fix: compatible with 3.9 python syntax

Fixed code to avoid conflict with other nodes. This code will be executed only inside the AnimateDiffCombine node now.

LICENSE

@@ -0,0 +1,201 @@
+                                 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.

README.md

@@ -5,73 +5,233 @@
 ## How to Use
 
 1. Clone this repo into `custom_nodes` folder.
-2. Download motion modules from [Google Drive](https://drive.google.com/drive/folders/1EqLC65eR1-W-sGD0Im7fkED6c8GkiNFI) | [HuggingFace](https://huggingface.co/guoyww/animatediff) | [CivitAI](https://civitai.com/models/108836) | [Baidu NetDisk](https://pan.baidu.com/s/18ZpcSM6poBqxWNHtnyMcxg?pwd=et8y). You only need to download one of `mm_sd_v14.ckpt` | `mm_sd_v15.ckpt`. Put the model weights under `comfyui-animatediff/models/`. DO NOT change model filename.
+2. Download motion modules and put them under `comfyui-animatediff/models/`.
 
-#### Update 2023/09/15
+- Original modules: [Google Drive](https://drive.google.com/drive/folders/1EqLC65eR1-W-sGD0Im7fkED6c8GkiNFI) | [HuggingFace](https://huggingface.co/guoyww/animatediff) | [CivitAI](https://civitai.com/models/108836) | [Baidu NetDisk](https://pan.baidu.com/s/18ZpcSM6poBqxWNHtnyMcxg?pwd=et8y)
+- 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)
 
-- You can now use community models from [manshoety/AD_Stabilized_Motion](https://huggingface.co/manshoety/AD_Stabilized_Motion) or [CiaraRowles/TemporalDiff](https://huggingface.co/CiaraRowles/TemporalDiff)
+## Update 2023/09/25
-- Supports AnimateDiff v2 [mm_sd_v15_v2.ckpt](https://huggingface.co/guoyww/animatediff/blob/main/mm_sd_v15_v2.ckpt) model
-- Fix image is grayed out.
-- New node: **AnimateDiffSampler** and **AnimateDiffLoader**
-  - Mostly the same with `KSampler`
-  - Use `AnimateDiffLoader` to load the motion module
-  - `inject_method`: should left default. See [this issue](https://github.com/ArtVentureX/comfyui-animatediff#gif-has-wartermark-after-update-to-the-latest-version) for more details.
-  - `frame_number`: animation length
 
-<img width="506" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/f22d6b36-ce36-44cc-80e8-dffe6f77b296">
+#### **Motion LoRA** is now supported!
 
-#### Example Workflow
+Download [motion LoRAs](https://huggingface.co/guoyww/animatediff/tree/main) and put them under `comfyui-animatediff/loras/` folder.
 
-<img width="1311" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/b7164539-bc58-4ef9-b178-d914e833805e">
+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`
 
-Workflow file: https://github.com/ArtVentureX/comfyui-animatediff/blob/main/workflow.json
+<img width="370" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/7a9f62f7-702e-48a4-934c-bbfe1e23aff2">
 
-## Samples
+Example workflow:
+<img width="1280" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/93e7550f-4648-4482-9961-6cece5132dc9">
 
-![23b44c29-29e8-4f48-ab3c-4df87c90c13f](https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/97efb96f-3d3d-4976-8789-78b88f89b2eb)
+Workflow: [lora.json](https://github.com/ArtVentureX/comfyui-animatediff/blob/main/workflows/lora.json)
 
-![25f6c60c-f8ac-4abe-984f-1559c355d7f6](https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/c39b26f7-a2af-4dc4-902f-c363e2e6f39a)
+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.
+
+## Nodes
+
+#### AnimateDiffLoader
+
+<img width="370" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/9d756d01-ea45-4d1c-8e48-56f2725c7ca1">
+
+#### AnimateDiffSampler
+
+- Mostly the same with `KSampler`
+- `motion_module`: use `AnimateDiffLoader` to load the motion module
+- `inject_method`: should left default
+- `frame_number`: animation length
+- `latent_image`: You can pass an `EmptyLatentImage`
+- `sliding_window_opts`: custom sliding window options
+
+<img width="370" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/a352195d-f40c-494d-bd3d-30ee88174b88">
+
+#### AnimateDiffCombine
+
+- Combine GIF frames and produce the GIF image
+- `frame_rate`: number of frame per second
+- `loop_count`: use 0 for infinite loop
+- `save_image`: should GIF be saved to disk
+- `format`: supports `image/gif`, `image/webp` (better compression), `video/webm`, `video/h264-mp4`, `video/h265-mp4`. To use video formats, you'll need [ffmpeg](https://ffmpeg.org/download.html) installed and available in **`PATH`**
+
+<img width="370" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/381c5acc-06ef-43da-ada0-3dc76f37a3e4">
+
+#### SlidingWindowOptions
+
+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
+
+<img width="370" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/6679a8dd-bf96-419f-8934-ea2b046dd23c">
+
+#### LoadVideo
+
+Load GIF or video as images. Usefull to load a GIF as ControlNet input.
+
+- `frame_start`: Skip some begining frames and start at `frame_start`
+- `frame_limit`: Only take `frame_limit` frames
+
+<img width="370" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/684176d5-6369-4a27-9f33-e721e0fe1876">
+
+## Workflows
+
+### Simple txt2gif
+
+<img width="1280" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/b7164539-bc58-4ef9-b178-d914e833805e">
+
+Workflow: [simple.json](https://github.com/ArtVentureX/comfyui-animatediff/blob/main/workflows/simple.json)
+
+Samples:
+
+![animate_diff_01](https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/97efb96f-3d3d-4976-8789-78b88f89b2eb)
+
+![animate_diff_02](https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/c39b26f7-a2af-4dc4-902f-c363e2e6f39a)
+
+### Long duration with sliding window
+
+<img width="1280" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/0f8bfb87-83cb-4119-9777-e3948ec0cb5c">
+
+Workflow: [sliding-window.json](https://github.com/ArtVentureX/comfyui-animatediff/blob/main/workflows/sliding-window.json)
+
+Samples:
+
+<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>
+
+### Latent upscale
+
+Upscale latent output using `LatentUpscale` then do a 2nd pass with `AnimateDiffSampler`.
+
+<img width="1280" alt="image" src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/987a1c5a-c1f8-4b24-8c62-f14496261d6c">
+
+Workflow: [latent-upscale.json](https://github.com/ArtVentureX/comfyui-animatediff/blob/main/workflows/latent-upscale.json)
+
+Samples:
+![animate_diff_upscale](https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/f363f6f8-3117-4fa8-bca9-62f6a6e38ce7)
+
+### Using with ControlNet
+
+You will need following additional nodes:
+
+- [Kosinkadink/ComfyUI-Advanced-ControlNet](https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet): Apply different weight for each latent in batch
+- [Fannovel16/comfyui_controlnet_aux](https://github.com/Fannovel16/comfyui_controlnet_aux): ControlNet preprocessors
+
+#### Animate with starting and ending images
+
+- Use `LatentKeyframe` and `TimestampKeyframe` from [ComfyUI-Advanced-ControlNet](https://github.com/Kosinkadink/ComfyUI-Advanced-ControlNet) to apply diffrent weights for each latent index.
+- Use 2 controlnet modules for two images with weights reverted.
+
+![image](https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/bcca1070-e4a1-4698-a2af-aadf9723d015)
+
+Workflow: [cn-2images.json](https://github.com/ArtVentureX/comfyui-animatediff/blob/main/workflows/cn-2images.json)
+
+Samples:
+
+<table>
+<tr>
+<td>
+<img src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/e73fc3cd-a590-40a9-8b33-11358b54f0cd">
+</td>
+<td>
+<img src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/96c2ee92-d457-4862-94d3-d675b7fa2d1f">
+</td>
+</tr>
+<tr>
+<td>
+<img src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/46338853-1ae0-433e-925c-2a41e0382e68">
+</td>
+<td>
+<img src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/707e4ce3-3594-4ff5-9a5f-f9596eb2bcf4">
+</td>
+</tr>
+</table>
+
+#### Using GIF as ControlNet input
+
+Using a GIF (or video, or a list of images) as ControlNet input.
+
+![image](https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/cfeed634-e683-4797-b2fd-dbe0926a449e)
+
+Workflow: [cn-vid2vid.json](https://github.com/ArtVentureX/comfyui-animatediff/blob/main/workflows/cn-vid2vid.json)
+
+Samples:
+
+<table>
+<tr>
+<td>
+<img src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/bf926f52-da97-4fb4-b86a-8b26ef5fab04">
+</td>
+<td>
+<img src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/f6472c8c-9b92-47c2-8f28-638726f21be7">
+</td>
+</tr>
+</table>
 
 ## 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)
 
-See: https://github.com/continue-revolution/sd-webui-animatediff/issues/38
-
-Main reasons:
-
-- Promt are too long (more than 75 tokens)
-- Resolution are too high
-- Number of frame too high
-
 Work around:
 
 - Shorter your prompt and negative prompt
 - Reduce resolution. AnimateDiff is trained on 512x512 images so it works best with 512x512 output.
-- Shouldn't generate longer than 16 frames. AnimateDiff is trained to output the best results with 16 frames.
+- Disable xformers with `--disable-xformers`
 
-### GIF has Wartermark after update to the latest version
+### GIF has Wartermark (especially when using mm_sd_v15)
 
 See: https://github.com/continue-revolution/sd-webui-animatediff/issues/31
 
-As mentioned in the issue thread, it seems to be due to the training dataset. The new version is the correct implementation and produces smoother GIFs compared to the older version.
+Training data used by the authors of the AnimateDiff paper contained Shutterstock watermarks. Since mm_sd_v15 was finetuned on finer, less drastic movement, the motion module attempts to replicate the transparency of that watermark and does not get blurred away like mm_sd_v14. Try other community finetuned modules.
-
-<table  class="center">
-    <tr>
-    <td>Old revision</td>
-    <td>New revision</td>
-    </tr>
-    <tr>
-    <td><img src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/8f1a6233-875f-4f0c-aa60-ba93e73b7d64" /></td>
-    <td><img src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/a2029eba-f519-437c-a0b5-1f881e099a20" /></td>
-    </tr>
-    <tr>
-    <td><img src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/41ec449f-1955-466c-bd38-6f2a55d654f8" /></td>
-    <td><img src="https://github.com/ArtVentureX/comfyui-animatediff/assets/133728487/766c2891-5d27-4052-99f9-be9862620919" /></td>
-    </tr>
-</table>
-
-I played around with both version and found that the watermark only present in some models, not always. To use the **old (legacy)** method, change `injection_method` to `legacy` in the `AnimateDiffSampler` node.

