": {
-        "0": 325.7265625,
-        "1": 517.7265625
-      },
-      "flags": {},
-      "order": 14,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "images",
-          "type": "IMAGE",
-          "link": 19
-        }
-      ],
-      "outputs": [
-        {
-          "name": "GIF",
-          "type": "GIF",
-          "links": null,
-          "shape": 3
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "AnimateDiffCombine"
-      },
-      "widgets_values": [
-        8,
-        0,
-        true,
-        "AnimateDiff",
-        "image/gif",
-        false
+        "image/webp",
+        false,
+        "/view?filename=AnimateDiff_00032_.webp&subfolder=&type=output&format=image%2Fwebp"
      ]
    }
  ],
@@ -1,515 +0,0 @@
-{
-  "last_node_id": 21,
-  "last_link_id": 38,
-  "nodes": [
-    {
-      "id": 6,
-      "type": "CLIPTextEncode",
-      "pos": [
-        415,
-        186
-      ],
-      "size": {
-        "0": 422.84503173828125,
-        "1": 164.31304931640625
-      },
-      "flags": {},
-      "order": 4,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "clip",
-          "type": "CLIP",
-          "link": 3
-        }
-      ],
-      "outputs": [
-        {
-          "name": "CONDITIONING",
-          "type": "CONDITIONING",
-          "links": [
-            29
-          ],
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "CLIPTextEncode"
-      },
-      "widgets_values": [
-        "photo of coastline, rocks, storm weather, wind, waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3"
-      ]
-    },
-    {
-      "id": 8,
-      "type": "VAEDecode",
-      "pos": [
-        1253,
-        191
-      ],
-      "size": {
-        "0": 210,
-        "1": 46
-      },
-      "flags": {},
-      "order": 8,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "samples",
-          "type": "LATENT",
-          "link": 28
-        },
-        {
-          "name": "vae",
-          "type": "VAE",
-          "link": 20
-        }
-      ],
-      "outputs": [
-        {
-          "name": "IMAGE",
-          "type": "IMAGE",
-          "links": [
-            19
-          ],
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "VAEDecode"
-      }
-    },
-    {
-      "id": 12,
-      "type": "AnimateDiffCombine",
-      "pos": [
-        1254,
-        290
-      ],
-      "size": [
-        315,
-        507
-      ],
-      "flags": {},
-      "order": 9,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "images",
-          "type": "IMAGE",
-          "link": 19
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "AnimateDiffCombine"
-      },
-      "widgets_values": [
-        8,
-        0,
-        false,
-        "AnimateDiff",
-        "image/gif",
-        false,
-        "/view?filename=AnimateDiff_00003_.gif&subfolder=&type=temp&format=image%2Fgif"
-      ]
-    },
-    {
-      "id": 7,
-      "type": "CLIPTextEncode",
-      "pos": [
-        413,
-        389
-      ],
-      "size": {
-        "0": 425.27801513671875,
-        "1": 180.6060791015625
-      },
-      "flags": {},
-      "order": 5,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "clip",
-          "type": "CLIP",
-          "link": 5
-        }
-      ],
-      "outputs": [
-        {
-          "name": "CONDITIONING",
-          "type": "CONDITIONING",
-          "links": [
-            30
-          ],
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "CLIPTextEncode"
-      },
-      "widgets_values": [
-        "blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation"
-      ]
-    },
-    {
-      "id": 20,
-      "type": "EmptyLatentImage",
-      "pos": [
-        522,
-        621
-      ],
-      "size": {
-        "0": 315,
-        "1": 106
-      },
-      "flags": {},
-      "order": 0,
-      "mode": 0,
-      "outputs": [
-        {
-          "name": "LATENT",
-          "type": "LATENT",
-          "links": [
-            35
-          ],
-          "shape": 3,
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "EmptyLatentImage"
-      },
-      "widgets_values": [
-        512,
-        512,
-        1
-      ]
-    },
-    {
-      "id": 13,
-      "type": "VAELoader",
-      "pos": [
-        28,
-        223
-      ],
-      "size": {
-        "0": 315,
-        "1": 58
-      },
-      "flags": {},
-      "order": 1,
-      "mode": 0,
-      "outputs": [
-        {
-          "name": "VAE",
-          "type": "VAE",
-          "links": [
-            20
-          ],
-          "shape": 3,
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "VAELoader"
-      },
-      "widgets_values": [
-        "vae-ft-mse-840000-ema-pruned.safetensors"
-      ]
-    },
-    {
-      "id": 15,
-      "type": "AnimateDiffSampler",
-      "pos": [
-        882,
-        192
-      ],
-      "size": {
-        "0": 315,
-        "1": 350
-      },
-      "flags": {},
-      "order": 7,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "motion_module",
-          "type": "MOTION_MODULE",
-          "link": 24,