__init__.py

@@ -5,4 +5,6 @@ from .animatediff.model_utils import get_available_models
 if len(get_available_models()) == 0:
     logger.error("No models available. Please download one and put it in models folder")
 
-__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS"]
+WEB_DIRECTORY = "./web"
+
+__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS", "WEB_DIRECTORY"]

animatediff/model_utils.py

@@ -1,7 +1,18 @@
 import os
 import hashlib
+import torch
+from typing import Dict
 
 import folder_paths
+import comfy.model_management as model_management
+from comfy.utils import load_torch_file, calculate_parameters
+
+from .logger import logger
+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"] = (
@@ -11,17 +22,79 @@ 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()  # read entire file as bytes
+        bytes = f.read(1024 * 1024)  # read entire file as bytes
         return hashlib.sha256(bytes).hexdigest()
+
+
+def load_motion_module(model_name: str):
+    model_path = get_model_path(model_name)
+    model_hash = get_model_hash(model_path)
+    if model_hash not in motion_modules:
+        logger.info(f"Loading motion module {model_name}")
+        mm_state_dict = load_torch_file(model_path)
+        motion_module = MotionWrapper.from_state_dict(mm_state_dict, model_name)
+
+        params = calculate_parameters(mm_state_dict, "")
+        if model_management.should_use_fp16(model_params=params):
+            logger.info(f"Converting motion module to fp16.")
+            motion_module.half()
+        offload_device = model_management.unet_offload_device()
+        motion_module = motion_module.to(offload_device)
+
+        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]

animatediff/motion_module.py

@@ -1,12 +1,35 @@
-import os
 import torch
 from torch import Tensor, nn
 
 import math
 from einops import rearrange, repeat
 
-from comfy.utils import load_torch_file
+import comfy.model_management as model_management
-from comfy.ldm.modules.attention import FeedForward, CrossAttention
+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
 
 
 def zero_module(module):
@@ -33,6 +56,24 @@ 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__()
@@ -42,29 +83,22 @@ class MotionWrapper(nn.Module):
         self.down_blocks = nn.ModuleList([])
         self.up_blocks = nn.ModuleList([])
         self.mid_block = None
+        self.encoding_max_len = encoding_max_len
 
         for c in (320, 640, 1280, 1280):
-            self.down_blocks.append(
+            self.down_blocks.append(MotionModule(c, BlockType.DOWN, encoding_max_len=encoding_max_len))
-                MotionModule(c, BlockType.DOWN, encoding_max_len=encoding_max_len)
-            )
         for c in (1280, 1280, 640, 320):
-            self.up_blocks.append(
+            self.up_blocks.append(MotionModule(c, BlockType.UP, encoding_max_len=encoding_max_len))
-                MotionModule(c, BlockType.UP, encoding_max_len=encoding_max_len)
-            )
         if is_v2:
-            self.mid_block = MotionModule(
+            self.mid_block = MotionModule(1280, BlockType.MID, encoding_max_len=encoding_max_len)
-                1280, BlockType.MID, encoding_max_len=encoding_max_len
-            )
 
     @classmethod
-    def from_pretrained(cls, checkpoint_path: str):
+    def from_state_dict(cls, mm_state_dict: dict[str, Tensor], mm_type: str):
-        mm_state_dict = load_torch_file(checkpoint_path)
-        mm_type = os.path.basename(checkpoint_path)
         encoding_max_len = get_encoding_max_len(mm_state_dict)
         is_v2 = has_mid_block(mm_state_dict)
 
         mm = cls(mm_type, encoding_max_len=encoding_max_len, is_v2=is_v2)
-        mm.load_state_dict(mm_state_dict)
+        mm.load_state_dict(mm_state_dict, strict=False)
         return mm
 
     def set_video_length(self, video_length: int):
@@ -93,9 +127,7 @@ class MotionModule(nn.Module):
         self.block_type = block_type
 
         if block_type == BlockType.MID:
-            self.motion_modules = nn.ModuleList(
+            self.motion_modules = nn.ModuleList([get_motion_module(in_channels, encoding_max_len)])
-                [get_motion_module(in_channels, encoding_max_len)]
-            )
         else:
             self.motion_modules = nn.ModuleList(
                 [
@@ -104,9 +136,7 @@ class MotionModule(nn.Module):
                 ]
             )
             if block_type == BlockType.UP:
-                self.motion_modules.append(
+                self.motion_modules.append(get_motion_module(in_channels, encoding_max_len))
-                    get_motion_module(in_channels, encoding_max_len)
-                )
 
     def set_video_length(self, video_length: int):
         for motion_module in self.motion_modules:
@@ -114,9 +144,7 @@ class MotionModule(nn.Module):
 
 
 def get_motion_module(in_channels, max_len):
-    return VanillaTemporalModule(
+    return VanillaTemporalModule(in_channels=in_channels, temporal_position_encoding_max_len=max_len)
-        in_channels=in_channels, temporal_position_encoding_max_len=max_len
-    )
 
 
 class VanillaTemporalModule(nn.Module):
@@ -137,9 +165,7 @@ class VanillaTemporalModule(nn.Module):
         self.temporal_transformer = TemporalTransformer3DModel(
             in_channels=in_channels,
             num_attention_heads=num_attention_heads,
-            attention_head_dim=in_channels
+            attention_head_dim=in_channels // num_attention_heads // temporal_attention_dim_div,
-            // 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,
@@ -148,17 +174,13 @@ class VanillaTemporalModule(nn.Module):
         )
 
         if zero_initialize:
-            self.temporal_transformer.proj_out = zero_module(
+            self.temporal_transformer.proj_out = zero_module(self.temporal_transformer.proj_out)
-                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, attention_mask=None):
+    def forward(self, input_tensor, encoder_hidden_states=None, attention_mask=None):
-        return self.temporal_transformer(
+        return self.temporal_transformer(input_tensor, encoder_hidden_states, attention_mask)
-            input_tensor, encoder_hidden_states, attention_mask
-        )
 
 
 class TemporalTransformer3DModel(nn.Module):
@@ -186,9 +208,7 @@ class TemporalTransformer3DModel(nn.Module):
 
         inner_dim = num_attention_heads * attention_head_dim
 
-        self.norm = torch.nn.GroupNorm(
+        self.norm = torch.nn.GroupNorm(num_groups=norm_num_groups, num_channels=in_channels, eps=1e-6, affine=True)
-            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(
@@ -223,9 +243,7 @@ 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(
+        hidden_states = hidden_states.permute(0, 2, 3, 1).reshape(batch, height * weight, inner_dim)
-            batch, height * weight, inner_dim
-        )
         hidden_states = self.proj_in(hidden_states)
 
         # Transformer Blocks
@@ -238,11 +256,7 @@ class TemporalTransformer3DModel(nn.Module):
 
         # output
         hidden_states = self.proj_out(hidden_states)
-        hidden_states = (
+        hidden_states = hidden_states.reshape(batch, height, weight, inner_dim).permute(0, 3, 1, 2).contiguous()
-            hidden_states.reshape(batch, height, weight, inner_dim)
-            .permute(0, 3, 1, 2)
-            .contiguous()
-        )
 
         output = hidden_states + residual
 
@@ -278,9 +292,7 @@ class TemporalTransformerBlock(nn.Module):
             attention_blocks.append(
                 VersatileAttention(
                     attention_mode=block_name.split("_")[0],
-                    context_dim=cross_attention_dim
+                    context_dim=cross_attention_dim if block_name.endswith("_Cross") else None,
-                    if block_name.endswith("_Cross")
-                    else None,
                     query_dim=dim,
                     heads=num_attention_heads,
                     dim_head=attention_head_dim,
@@ -312,9 +324,7 @@ class TemporalTransformerBlock(nn.Module):
             hidden_states = (
                 attention_block(
                     norm_hidden_states,
-                    encoder_hidden_states=encoder_hidden_states
+                    encoder_hidden_states=encoder_hidden_states if attention_block.is_cross_attention else None,
-                    if attention_block.is_cross_attention
-                    else None,
                     video_length=video_length,
                 )
                 + hidden_states
@@ -331,9 +341,7 @@ class PositionalEncoding(nn.Module):
         super().__init__()
         self.dropout = nn.Dropout(p=dropout)
         position = torch.arange(max_len).unsqueeze(1)
-        div_term = torch.exp(
+        div_term = torch.exp(torch.arange(0, d_model, 2) * (-math.log(10000.0) / d_model))
-            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)
@@ -385,9 +393,7 @@ class VersatileAttention(CrossAttention):
             raise NotImplementedError
 
         d = hidden_states.shape[1]
-        hidden_states = rearrange(
+        hidden_states = rearrange(hidden_states, "(b f) d c -> (b d) f c", f=video_length)
-            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)

animatediff/nodes.py

@@ -2,168 +2,25 @@ import os
 import json
 import torch
 import numpy as np
-from typing import Dict, List
+import hashlib
+from typing import List, Dict, Tuple
 from torch import Tensor
-from torch.nn.functional import group_norm
+from PIL import Image, ImageSequence
-from PIL import Image
 from PIL.PngImagePlugin import PngInfo
-from einops import rearrange
 
 import folder_paths
-import comfy.ldm.modules.diffusionmodules.openaimodel as openaimodel
-import comfy.model_management as model_management
-from comfy.model_base import BaseModel
-from comfy.ldm.modules.attention import SpatialTransformer
-from comfy.cli_args import args as cli_args
-from nodes import KSampler
 
+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 .sampler import AnimateDiffSampler, AnimateDiffSlidingWindowOptions
 from .logger import logger
-from .motion_module import MotionWrapper, VanillaTemporalModule
-from .model_utils import get_available_models, get_model_path, get_model_hash
 
 
-def forward_timestep_embed(
+SLIDING_CONTEXT_LENGTH = 16
-    ts, x, emb, context=None, transformer_options={}, output_shape=None
-):
-    for layer in ts:
-        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 = layer(x)
-    return x
 
-
+video_formats_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "..", "video_formats")
-def groupnorm_mm_factory(video_length: int):
+video_formats = ["video/" + x[:-5] for x in os.listdir(video_formats_dir)]
-    def groupnorm_mm_forward(self, input: Tensor) -> Tensor:
-        # axes_factor normalizes batch based on total conds and unconds passed in batch;
-        # the conds and unconds per batch can change based on VRAM optimizations that may kick in
-        axes_factor = input.size(0) // video_length
-
-        input = rearrange(input, "(b f) c h w -> b c f h w", b=axes_factor)
-        input = group_norm(input, self.num_groups, self.weight, self.bias, self.eps)
-        input = rearrange(input, "b c f h w -> (b f) c h w", b=axes_factor)
-        return input
-
-    return groupnorm_mm_forward
-
-
-orig_forward_timestep_embed = openaimodel.forward_timestep_embed
-orig_maximum_batch_area = model_management.maximum_batch_area
-orig_groupnorm_forward = torch.nn.GroupNorm.forward
-openaimodel.forward_timestep_embed = forward_timestep_embed
-
-motion_modules: Dict[str, MotionWrapper] = {}
-
-
-def load_motion_module(model_name: str):
-    model_path = get_model_path(model_name)
-    model_hash = get_model_hash(model_path)
-    if model_hash not in motion_modules:
-        logger.info(f"Loading motion module {model_name}")
-        motion_module = MotionWrapper.from_pretrained(model_path)
-        if not cli_args.force_fp32:
-            logger.info(f"Converting motion module to fp16.")
-            motion_module.half()
-
-        motion_modules[model_hash] = motion_module
-
-    return motion_modules[model_hash]
-
-
-def inject_motion_module_to_unet_legacy(unet, motion_module: MotionWrapper):
-    for mm_idx, unet_idx in enumerate([1, 2, 4, 5, 7, 8, 10, 11]):
-        mm_idx0, mm_idx1 = mm_idx // 2, mm_idx % 2
-        unet.input_blocks[unet_idx].append(
-            motion_module.down_blocks[mm_idx0].motion_modules[mm_idx1]
-        )
-
-    for unet_idx in range(12):
-        mm_idx0, mm_idx1 = unet_idx // 3, unet_idx % 3
-        if unet_idx % 2 == 2:
-            unet.output_blocks[unet_idx].insert(
-                -1, motion_module.up_blocks[mm_idx0].motion_modules[mm_idx1]
-            )
-        else:
-            unet.output_blocks[unet_idx].append(
-                motion_module.up_blocks[mm_idx0].motion_modules[mm_idx1]
-            )
-    if motion_module.is_v2:
-        unet.middle_block.insert(-1, motion_module.mid_block.motion_modules[0])
-
-    unet.motion_module = motion_module
-
-
-def eject_motion_module_from_unet_legacy(unet):
-    for unet_idx in [1, 2, 4, 5, 7, 8, 10, 11]:
-        unet.input_blocks[unet_idx].pop(-1)
-
-    for unet_idx in range(12):
-        if unet_idx % 2 == 2:
-            unet.output_blocks[unet_idx].pop(-2)
-        else:
-            unet.output_blocks[unet_idx].pop(-1)
-
-    if unet.motion_module.is_v2:
-        unet.middle_block.pop(-2)
-
-    del unet.motion_module
-
-
-def inject_motion_module_to_unet(unet, motion_module: MotionWrapper):
-    for mm_idx, unet_idx in enumerate([1, 2, 4, 5, 7, 8, 10, 11]):
-        mm_idx0, mm_idx1 = mm_idx // 2, mm_idx % 2
-        unet.input_blocks[unet_idx].append(
-            motion_module.down_blocks[mm_idx0].motion_modules[mm_idx1]
-        )
-
-    for unet_idx in range(12):
-        mm_idx0, mm_idx1 = unet_idx // 3, unet_idx % 3
-        if unet_idx % 3 == 2 and unet_idx != 11:
-            unet.output_blocks[unet_idx].insert(
-                -1, motion_module.up_blocks[mm_idx0].motion_modules[mm_idx1]
-            )
-        else:
-            unet.output_blocks[unet_idx].append(
-                motion_module.up_blocks[mm_idx0].motion_modules[mm_idx1]
-            )
-    if motion_module.is_v2:
-        unet.middle_block.insert(-1, motion_module.mid_block.motion_modules[0])
-
-    unet.motion_module = motion_module
-
-
-def eject_motion_module_from_unet(unet):
-    for unet_idx in [1, 2, 4, 5, 7, 8, 10, 11]:
-        unet.input_blocks[unet_idx].pop(-1)
-
-    for unet_idx in range(12):
-        if unet_idx % 3 == 2 and unet_idx != 11:
-            unet.output_blocks[unet_idx].pop(-2)
-        else:
-            unet.output_blocks[unet_idx].pop(-1)
-
-    if unet.motion_module.is_v2:
-        unet.middle_block.pop(-2)
-
-    del unet.motion_module
-
-
-injectors = {
-    "legacy": inject_motion_module_to_unet_legacy,
-    "default": inject_motion_module_to_unet,
-}
-
-ejectors = {
-    "legacy": eject_motion_module_from_unet_legacy,
-    "default": eject_motion_module_from_unet,
-}
 
 
 class AnimateDiffModuleLoader:
@@ -173,146 +30,97 @@ 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 AnimateDiffSampler(KSampler):
+class AnimateDiffLoraLoader:
     @classmethod
     def INPUT_TYPES(s):
-        inputs = {
+        return {
             "required": {
-                "motion_module": ("MOTION_MODULE",),
+                "lora_name": (get_available_loras(),),
-                "inject_method": (["default", "legacy"],),
+                "alpha": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.001}),
-                "frame_number": (
+            },
-                    "INT",
+            "optional": {
-                    {"default": 16, "min": 2, "max": 32, "step": 1},
+                "lora_stack": ("MOTION_LORA_STACK",),
-                ),
+            },
-            }
         }
-        inputs["required"].update(KSampler.INPUT_TYPES()["required"])
-        return inputs
 
-    FUNCTION = "animatediff_sample"
+    RETURN_TYPES = ("MOTION_LORA_STACK",)
     CATEGORY = "Animate Diff"
+    FUNCTION = "load_lora"
 
-    def __init__(self) -> None:
+    def load_lora(
-        super().__init__()
-        self.prev_beta = None
-        self.prev_linear_start = None
-        self.prev_linear_end = None
-
-    def override_beta_schedule(self, model: BaseModel):
-        logger.info(f"Override beta schedule.")
-        self.prev_beta = model.get_buffer("betas")
-        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):
-        logger.info(f"Restoring beta schedule.")
-        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()
-        unet = model.model.diffusion_model
-
-        logger.info(f"Injecting motion module with method {inject_method}.")
-        injectors[inject_method](unet, motion_module)
-        self.override_beta_schedule(model.model)
-        if not motion_module.is_v2:
-            logger.info(f"Hacking GroupNorm.forward function.")
-            torch.nn.GroupNorm.forward = groupnorm_mm_factory(frame_number)
-
-        return model
-
-    def eject_motion_module(self, model, inject_method):
-        unet = model.model.diffusion_model
-
-        self.restore_beta_schedule(model.model)
-        if not unet.motion_module.is_v2:
-            logger.info(f"Restore GroupNorm32 forward function.")
-            torch.nn.GroupNorm.forward = orig_groupnorm_forward
-
-        logger.info(f"Ejecting motion module with method {inject_method}.")
-        ejectors[inject_method](unet)
-
-    def animatediff_sample(
         self,
-        motion_module,
+        lora_name: str,
-        inject_method,
+        alpha: float,
-        frame_number,
+        lora_stack: List = None,
-        model,
-        seed,
-        steps,
-        cfg,
-        sampler_name,
-        scheduler,
-        positive,
-        negative,
-        latent_image,
-        denoise=1.0,
     ):
-        model = self.inject_motion_module(
+        if not lora_stack:
-            model, motion_module, inject_method, frame_number
+            lora_stack = []
-        )
 
-        init_frames = len(latent_image["samples"])
+        lora = load_lora(lora_name)
-        samples = latent_image["samples"][:init_frames, :, :, :].clone().cpu()
+        lora_stack.append((lora, alpha))
 
-        if init_frames < frame_number:
+        return (lora_stack,)
-            last_frame = samples[-1].unsqueeze(0)
-            repeated_last_frames = last_frame.repeat(
-                frame_number - init_frames, 1, 1, 1
-            )
-            samples = torch.cat((samples, repeated_last_frames), dim=0)
-
-        latent_image = {"samples": samples}
-
-        try:
-            return super().sample(
-                model,
-                seed,
-                steps,
-                cfg,
-                sampler_name,
-                scheduler,
-                positive,
-                negative,
-                latent_image,
-                denoise=denoise,
-            )
-        except:
-            raise
-        finally:
-            self.eject_motion_module(model, inject_method)
 
 
 class AnimateDiffCombine:
@@ -326,8 +134,10 @@ class AnimateDiffCombine:
                     {"default": 8, "min": 1, "max": 24, "step": 1},
                 ),
                 "loop_count": ("INT", {"default": 0, "min": 0, "max": 100, "step": 1}),
-                "save_image": (["Enabled", "Disabled"],),
+                "save_image": ("BOOLEAN", {"default": True}),
-                "filename_prefix": ("STRING", {"default": "AnimateDiff"}),
+                "filename_prefix": ("STRING", {"default": "animate_diff"}),
+                "format": (["image/gif", "image/webp"] + video_formats,),
+                "pingpong": ("BOOLEAN", {"default": False}),
             },
             "hidden": {
                 "prompt": "PROMPT",
@@ -345,24 +155,22 @@ class AnimateDiffCombine:
         images,
         frame_rate: int,
         loop_count: int,
-        save_image="Enabled",
+        save_image=True,
         filename_prefix="AnimateDiff",
+        format="image/gif",
+        pingpong=False,
         prompt=None,
         extra_pnginfo=None,
     ):
         # convert images to numpy
-        pil_images: List[Image.Image] = []
+        frames: List[Image.Image] = []
         for image in images:
             img = 255.0 * image.cpu().numpy()
             img = Image.fromarray(np.clip(img, 0, 255).astype(np.uint8))
-            pil_images.append(img)
+            frames.append(img)
 
         # save image
-        output_dir = (
+        output_dir = folder_paths.get_output_directory() if save_image else folder_paths.get_temp_directory()
-            folder_paths.get_output_directory()
-            if save_image == "Enabled"
-            else folder_paths.get_temp_directory()
-        )
         (
             full_output_folder,
             filename,
@@ -381,43 +189,234 @@ class AnimateDiffCombine:
         # save first frame as png to keep metadata
         file = f"{filename}_{counter:05}_.png"
         file_path = os.path.join(full_output_folder, file)
-        pil_images[0].save(
+        frames[0].save(
             file_path,
             pnginfo=metadata,
             compress_level=4,
         )
+        if pingpong:
+            frames = frames + frames[-2:0:-1]
 
-        # save gif
+        format_type, format_ext = format.split("/")
-        file = f"{filename}_{counter:05}_.gif"
-        file_path = os.path.join(full_output_folder, file)
-        pil_images[0].save(
-            file_path,
-            save_all=True,
-            append_images=pil_images[1:],
-            duration=round(1000 / frame_rate),
-            loop=loop_count,
-            compress_level=4,
-        )
 