-          "slot_index": 0
-        },
-        {
-          "name": "model",
-          "type": "MODEL",
-          "link": 25,
-          "slot_index": 1
-        },
-        {
-          "name": "positive",
-          "type": "CONDITIONING",
-          "link": 29
-        },
-        {
-          "name": "negative",
-          "type": "CONDITIONING",
-          "link": 30
-        },
-        {
-          "name": "latent_image",
-          "type": "LATENT",
-          "link": 35
-        },
-        {
-          "name": "sliding_window_opts",
-          "type": "SLIDING_WINDOW_OPTS",
-          "link": null
-        }
-      ],
-      "outputs": [
-        {
-          "name": "LATENT",
-          "type": "LATENT",
-          "links": [
-            28
-          ],
-          "shape": 3,
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "AnimateDiffSampler"
-      },
-      "widgets_values": [
-        "default",
-        14,
-        45987230,
-        "fixed",
-        25,
-        7.5,
-        "ddim",
-        "ddim_uniform",
-        1
-      ]
-    },
-    {
-      "id": 16,
-      "type": "AnimateDiffModuleLoader",
-      "pos": [
-        27,
-        345
-      ],
-      "size": {
-        "0": 315,
-        "1": 58
-      },
-      "flags": {},
-      "order": 6,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "lora_stack",
-          "type": "MOTION_LORA_STACK",
-          "link": 38,
-          "slot_index": 0
-        }
-      ],
-      "outputs": [
-        {
-          "name": "MOTION_MODULE",
-          "type": "MOTION_MODULE",
-          "links": [
-            24
-          ],
-          "shape": 3
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "AnimateDiffModuleLoader"
-      },
-      "widgets_values": [
-        "mm_sd_v15_v2.ckpt"
-      ]
-    },
-    {
-      "id": 21,
-      "type": "AnimateDiffLoraLoader",
-      "pos": [
-        -317,
-        350
-      ],
-      "size": [
-        310,
-        80
-      ],
-      "flags": {},
-      "order": 3,
-      "mode": 0,
-      "inputs": [
-        {
-          "name": "lora_stack",
-          "type": "MOTION_LORA_STACK",
-          "link": null
-        }
-      ],
-      "outputs": [
-        {
-          "name": "MOTION_LORA_STACK",
-          "type": "MOTION_LORA_STACK",
-          "links": [
-            38
-          ],
-          "shape": 3,
-          "slot_index": 0
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "AnimateDiffLoraLoader"
-      },
-      "widgets_values": [
-        "v2_lora_ZoomIn.ckpt",
-        1
-      ]
-    },
-    {
-      "id": 4,
-      "type": "CheckpointLoaderSimple",
-      "pos": [
-        28,
-        457
-      ],
-      "size": {
-        "0": 315,
-        "1": 98
-      },
-      "flags": {},
-      "order": 2,
-      "mode": 0,
-      "outputs": [
-        {
-          "name": "MODEL",
-          "type": "MODEL",
-          "links": [
-            25
-          ],
-          "slot_index": 0
-        },
-        {
-          "name": "CLIP",
-          "type": "CLIP",
-          "links": [
-            3,
-            5
-          ],
-          "slot_index": 1
-        },
-        {
-          "name": "VAE",
-          "type": "VAE",
-          "links": [],
-          "slot_index": 2
-        }
-      ],
-      "properties": {
-        "Node name for S&R": "CheckpointLoaderSimple"
-      },
-      "widgets_values": [
-        "RealisticVision_v20.safetensors"
-      ]
-    }
-  ],
-  "links": [
-    [
-      3,
-      4,
-      1,
-      6,
-      0,
-      "CLIP"
-    ],
-    [
-      5,
-      4,
-      1,
-      7,
-      0,
-      "CLIP"
-    ],
-    [
-      19,
-      8,
-      0,
-      12,
-      0,
-      "IMAGE"
-    ],
-    [
-      20,
-      13,
-      0,
-      8,
-      1,
-      "VAE"
-    ],
-    [
-      24,
-      16,
-      0,
-      15,
-      0,
-      "MOTION_MODULE"
-    ],
-    [
-      25,
-      4,
-      0,
-      15,
-      1,
-      "MODEL"
-    ],
-    [
-      28,
-      15,
-      0,
-      8,
-      0,
-      "LATENT"
-    ],
-    [
-      29,
-      6,
-      0,
-      15,
-      2,
-      "CONDITIONING"
-    ],
-    [
-      30,
-      7,
-      0,
-      15,
-      3,
-      "CONDITIONING"
-    ],
-    [
-      35,
-      20,
-      0,
-      15,
-      4,
-      "LATENT"
-    ],
-    [
-      38,
-      21,
-      0,
-      16,
-      0,
-      "MOTION_LORA_STACK"
-    ]
-  ],
-  "groups": [],
-  "config": {},
-  "extra": {},
-  "version": 0.4
-}
Author	SHA1	Message	Date
Tung Nguyen	14d40b1d57	update README & add sliding window example workling	2023-09-21 05:38:33 +07:00
Tung Nguyen	192f2c3cb3	fix wrong step count	2023-09-21 04:38:10 +07:00
Tung Nguyen	62f4d6e441	remove video_formats from comfy folder_paths	2023-09-21 03:07:08 +07:00
Tung Nguyen	09ffef9e0f	move all injections code to sampling time	2023-09-21 03:01:04 +07:00
Tung Nguyen	d9702d937b	fix ctx.video_length, update progressbar status	2023-09-21 02:25:48 +07:00
Tung Nguyen	7307f4ea40	sliding window initial code	2023-09-20 22:44:03 +07:00