-        print("Saved gif to", file_path, os.path.exists(file_path))
+        if format_type == "image":
+            file = f"{filename}_{counter:05}_.{format_ext}"
+            file_path = os.path.join(full_output_folder, file)
+            frames[0].save(
+                file_path,
+                format=format_ext.upper(),
+                save_all=True,
+                append_images=frames[1:],
+                duration=round(1000 / frame_rate),
+                loop=loop_count,
+                compress_level=4,
+            )
+        else:
+            # save webm
+            import shutil
+            import subprocess
+
+            ffmpeg_path = shutil.which("ffmpeg")
+            if ffmpeg_path is None:
+                raise ProcessLookupError("Could not find ffmpeg")
+            video_format_path = os.path.join(video_formats_dir, format_ext + ".json")
+            with open(video_format_path, "r") as stream:
+                video_format = json.load(stream)
+            file = f"{filename}_{counter:05}_.{video_format['extension']}"
+            file_path = os.path.join(full_output_folder, file)
+            dimensions = f"{frames[0].width}x{frames[0].height}"
+            args = (
+                [
+                    ffmpeg_path,
+                    "-v",
+                    "error",
+                    "-f",
+                    "rawvideo",
+                    "-pix_fmt",
+                    "rgb24",
+                    "-s",
+                    dimensions,
+                    "-r",
+                    str(frame_rate),
+                    "-i",
+                    "-",
+                ]
+                + video_format["main_pass"]
+                + [file_path]
+            )
+
+            env = os.environ
+            if "environment" in video_format:
+                env.update(video_format["environment"])
+            with subprocess.Popen(args, stdin=subprocess.PIPE, env=env) as proc:
+                for frame in frames:
+                    proc.stdin.write(frame.tobytes())
 
         previews = [
             {
                 "filename": file,
                 "subfolder": subfolder,
-                "type": "output" if save_image == "Enabled" else "temp",
+                "type": "output" if save_image else "temp",
+                "format": format,
             }
         ]
-        return {"ui": {"images": previews}}
+        return {"ui": {"videos": previews}}
+
+
+class LoadVideo:
+    @classmethod
+    def INPUT_TYPES(s):
+        input_dir = os.path.join(folder_paths.get_input_directory(), "video")
+        if not os.path.exists(input_dir):
+            os.makedirs(input_dir, exist_ok=True)
+
+        files = [f"video/{f}" for f in os.listdir(input_dir) if os.path.isfile(os.path.join(input_dir, f))]
+
+        return {
+            "required": {
+                "video": (sorted(files), {"video_upload": True}),
+            },
+            "optional": {
+                "frame_start": ("INT", {"default": 0, "min": 0, "max": 0xFFFFFFFF, "step": 1}),
+                "frame_limit": ("INT", {"default": 16, "min": 1, "max": 10240, "step": 1}),
+            },
+        }
+
+    CATEGORY = "Animate Diff/Utils"
+    RETURN_TYPES = ("IMAGE", "INT")
+    RETURN_NAMES = ("frames", "frame_count")
+    FUNCTION = "load"
+
+    def load_gif(self, gif_path: str, frame_start: int, frame_limit: int):
+        image = Image.open(gif_path)
+        frames = []
+
+        for i, frame in enumerate(ImageSequence.Iterator(image)):
+            if i < frame_start:
+                continue
+            elif i >= frame_start + frame_limit:
+                break
+            else:
+                frames.append(pil2tensor(frame.copy().convert("RGB")))
+
+        return frames
+
+    def load_video(self, video_path, frame_start: int, frame_limit: int):
+        ensure_opencv()
+        import cv2
+
+        video = cv2.VideoCapture(video_path)
+        video.set(cv2.CAP_PROP_POS_FRAMES, frame_start)
+
+        frames = []
+        for i in range(frame_limit):
+            # Read the next frame
+            ret, frame = video.read()
+            if ret:
+                # Convert the frame to RGB (OpenCV uses BGR)
+                frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+                # Convert the NumPy array to a PIL image and append to list
+                frames.append(pil2tensor(Image.fromarray(frame)))
+            else:
+                break
+
+        video.release()
+
+        return frames
+
+    def load(self, video: str, frame_start=0, frame_limit=16):
+        video_path = folder_paths.get_annotated_filepath(video)
+        (_, ext) = os.path.splitext(video_path)
+
+        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"}:
+            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))
+
+    @classmethod
+    def IS_CHANGED(s, image, *args, **kwargs):
+        image_path = folder_paths.get_annotated_filepath(image)
+        m = hashlib.sha256()
+        with open(image_path, "rb") as f:
+            m.update(f.read())
+        return m.digest().hex()
+
+    @classmethod
+    def VALIDATE_INPUTS(s, video, *args, **kwargs):
+        if not folder_paths.exists_annotated_filepath(video):
+            return "Invalid video file: {}".format(video)
+
+        return True
+
+
+class ImageSizeAndBatchSize:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "image": ("IMAGE",),
+            },
+        }
+
+    CATEGORY = "Animate Diff/Utils"
+    RETURN_TYPES = ("INT", "INT", "INT")
+    RETURN_NAMES = ("width", "height", "batch_size")
+    FUNCTION = "batch_size"
+
+    def batch_size(self, image: Tensor):
+        (batch_size, height, width) = image.shape[0:3]
+        return (width, height, batch_size)
+
+
+class ImageChunking:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "images": ("IMAGE",),
+                "chunk_size": ("INT", {"default": 16, "min": 1, "max": 1024, "step": 1}),
+                "allow_remainder": ("BOOLEAN", {"default": True}),
+            },
+        }
+
+    CATEGORY = "Animate Diff/Utils"
+    RETURN_TYPES = ("IMAGE",)
+    OUTPUT_IS_LIST = (True,)
+    FUNCTION = "chunk"
+
+    def chunk(self, images: Tensor, chunk_size: int, allow_remainder: bool):
+        # Check if tensor is divisible into chunks of chunk_size
+        if images.shape[0] % chunk_size != 0 and not allow_remainder:
+            raise ValueError("Tensor's first dimension is not divisible by chunk size")
+
+        # Use torch.chunk to divide the tensor
+        chunk_count = images.shape[0] // chunk_size + images.shape[0] % chunk_size
+
+        print("chunk_count", chunk_count)
+        chunks = torch.chunk(images, chunk_count, dim=0)
+
+        return (list(chunks),)
 
 
 NODE_CLASS_MAPPINGS = {
     "AnimateDiffModuleLoader": AnimateDiffModuleLoader,
+    "AnimateDiffLoraLoader": AnimateDiffLoraLoader,
     "AnimateDiffCombine": AnimateDiffCombine,
     "AnimateDiffSampler": AnimateDiffSampler,
+    "AnimateDiffSlidingWindowOptions": AnimateDiffSlidingWindowOptions,
+    "LoadVideo": LoadVideo,
+    "ImageSizeAndBatchSize": ImageSizeAndBatchSize,
 }
 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",
+    "LoadVideo": "Load Video",
+    "ImageSizeAndBatchSize": "Get Image Size + Batch Size",
 }

animatediff/sampler.py

@@ -0,0 +1,298 @@
+import torch
+from torch import Tensor
+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
+from nodes import KSampler
+
+from .logger import logger
+from .motion_module import MotionWrapper, VanillaTemporalModule
+from .sliding_schedule import ContextSchedules
+from .sliding_context_sampling import SlidingContext, inject_sampling_function, eject_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):
+    for layer in ts:
+        if isinstance(layer, VanillaTemporalModule):
+            x = layer(x, context)
+        else:
+            x = orig_forward_timestep_embed([layer], x, emb, context, *args, **kwargs)
+
+    return x
+
+
+def groupnorm_mm_factory(video_length: int):
+    def groupnorm_mm_forward(self, input: Tensor) -> Tensor:
+        # axes_factor normalizes batch based on total conds and unconds passed in batch;
+        # the conds and unconds per batch can change based on VRAM optimizations that may kick in
+        axes_factor = input.size(0) // video_length
+
+        input = rearrange(input, "(b f) c h w -> b c f h w", b=axes_factor)
+        input = group_norm(input, self.num_groups, self.weight, self.bias, self.eps)
+        input = rearrange(input, "b c f h w -> (b f) c h w", b=axes_factor)
+        return input
+
+    return groupnorm_mm_forward
+
+
+orig_forward_timestep_embed = openaimodel.forward_timestep_embed
+orig_groupnorm_forward = torch.nn.GroupNorm.forward
+
+
+def inject_motion_module_to_unet_legacy(unet, motion_module: MotionWrapper):
+    for mm_idx, unet_idx in enumerate([1, 2, 4, 5, 7, 8, 10, 11]):
+        mm_idx0, mm_idx1 = mm_idx // 2, mm_idx % 2
+        unet.input_blocks[unet_idx].append(motion_module.down_blocks[mm_idx0].motion_modules[mm_idx1])
+
+    for unet_idx in range(12):
+        mm_idx0, mm_idx1 = unet_idx // 3, unet_idx % 3
+        if unet_idx % 2 == 2:
+            unet.output_blocks[unet_idx].insert(-1, motion_module.up_blocks[mm_idx0].motion_modules[mm_idx1])
+        else:
+            unet.output_blocks[unet_idx].append(motion_module.up_blocks[mm_idx0].motion_modules[mm_idx1])
+    if motion_module.is_v2:
+        unet.middle_block.insert(-1, motion_module.mid_block.motion_modules[0])
+
+    unet.motion_module = motion_module
+
+
+def eject_motion_module_from_unet_legacy(unet):
+    for unet_idx in [1, 2, 4, 5, 7, 8, 10, 11]:
+        unet.input_blocks[unet_idx].pop(-1)
+
+    for unet_idx in range(12):
+        if unet_idx % 2 == 2:
+            unet.output_blocks[unet_idx].pop(-2)
+        else:
+            unet.output_blocks[unet_idx].pop(-1)
+
+    if unet.motion_module.is_v2:
+        unet.middle_block.pop(-2)
+
+    del unet.motion_module
+
+
+def inject_motion_module_to_unet(unet, motion_module: MotionWrapper):
+    for mm_idx, unet_idx in enumerate([1, 2, 4, 5, 7, 8, 10, 11]):
+        mm_idx0, mm_idx1 = mm_idx // 2, mm_idx % 2
+        unet.input_blocks[unet_idx].append(motion_module.down_blocks[mm_idx0].motion_modules[mm_idx1])
+
+    for unet_idx in range(12):
+        mm_idx0, mm_idx1 = unet_idx // 3, unet_idx % 3
+        if unet_idx % 3 == 2 and unet_idx != 11:
+            unet.output_blocks[unet_idx].insert(-1, motion_module.up_blocks[mm_idx0].motion_modules[mm_idx1])
+        else:
+            unet.output_blocks[unet_idx].append(motion_module.up_blocks[mm_idx0].motion_modules[mm_idx1])
+    if motion_module.is_v2:
+        unet.middle_block.insert(-1, motion_module.mid_block.motion_modules[0])
+
+    unet.motion_module = motion_module
+
+
+def eject_motion_module_from_unet(unet):
+    for unet_idx in [1, 2, 4, 5, 7, 8, 10, 11]:
+        unet.input_blocks[unet_idx].pop(-1)
+
+    for unet_idx in range(12):
+        if unet_idx % 3 == 2 and unet_idx != 11:
+            unet.output_blocks[unet_idx].pop(-2)
+        else:
+            unet.output_blocks[unet_idx].pop(-1)
+
+    if unet.motion_module.is_v2:
+        unet.middle_block.pop(-2)
+
+    del unet.motion_module
+
+
+injectors = {
+    "legacy": inject_motion_module_to_unet_legacy,
+    "default": inject_motion_module_to_unet,
+}
+
+ejectors = {
+    "legacy": eject_motion_module_from_unet_legacy,
+    "default": eject_motion_module_from_unet,
+}
+
+
+class AnimateDiffSlidingWindowOptions:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "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}),
+                "closed_loop": ("BOOLEAN", {"default": False}),
+            }
+        }
+
+    RETURN_TYPES = ("SLIDING_WINDOW_OPTS",)
+    FUNCTION = "init_options"
+    CATEGORY = "Animate Diff"
+
+    def init_options(self, context_length, context_stride, context_overlap, context_schedule, closed_loop):
+        ctx = SlidingContext(
+            context_length=context_length,
+            context_stride=context_stride,
+            context_overlap=context_overlap,
+            context_schedule=context_schedule,
+            closed_loop=closed_loop,
+        )
+
+        return (ctx,)
+
+
+class AnimateDiffSampler(KSampler):
+    @classmethod
+    def INPUT_TYPES(s):
+        inputs = {
+            "required": {
+                "motion_module": ("MOTION_MODULE",),
+                "inject_method": (["default", "legacy"],),
+                "frame_number": (
+                    "INT",
+                    {"default": 16, "min": 2, "max": 10000, "step": 1},
+                ),
+            }
+        }
+        inputs["required"].update(KSampler.INPUT_TYPES()["required"])
+        inputs["optional"] = {"sliding_window_opts": ("SLIDING_WINDOW_OPTS",)}
+        return inputs
+
+    FUNCTION = "animatediff_sample"
+    CATEGORY = "Animate Diff"
+
+    def __init__(self) -> None:
+        super().__init__()
+        self.model_sampling = 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
+        )
+
+    def restore_beta_schedule(self, model: BaseModel):
+        model.model_sampling = self.model_sampling
+        self.model_sampling = None
+
+    def inject_motion_module(self, model, motion_module: MotionWrapper, inject_method: str, frame_number: int):
+        model = model.clone()
+        unet = model.model.diffusion_model
+
+        logger.info(f"Injecting motion module with method {inject_method}.")
+        motion_module.set_video_length(frame_number)
+        injectors[inject_method](unet, motion_module)
+        self.override_beta_schedule(model.model)
+        openaimodel.forward_timestep_embed = forward_timestep_embed
+        if not motion_module.is_v2:
+            logger.info(f"Hacking GroupNorm.forward function.")
+            torch.nn.GroupNorm.forward = groupnorm_mm_factory(frame_number)
+
+        return model
+
+    def inject_sliding_sampler(self, video_length, sliding_window_opts: SlidingContext = None):
+        ctx = sliding_window_opts.copy() if sliding_window_opts else SlidingContext()
+        ctx.video_length = video_length
+
+        inject_sampling_function(ctx)
+
+    def eject_motion_module(self, model, inject_method):
+        unet = model.model.diffusion_model
+
+        self.restore_beta_schedule(model.model)
+        openaimodel.forward_timestep_embed = orig_forward_timestep_embed
+        if not unet.motion_module.is_v2:
+            logger.info(f"Restore GroupNorm.forward function.")
+            torch.nn.GroupNorm.forward = orig_groupnorm_forward
+
+        logger.info(f"Ejecting motion module with method {inject_method}.")
+        ejectors[inject_method](unet)
+
+    def eject_sliding_sampler(self):
+        eject_sampling_function()
+
+    def animatediff_sample(
+        self,
+        motion_module,
+        inject_method,
+        frame_number,
+        model,
+        seed,
+        steps,
+        cfg,
+        sampler_name,
+        scheduler,
+        positive,
+        negative,
+        latent_image,
+        denoise=1.0,
+        sliding_window_opts: SlidingContext = None,
+        **kwargs,
+    ):
+        # init latents
+        samples = latent_image["samples"]
+        init_frames = len(samples)
+        if init_frames < frame_number:
+            # TODO: apply different noise to each frame
+            last_frame = samples[-1].clone().cpu().unsqueeze(0)
+            repeated_last_frames = last_frame.repeat(frame_number - init_frames, 1, 1, 1)
+            samples = torch.cat((samples, repeated_last_frames), dim=0)
+
+        latent_image = {"samples": samples}
+
+        # validate context_length
+        context_length = sliding_window_opts.context_length if sliding_window_opts else SLIDING_CONTEXT_LENGTH
+        is_sliding = frame_number > context_length
+        video_length = context_length if is_sliding else frame_number
+
+        if video_length > motion_module.encoding_max_len:
+            error = f'{"context_length" if is_sliding else "frame_number"} = {video_length}'
+            raise ValueError(
+                f"AnimateDiff model {motion_module.mm_type} has upper limit of {motion_module.encoding_max_len} frames, but received {error}."
+            )
+
+        # inject motion module
+        model = self.inject_motion_module(model, motion_module, inject_method, video_length)
+
+        # inject sliding sampler
+        if is_sliding:
+            self.inject_sliding_sampler(frame_number, sliding_window_opts=sliding_window_opts)
+
+        try:
+            return super().sample(
+                model,
+                seed,
+                steps,
+                cfg,
+                sampler_name,
+                scheduler,
+                positive,
+                negative,
+                latent_image,
+                denoise=denoise,
+                **kwargs,
+            )
+        except:
+            raise
+        finally:
+            # eject motion module
+            self.eject_motion_module(model, inject_method)
+
+            # eject sliding sampler
+            if is_sliding:
+                self.eject_sliding_sampler()

animatediff/sliding_context_sampling.py

@@ -0,0 +1,438 @@
+import math
+import torch
+from torch import Tensor
+from typing import List, Dict
+
+import comfy.utils
+import comfy.sample
+import comfy.samplers as comfy_samplers
+import comfy.model_management as model_management
+from comfy.controlnet import ControlBase
+from comfy.model_patcher import ModelPatcher
+
+from .logger import logger
+from .sliding_schedule import get_context_scheduler, ContextSchedules
+
+
+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,
+        context_length=16,
+        context_stride=1,
+        context_overlap=4,
+        context_schedule=ContextSchedules.UNIFORM,
+        closed_loop=False,
+        video_length=0,
+        current_step=0,
+        total_steps=0,
+    ):
+        self.context_length = context_length
+        self.context_stride = context_stride
+        self.context_overlap = context_overlap
+        self.context_schedule = context_schedule
+        self.closed_loop = closed_loop
+        self.video_length = video_length
+        self.current_step = current_step
+        self.total_steps = total_steps
+
+    def copy(self):
+        return SlidingContext(
+            context_length=self.context_length,
+            context_stride=self.context_stride,
+            context_overlap=self.context_overlap,
+            context_schedule=self.context_schedule,
+            closed_loop=self.closed_loop,
+            video_length=self.video_length,
+            current_step=self.current_step,
+            total_steps=self.total_steps,
+        )
+
+
+def __sliding_sample_factory(ctx: SlidingContext):
+    logger.info(f"Injecting sliding context sampling function.")
+    logger.info(f"Video length: {ctx.video_length}")
+    logger.info(f"Context length: {ctx.context_length}")
+    logger.info(f"Context schedule: {ctx.context_schedule}")
+
+    context_scheduler = get_context_scheduler(ctx.context_schedule)
+
+    def sample(model: ModelPatcher, *args, **kwargs):
+        orig_callback = kwargs.pop("callback", None)
+        start_step = kwargs.get("start_step") or 0
+
+        # adjust progressbar to account for context frames
+        def callback(step, x0, x, total_steps):
+            if orig_callback:
+                orig_callback(step, x0, x, total_steps)
+
+            ctx.current_step = start_step + step + 1
+
+        return orig_comfy_sample(model, *args, **kwargs, callback=callback)
+
+    def sampling_function(model, x, timestep, uncond, cond, cond_scale, model_options={}, seed=None):
+        def get_area_and_mult(conds, x_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_in[0] > timestep_start:
+                    return None
+            if "timestep_end" in conds:
+                timestep_end = conds["timestep_end"]
+                if timestep_in[0] < timestep_end:
+                    return None
+            if "area" in conds:
+                area = conds["area"]
+            if "strength" in conds:
+                strength = conds["strength"]
+
+            input_x = x_in[:, :, area[2] : area[0] + area[2], area[3] : area[1] + area[3]]
+            if "mask" in conds:
+                # 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"]
+                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
+                mask = mask.unsqueeze(1).repeat(input_x.shape[0] // mask.shape[0], input_x.shape[1], 1, 1)
+            else:
+                mask = torch.ones_like(input_x)
+            mult = mask * strength
+
+            if "mask" not in conds:
+                rr = 8
+                if area[2] != 0:
+                    for t in range(rr):
+                        mult[:, :, t : 1 + t, :] *= (1.0 / rr) * (t + 1)
+                if (area[0] + area[2]) < x_in.shape[2]:
+                    for t in range(rr):
+                        mult[:, :, area[0] - 1 - t : area[0] - t, :] *= (1.0 / rr) * (t + 1)
+                if area[3] != 0:
+                    for t in range(rr):
+                        mult[:, :, :, t : 1 + t] *= (1.0 / rr) * (t + 1)
+                if (area[1] + area[3]) < x_in.shape[3]:
+                    for t in range(rr):
+                        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)
+
+            control = None
+            if "control" in conds:
+                control = conds["control"]
+
+            patches = None
+            if "gligen" in conds:
+                gligen = conds["gligen"]
+                patches = {}
+                gligen_type = gligen[0]
+                gligen_model = gligen[1]
+                if gligen_type == "position":
+                    gligen_patch = gligen_model.model.set_position(input_x.shape, gligen[2], input_x.device)
+                else:
+                    gligen_patch = gligen_model.model.set_empty(input_x.shape, input_x.device)
+
+                patches["middle_patch"] = [gligen_patch]
+
+            return (input_x, mult, conditionning, area, control, patches)
+
+        def cond_equal_size(c1, c2):
+            if c1 is c2:
+                return True
+            if c1.keys() != c2.keys():
+                return False
+            for k in c1:
+                if not c1[k].can_concat(c2[k]):
+                    return False
+            return True
+
+        def can_concat_cond(c1, c2):
+            if c1[0].shape != c2[0].shape:
+                return False
+
+            # control
+            if (c1[4] is None) != (c2[4] is None):
+                return False
+            if c1[4] is not None:
+                if c1[4] is not c2[4]:
+                    return False
+
+            # patches
+            if (c1[5] is None) != (c2[5] is None):
+                return False
+            if c1[5] is not None:
+                if c1[5] is not c2[5]:
+                    return False
+
+            return cond_equal_size(c1[2], c2[2])
+
+        def cond_cat(c_list):
+            c_crossattn = []
+            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
+
+            out = {}
+            for k in temp:
+                conds = temp[k]
+                out[k] = conds[0].concat(conds[1:])
+
+            return out
+
+        def calc_cond_uncond_batch(model, cond, uncond, x_in, timestep, model_options):
+            out_cond = torch.zeros_like(x_in)
+            out_count = torch.ones_like(x_in) * 1e-37
+
+            out_uncond = torch.zeros_like(x_in)
+            out_uncond_count = torch.ones_like(x_in) * 1e-37
+
+            COND = 0
+            UNCOND = 1
+
+            to_run = []
+            for x in cond:
+                p = get_area_and_mult(x, x_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)
+                    if p is None:
+                        continue
+
+                    to_run += [(p, UNCOND)]
+
+            while len(to_run) > 0:
+                first = to_run[0]
+                first_shape = first[0][0].shape
+                to_batch_temp = []
+                for x in range(len(to_run)):
+                    if can_concat_cond(to_run[x][0], first[0]):
+                        to_batch_temp += [x]
+
+                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:
+                        to_batch = batch_amount
+                        break
+
+                input_x = []
+                mult = []
+                c = []
+                cond_or_uncond = []
+                area = []
+                control = None
+                patches = None
+                for x in to_batch:
+                    o = to_run.pop(x)
+                    p = o[0]
+                    input_x += [p[0]]
+                    mult += [p[1]]
+                    c += [p[2]]
+                    area += [p[3]]
+                    cond_or_uncond += [o[1]]
+                    control = p[4]
+                    patches = p[5]
+
+                batch_chunks = len(cond_or_uncond)
+                input_x = torch.cat(input_x)
+                c = cond_cat(c)
+                timestep_ = torch.cat([timestep] * batch_chunks)
+
+                if control is not None:
+                    c["control"] = control.get_control(input_x, timestep_, c, len(cond_or_uncond))
+
+                transformer_options = {}
+                if "transformer_options" in model_options:
+                    transformer_options = model_options["transformer_options"].copy()
+
+                if patches is not None:
+                    if "patches" in transformer_options:
+                        cur_patches = transformer_options["patches"].copy()
+                        for p in patches:
+                            if p in cur_patches:
+                                cur_patches[p] = cur_patches[p] + patches[p]
+                            else:
+                                cur_patches[p] = patches[p]
+                    else:
+                        transformer_options["patches"] = patches
+
+                transformer_options["cond_or_uncond"] = cond_or_uncond[:]
+                c["transformer_options"] = transformer_options
+
+                if "model_function_wrapper" in model_options:
+                    output = model_options["model_function_wrapper"](
+                        model.apply_model,
+                        {"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)
+                del input_x
+
+                for o in range(batch_chunks):
+                    if cond_or_uncond[o] == COND:
+                        out_cond[:, :, area[o][2] : area[o][0] + area[o][2], area[o][3] : area[o][1] + area[o][3]] += (
+                            output[o] * mult[o]
+                        )
+                        out_count[
+                            :, :, area[o][2] : area[o][0] + area[o][2], area[o][3] : area[o][1] + area[o][3]
+                        ] += mult[o]
+                    else:
+                        out_uncond[
+                            :, :, area[o][2] : area[o][0] + area[o][2], area[o][3] : area[o][1] + area[o][3]
+                        ] += (output[o] * mult[o])
+                        out_uncond_count[
+                            :, :, area[o][2] : area[o][0] + area[o][2], area[o][3] : area[o][1] + area[o][3]
+                        ] += mult[o]
+                del mult
+
+            out_cond /= out_count
+            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):
+            # figure out how input is split
+            axes_factor = x.size(0) // ctx.video_length
+
+            # prepare final cond, uncond, and out_count
+            cond_final = torch.zeros_like(x)
+            uncond_final = torch.zeros_like(x)
+            out_count_final = torch.zeros((x.shape[0], 1, 1, 1), device=x.device)
+
+            def prepare_control_objects(control: ControlBase, full_idxs: list[int]):
+                if control.previous_controlnet is not None:
+                    prepare_control_objects(control.previous_controlnet, full_idxs)
+                control.sub_idxs = full_idxs
+                control.full_latent_length = ctx.video_length
+                control.context_length = ctx.context_length
+
+            def get_resized_cond(cond_in: List[Dict], 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():
+                        if isinstance(cond_item, Tensor):
+                            # check that tensor is the expected length - x.size(0)
+                            if cond_item.size(0) == x.size(0):
+                                # 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)
+                            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)
+                return resized_cond
+
+            # perform calc_cond_uncond_batch per context window
+            for ctx_idxs in context_scheduler(
+                ctx.current_step,
+                ctx.total_steps,
+                ctx.video_length,
+                ctx.context_length,
+                ctx.context_stride,
+                ctx.context_overlap,
+                ctx.closed_loop,
+            ):
+                # account for all portions of input frames
+                full_idxs = []
+                for n in range(axes_factor):
+                    for ind in ctx_idxs:
+                        full_idxs.append((ctx.video_length * n) + ind)
+                # get subsections of x, timestep, cond, uncond, cond_concat
+                sub_x = x[full_idxs]
+                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_out, sub_uncond_out = calc_cond_uncond_batch(
+                    model,
+                    sub_cond,
+                    sub_uncond,
+                    sub_x,
+                    sub_timestep,
+                    model_options,
+                )
+
+                cond_final[full_idxs] += sub_cond_out
+                uncond_final[full_idxs] += sub_uncond_out
+                out_count_final[full_idxs] += 1  # increment which indeces were used
+
+            # normalize cond and uncond via division by context usage counts
+            cond_final /= out_count_final
+            uncond_final /= out_count_final
+            return cond_final, uncond_final
+
+        if math.isclose(cond_scale, 1.0):
+            uncond = None
+
+        cond, uncond = sliding_calc_cond_uncond_batch(model, cond, uncond, x, timestep, 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)
+        else:
+            return uncond + (cond - uncond) * cond_scale
+
+    return (sample, sampling_function)
+
+
+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
+
+
+def eject_sampling_function():
+    comfy.sample.sample = orig_comfy_sample
+    comfy_samplers.sampling_function = orig_sampling_function

animatediff/sliding_schedule.py

@@ -0,0 +1,153 @@
+# from https://github.com/neggles/animatediff-cli/blob/main/src/animatediff/pipelines/context.py
+from typing import Callable, Optional
+
+import numpy as np
+
+
+class ContextSchedules:
+    UNIFORM = "uniform"
+    UNIFORM_CONSTANT = "uniform_constant"
+    UNIFORM_V2 = "uniform v2"
+
+    CONTEXT_SCHEDULE_LIST = [UNIFORM]
+
+
+# Returns fraction that has denominator that is a power of 2
+def ordered_halving(val, print_final=False):
+    # get binary value, padded with 0s for 64 bits
+    bin_str = f"{val:064b}"
+    # flip binary value, padding included
+    bin_flip = bin_str[::-1]
+    # convert binary to int
+    as_int = int(bin_flip, 2)
+    # divide by 1 << 64, equivalent to 2**64, or 18446744073709551616,
+    # or b10000000000000000000000000000000000000000000000000000000000000000 (1 with 64 zero's)
+    final = as_int / (1 << 64)
+    if print_final:
+        print(f"$$$$ final: {final}")
+    return final
+
+
+# Generator that returns lists of latent indeces to diffuse on
+def uniform(
+    step: int = ...,
+    num_steps: Optional[int] = None,
+    num_frames: int = ...,
+    context_size: Optional[int] = None,
+    context_stride: int = 3,
+    context_overlap: int = 4,
+    closed_loop: bool = True,
+    print_final: bool = False,
+):
+    if num_frames <= context_size:
+        yield list(range(num_frames))
+        return
+
+    context_stride = min(context_stride, int(np.ceil(np.log2(num_frames / context_size))) + 1)
+
+    for context_step in 1 << np.arange(context_stride):
+        pad = int(round(num_frames * ordered_halving(step, print_final)))
+        for j in range(
+            int(ordered_halving(step) * context_step) + pad,
+            num_frames + pad + (0 if closed_loop else -context_overlap),
+            (context_size * context_step - context_overlap),
+        ):
+            yield [e % num_frames for e in range(j, j + context_size * context_step, context_step)]
+
+
+def uniform_v2(
+    step: int = ...,
+    num_steps: Optional[int] = None,
+    num_frames: int = ...,
+    context_size: Optional[int] = None,
+    context_stride: int = 3,
+    context_overlap: int = 4,
+    closed_loop: bool = True,
+    print_final: bool = False,
+):
+    if num_frames <= context_size:
+        yield list(range(num_frames))
+        return
+
+    context_stride = min(context_stride, int(np.ceil(np.log2(num_frames / context_size))) + 1)
+
+    pad = int(round(num_frames * ordered_halving(step, print_final)))
+    for context_step in 1 << np.arange(context_stride):
+        j_initial = int(ordered_halving(step) * context_step) + pad
+        for j in range(
+            j_initial,
+            num_frames + pad - context_overlap,
+            (context_size * context_step - context_overlap),
+        ):
+            if context_size * context_step > num_frames:
+                # On the final context_step,
+                # ensure no frame appears in the window twice
+                yield [e % num_frames for e in range(j, j + num_frames, context_step)]
+                continue
+            j = j % num_frames
+            if j > (j + context_size * context_step) % num_frames and not closed_loop:
+                yield [e for e in range(j, num_frames, context_step)]
+                j_stop = (j + context_size * context_step) % num_frames
+                # When  ((num_frames % (context_size - context_overlap)+context_overlap) % context_size != 0,
+                # This can cause 'superflous' runs where all frames in
+                # a context window have already been processed during
+                # the first context window of this stride and step.
+                # While the following commented if should prevent this,
+                # I believe leaving it in is more correct as it maintains
+                # the total conditional passes per frame over a large total steps
+                # if j_stop > context_overlap:
+                yield [e for e in range(0, j_stop, context_step)]
+                continue
+            yield [e % num_frames for e in range(j, j + context_size * context_step, context_step)]
+
+
+def uniform_constant(
+    step: int = ...,
+    num_steps: Optional[int] = None,
+    num_frames: int = ...,
+    context_size: Optional[int] = None,
+    context_stride: int = 3,
+    context_overlap: int = 4,
+    closed_loop: bool = True,
+    print_final: bool = False,
+):
+    if num_frames <= context_size:
+        yield list(range(num_frames))
+        return
+
+    context_stride = min(context_stride, int(np.ceil(np.log2(num_frames / context_size))) + 1)
+
+    # want to avoid loops that connect end to beginning
+
+    for context_step in 1 << np.arange(context_stride):
+        pad = int(round(num_frames * ordered_halving(step, print_final)))
+        for j in range(
+            int(ordered_halving(step) * context_step) + pad,
+            num_frames + pad + (0 if closed_loop else -context_overlap),
+            (context_size * context_step - context_overlap),
+        ):
+            skip_this_window = False
+            prev_val = -1
+            to_yield = []
+            for e in range(j, j + context_size * context_step, context_step):
+                e = e % num_frames
+                # if not a closed loop and loops back on itself, should be skipped
+                if not closed_loop and e < prev_val:
+                    skip_this_window = True
+                    break
+                to_yield.append(e)
+                prev_val = e
+            if skip_this_window:
+                continue
+            # 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}")

animatediff/utils.py

@@ -0,0 +1,32 @@
+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))
+
+
+# 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.")

requirements.txt

@@ -0,0 +1 @@
+opencv-python

video_formats/av1-webm.json

@@ -0,0 +1,10 @@
+{
+    "main_pass":
+    [
+        "-n", "-c:v", "libsvtav1",
+        "-pix_fmt", "yuv420p10le",
+        "-crf", "23"
+    ],
+     "extension": "webm",
+     "environment": {"SVT_LOG": "1"}
+}

video_formats/h264-mp4.json

@@ -0,0 +1,9 @@
+{
+    "main_pass":
+    [
+        "-n", "-c:v", "libx264",
+        "-pix_fmt", "yuv420p",
+        "-crf", "19"
+    ],
+     "extension": "mp4"
+}

video_formats/h265-mp4.json

@@ -0,0 +1,11 @@
+{
+    "main_pass":
+    [
+        "-n", "-c:v", "libx265",
+        "-pix_fmt", "yuv420p10le",
+        "-preset", "medium",
+        "-crf", "22",
+        "-x265-params", "log-level=quiet"
+    ],
+     "extension": "mp4"
+}

video_formats/webm.json

@@ -0,0 +1,9 @@
+{
+    "main_pass":
+    [
+        "-n",
+        "-pix_fmt", "yuv420p",
+        "-crf", "23"
+    ],
+     "extension": "webm"
+}

web/js/vid_preview.js

@@ -0,0 +1,245 @@
+import { app, ANIM_PREVIEW_WIDGET } 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\/)/;
+
+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);
+    }
+  });
+}
+
+app.registerExtension({
+  name: "AnimateDiff.VideoPreview",
+  init() {
+    $el('style', {
+      textContent: style,
+      parent: document.head,
+    });
+  },
+  async beforeRegisterNodeDef(nodeType, nodeData) {
+    if (nodeData.name !== "AnimateDiffCombine") {
+      return;
+    }
+
+    addVideoPreview(nodeType);
+  },
+});

web/js/vid_upload.js

@@ -0,0 +1,90 @@
+import { app } from "../../../scripts/app.js";
+import { api } from "../../../scripts/api.js";
+
+import {
+  chainCallback,
+  addVideoPreview,
+} from "./vid_preview.js";
+
+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,
+    });
+
+    if (resp.status === 200 || resp.status === 201) {
+      return resp.json();
+    } else {
+      alert(`Upload failed: ${resp.statusText}`);
+    }
+  } 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);
+        }
+      },
+    });
+
+    document.body.append(fileInput);
+    let uploadWidget = this.addWidget(
+      "button",
+      "choose video to upload",
+      "image",
+      () => {
+        app.canvas.node_widget = null;
+        fileInput.click();
+      }
+    );
+    uploadWidget.options.serialize = false;
+  });
+}
+
+// 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' });
+    }
+  },
+});

workflows/cn-vid2vid.json

@@ -0,0 +1,877 @@
+{
+  "last_node_id": 107,
+  "last_link_id": 199,
+  "nodes": [
+    {
+      "id": 16,
+      "type": "AnimateDiffModuleLoader",
+      "pos": [
+        -280,
+        140
+      ],
+      "size": {
+        "0": 310,
+        "1": 60
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "MOTION_MODULE",
+          "type": "MOTION_MODULE",
+          "links": [
+            193
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AnimateDiffModuleLoader"
+      },
+      "widgets_values": [
+        "mm-Stabilized_mid.pth"
+      ],
+      "color": "#571a1a",
+      "bgcolor": "#6b2e2e"
+    },
+    {
+      "id": 13,
+      "type": "VAELoader",
+      "pos": [
+        -280,
+        400
+      ],
+      "size": {
+        "0": 310,
+        "1": 60
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            82
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAELoader"
+      },
+      "widgets_values": [
+        "vae-ft-mse-840000-ema-pruned.safetensors"
+      ],
+      "color": "#571a1a",
+      "bgcolor": "#6b2e2e"
+    },
+    {
+      "id": 45,
+      "type": "AnimateDiffCombine",
+      "pos": [
+        1240,
+        140
+      ],
+      "size": {
+        "0": 360,
+        "1": 732
+      },
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 172
+        }
+      ],
+      "outputs": [
+        {
+          "name": "GIF",
+          "type": "GIF",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AnimateDiffCombine"
+      },
+      "widgets_values": [
+        8,
+        0,
+        true,
+        "AnimateDiff",
+        "image/gif",
+        true
+      ]
+    },
+    {
+      "id": 4,
+      "type": "CheckpointLoaderSimple",
+      "pos": [
+        -280,
+        250
+      ],
+      "size": {
+        "0": 310,
+        "1": 100
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            194
+          ],
+          "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": [
+        "SDHK_v4.safetensors"
+      ],
+      "color": "#571a1a",
+      "bgcolor": "#6b2e2e"
+    },
+    {
+      "id": 7,
+      "type": "CLIPTextEncode",
+      "pos": [
+        60,
+        300
+      ],
+      "size": {
+        "0": 310,
+        "1": 100
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 5
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            70
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "embedding:easynegative, embedding:badhandv4, nsfw"
+      ],
+      "color": "#572e1a",
+      "bgcolor": "#6b422e"
+    },
+    {
+      "id": 6,
+      "type": "CLIPTextEncode",
+      "pos": [
+        60,
+        140
+      ],
+      "size": {
+        "0": 310,
+        "1": 110
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 3
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            69
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "(best quality, masterpiece), 1girl, short hair, blue eyes, dancing, city, cloudy"
+      ],
+      "color": "#572e1a",
+      "bgcolor": "#6b422e"
+    },
+    {
+      "id": 39,
+      "type": "ControlNetApplyAdvanced",
+      "pos": [
+        471,
+        275
+      ],
+      "size": {
+        "0": 300,
+        "1": 170
+      },
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 69
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 70
+        },
+        {
+          "name": "control_net",
+          "type": "CONTROL_NET",
+          "link": 68
+        },
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 181
+        }
+      ],
+      "outputs": [
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "links": [
+            195
+          ],
+          "shape": 3,
+          "slot_index": 0
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "links": [
+            196
+          ],
+          "shape": 3,
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ControlNetApplyAdvanced"
+      },
+      "widgets_values": [
+        1,
+        0,
+        1
+      ],
+      "color": "#43571a",
+      "bgcolor": "#576b2e"
+    },
+    {
+      "id": 103,
+      "type": "LoadVideo",
+      "pos": [
+        -280,
+        650
+      ],
+      "size": [
+        310,
+        629
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "frames",
+          "type": "IMAGE",
+          "links": [
+            181,
+            182,
+            186
+          ],
+          "shape": 3,
+          "slot_index": 0
+        },
+        {
+          "name": "frame_count",
+          "type": "INT",
+          "links": null,
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LoadVideo"
+      },
+      "widgets_values": [
+        "video/265043418-23291941-864d-495a-8ba8-d02e05756396.gif",
+        "image",
+        0,
+        16,
+        "/view?filename=265043418-23291941-864d-495a-8ba8-d02e05756396.gif&type=input&subfolder=video&format=image%2Fgif"
+      ]
+    },
+    {
+      "id": 20,
+      "type": "EmptyLatentImage",
+      "pos": [
+        520,
+        630
+      ],
+      "size": {
+        "0": 210,
+        "1": 80
+      },
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "width",
+          "type": "INT",
+          "link": 190,
+          "widget": {
+            "name": "width",
+            "config": [
+              "INT",
+              {
+                "default": 512,
+                "min": 64,
+                "max": 8192,
+                "step": 8
+              }
+            ]
+          }
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "link": 191,
+          "widget": {
+            "name": "height",
+            "config": [
+              "INT",
+              {
+                "default": 512,
+                "min": 64,
+                "max": 8192,
+                "step": 8
+              }
+            ]
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            197
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EmptyLatentImage"
+      },
+      "widgets_values": [
+        512,
+        512,
+        1
+      ],
+      "color": "#1a572e",
+      "bgcolor": "#2e6b42"
+    },
+    {
+      "id": 36,
+      "type": "ControlNetLoaderAdvanced",
+      "pos": [
+        -280,
+        540
+      ],
+      "size": {
+        "0": 310,
+        "1": 60
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "timestep_keyframe",
+          "type": "TIMESTEP_KEYFRAME",
+          "link": null,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONTROL_NET",
+          "type": "CONTROL_NET",
+          "links": [
+            68
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ControlNetLoaderAdvanced"
+      },
+      "widgets_values": [
+        "control_v11p_sd15_openpose.pth"
+      ],
+      "color": "#571a1a",
+      "bgcolor": "#6b2e2e"
+    },
+    {
+      "id": 105,
+      "type": "PreviewImage",
+      "pos": [
+        70,
+        830
+      ],
+      "size": {
+        "0": 530,
+        "1": 420
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 186
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      },
+      "color": "#1a5757",
+      "bgcolor": "#2e6b6b"
+    },
+    {
+      "id": 106,
+      "type": "PreviewImage",
+      "pos": [
+        670,
+        830
+      ],
+      "size": {
+        "0": 530,
+        "1": 420
+      },
+      "flags": {},
+      "order": 14,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 187
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      },
+      "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": [
+    [
+      3,
+      4,
+      1,
+      6,
+      0,
+      "CLIP"
+    ],
+    [
+      5,
+      4,
+      1,
+      7,
+      0,
+      "CLIP"
+    ],
+    [
+      68,
+      36,
+      0,
+      39,
+      2,
+      "CONTROL_NET"
+    ],
+    [
+      69,
+      6,
+      0,
+      39,
+      0,
+      "CONDITIONING"
+    ],
+    [
+      70,
+      7,
+      0,
+      39,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      82,
+      13,
+      0,
+      44,
+      1,
+      "VAE"
+    ],
+    [
+      172,
+      44,
+      0,
+      45,
+      0,
+      "IMAGE"
+    ],
+    [
+      181,
+      103,
+      0,
+      39,
+      3,
+      "IMAGE"
+    ],
+    [
+      182,
+      103,
+      0,
+      104,
+      0,
+      "IMAGE"
+    ],
+    [
+      186,
+      103,
+      0,
+      105,
+      0,
+      "IMAGE"
+    ],
+    [
+      187,
+      44,
+      0,
+      106,
+      0,
+      "IMAGE"
+    ],
+    [
+      190,
+      104,
+      0,
+      20,
+      0,
+      "INT"
+    ],
+    [
+      191,
+      104,
+      1,
+      20,
+      1,
+      "INT"
+    ],
+    [
+      193,
+      16,
+      0,
+      107,
+      0,
+      "MOTION_MODULE"
+    ],
+    [
+      194,
+      4,
+      0,
+      107,
+      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": [],
+  "config": {},
+  "extra": {},
+  "version": 0.4
+}

workflows/latent-upscale.json

@@ -0,0 +1,828 @@
+{
+  "last_node_id": 28,
+  "last_link_id": 56,
+  "nodes": [
+    {
+      "id": 20,
+      "type": "EmptyLatentImage",
+      "pos": [
+        520,
+        20
+      ],
+      "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": 25,
+      "type": "Reroute",
+      "pos": [
+        440,
+        611
+      ],
+      "size": [
+        75,
+        26
+      ],
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "",
+          "type": "*",
+          "link": 45
+        }
+      ],
+      "outputs": [
+        {
+          "name": "",
+          "type": "LATENT",
+          "links": [
+            46
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "showOutputText": false,
+        "horizontal": false
+      }
+    },
+    {
+      "id": 24,
+      "type": "Reroute",
+      "pos": [
+        1224,
+        604
+      ],
+      "size": [
+        75,
+        26
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "",
+          "type": "*",
+          "link": 44
+        }
+      ],
+      "outputs": [
+        {
+          "name": "",
+          "type": "LATENT",
+          "links": [
+            45
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "showOutputText": false,
+        "horizontal": false
+      }
+    },
+    {
+      "id": 16,
+      "type": "AnimateDiffModuleLoader",
+      "pos": [
+        27,
+        345
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "MOTION_MODULE",
+          "type": "MOTION_MODULE",
+          "links": [
+            24,
+            48
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AnimateDiffModuleLoader"
+      },
+      "widgets_values": [
+        "mm-Stabilized_mid.pth"
+      ]
+    },
+    {
+      "id": 4,
+      "type": "CheckpointLoaderSimple",
+      "pos": [
+        26,
+        474
+      ],
+      "size": {
+        "0": 315,
+        "1": 98
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            25,
+            49
+          ],
+          "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": [
+        "AnimeLike25D_v11.safetensors"
+      ]
+    },
+    {
+      "id": 22,
+      "type": "LatentUpscaleBy",
+      "pos": [
+        571,
+        712
+      ],
+      "size": {
+        "0": 275.35137939453125,
+        "1": 82
+      },
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 46
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            47
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LatentUpscaleBy"
+      },
+      "widgets_values": [
+        "nearest-exact",
+        1.5
+      ]
+    },
+    {
+      "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,
+            50
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "masterpiece, best quality, 1girl, solo, cherry blossoms, hanami, pink flower, white flower, spring season, wisteria, petals, flower, plum blossoms, outdoors, falling petals, white hair, black eyes"
+      ]
+    },
+    {
+      "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,
+            51
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "embedding:easynegative, embedding:badhandv4, "
+      ]
+    },
+    {
+      "id": 26,
+      "type": "AnimateDiffSampler",
+      "pos": [
+        893,
+        712
+      ],
+      "size": {
+        "0": 315,
+        "1": 350
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "motion_module",
+          "type": "MOTION_MODULE",
+          "link": 48,
+          "slot_index": 0
+        },
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 49,
+          "slot_index": 1
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 50
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 51
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 47
+        },
+        {
+          "name": "sliding_window_opts",
+          "type": "SLIDING_WINDOW_OPTS",
+          "link": null
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            52
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AnimateDiffSampler"
+      },
+      "widgets_values": [
+        "default",
+        16,
+        345029849956687,
+        "increment",
+        20,
+        8,
+        "euler",
+        "normal",
+        0.4
+      ]
+    },
+    {
+      "id": 8,
+      "type": "VAEDecode",
+      "pos": [
+        1239,
+        712
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 52
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 20
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            19
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      }
+    },
+    {
+      "id": 15,
+      "type": "AnimateDiffSampler",
+      "pos": [
+        882,
+        192
+      ],
+      "size": {
+        "0": 315,
+        "1": 350
+      },
+      "flags": {},
+      "order": 6,
+      "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": [
+            44,
+            53
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AnimateDiffSampler"
+      },
+      "widgets_values": [
+        "default",
+        16,
+        345029849956687,
+        "increment",
+        20,
+        8,
+        "euler",
+        "normal",
+        1
+      ]
+    },
+    {
+      "id": 13,
+      "type": "VAELoader",
+      "pos": [
+        27,
+        631
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            20,
+            54
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAELoader"
+      },
+      "widgets_values": [
+        "klF8Anime2.ckpt"
+      ]
+    },
+    {
+      "id": 27,
+      "type": "VAEDecode",
+      "pos": [
+        1258,
+        187
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 53
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 54
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            56
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      }
+    },
+    {
+      "id": 28,
+      "type": "AnimateDiffCombine",
+      "pos": [
+        1505,
+        -72
+      ],
+      "size": {
+        "0": 321.19171142578125,
+        "1": 513.0408935546875
+      },
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 56
+        }
+      ],
+      "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
+      ]
+    },
+    {
+      "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
+      ]
+    }
+  ],
+  "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"
+    ],
+    [
+      29,
+      6,
+      0,
+      15,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      30,
+      7,
+      0,
+      15,
+      3,
+      "CONDITIONING"
+    ],
+    [
+      35,
+      20,
+      0,
+      15,
+      4,
+      "LATENT"
+    ],
+    [
+      44,
+      15,
+      0,
+      24,
+      0,
+      "*"
+    ],
+    [
+      45,
+      24,
+      0,
+      25,
+      0,
+      "*"
+    ],
+    [
+      46,
+      25,
+      0,
+      22,
+      0,
+      "LATENT"
+    ],
+    [
+      47,
+      22,
+      0,
+      26,
+      4,
+      "LATENT"
+    ],
+    [
+      48,
+      16,
+      0,
+      26,
+      0,
+      "MOTION_MODULE"
+    ],
+    [
+      49,
+      4,
+      0,
+      26,
+      1,
+      "MODEL"
+    ],
+    [
+      50,
+      6,
+      0,
+      26,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      51,
+      7,
+      0,
+      26,
+      3,
+      "CONDITIONING"
+    ],
+    [
+      52,
+      26,
+      0,
+      8,
+      0,
+      "LATENT"
+    ],
+    [
+      53,
+      15,
+      0,
+      27,
+      0,
+      "LATENT"
+    ],
+    [
+      54,
+      13,
+      0,
+      27,
+      1,
+      "VAE"
+    ],
+    [
+      56,
+      27,
+      0,
+      28,
+      0,
+      "IMAGE"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {},
+  "version": 0.4
+}

workflows/lora.json

@@ -0,0 +1,515 @@
+{
+  "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
+}

workflows/sliding-window.json

@@ -0,0 +1,502 @@
+{
+  "last_node_id": 21,
+  "last_link_id": 36,
+  "nodes": [
+    {
+      "id": 6,
+      "type": "CLIPTextEncode",
+      "pos": [
+        415,
+        186
+      ],
+      "size": {
+        "0": 422.84503173828125,
+        "1": 164.31304931640625
+      },
+      "flags": {},
+      "order": 5,
+      "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": [
+        "masterpiece, best quality, 1girl, solo, cherry blossoms, hanami, pink flower, white flower, spring season, wisteria, petals, flower, plum blossoms, outdoors, falling petals, white hair, black eyes"
+      ]
+    },
+    {
+      "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": {
+        "0": 315,
+        "1": 342
+      },
+      "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
+      ]
+    },
+    {
+      "id": 16,
+      "type": "AnimateDiffModuleLoader",
+      "pos": [
+        27,
+        345
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "MOTION_MODULE",
+          "type": "MOTION_MODULE",
+          "links": [
+            24
+          ],
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AnimateDiffModuleLoader"
+      },
+      "widgets_values": [
+        "mm-Stabilized_mid.pth"
+      ]
+    },
+    {
+      "id": 4,
+      "type": "CheckpointLoaderSimple",
+      "pos": [
+        26,
+        474
+      ],
+      "size": {
+        "0": 315,
+        "1": 98
+      },
+      "flags": {},
+      "order": 1,
+      "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": [
+        "AnimeLike25D_v11.safetensors"
+      ]
+    },
+    {
+      "id": 13,
+      "type": "VAELoader",
+      "pos": [
+        28,
+        223
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            20
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAELoader"
+      },
+      "widgets_values": [
+        "klF8Anime2.ckpt"
+      ]
+    },
+    {
+      "id": 7,
+      "type": "CLIPTextEncode",
+      "pos": [
+        413,
+        389
+      ],
+      "size": {
+        "0": 425.27801513671875,
+        "1": 180.6060791015625
+      },
+      "flags": {},
+      "order": 6,
+      "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": [
+        "embedding:easynegative, embedding:badhandv4, "
+      ]
+    },
+    {
+      "id": 20,
+      "type": "EmptyLatentImage",
+      "pos": [
+        522,
+        621
+      ],
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {},
+      "order": 3,
+      "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": 21,
+      "type": "AnimateDiffSlidingWindowOptions",
+      "pos": [
+        517,
+        -34
+      ],
+      "size": {
+        "0": 315,
+        "1": 154
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "SLIDING_WINDOW_OPTS",
+          "type": "SLIDING_WINDOW_OPTS",
+          "links": [
+            36
+          ],
+          "shape": 3
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AnimateDiffSlidingWindowOptions"
+      },
+      "widgets_values": [
+        16,
+        1,
+        4,
+        "uniform",
+        true
+      ]
+    },
+    {
+      "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": 36,
+          "slot_index": 5
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            28
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "AnimateDiffSampler"
+      },
+      "widgets_values": [
+        "default",
+        40,
+        345029849956677,
+        "fixed",
+        20,
+        8,
+        "euler",
+        "normal",
+        0.8
+      ]
+    }
+  ],
+  "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"
+    ],
+    [
+      36,
+      21,
+      0,
+      15,
+      5,
+      "SLIDING_WINDOW_OPTS"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {},
+  "version": 0.4
+}