Upload RAV model checkpoints and configuration

LICENSE-SVD.txt

@@ -0,0 +1,58 @@
+STABILITY AI COMMUNITY LICENSE AGREEMENT
+	
+Last Updated: July 5, 2024
+
+1. INTRODUCTION
+
+This Agreement applies to any individual person or entity (“You”, “Your” or “Licensee”) that uses or distributes any portion or element of the Stability AI Materials  or Derivative Works thereof for any Research & Non-Commercial or Commercial purpose. Capitalized terms not otherwise defined herein are defined in Section V below.
+
+This Agreement is intended to allow research, non-commercial, and limited commercial uses of the Models free of charge. In order to ensure that certain limited commercial uses of the Models continue to be allowed, this Agreement  preserves free access to the Models for people or organizations  generating annual revenue of less than US $1,000,000 (or local currency equivalent).  
+
+By clicking “I Accept”  or by using or distributing or using any portion or element of the Stability Materials or Derivative Works, You agree that You have read, understood and are bound by the terms of this Agreement. If You are acting on behalf of a company, organization or other entity, then “You” includes you and that entity, and You agree that You: (i) are an authorized representative of such entity with the authority to bind such entity to this Agreement, and (ii) You agree to the terms of this Agreement on that entity’s behalf. 
+
+2. RESEARCH & NON-COMMERCIAL USE LICENSE
+
+Subject to the terms of this Agreement, Stability AI grants You a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable and royalty-free limited license under Stability AI’s intellectual property or other rights owned by Stability AI embodied in the Stability AI Materials to use, reproduce, distribute, and create Derivative Works of, and make modifications to, the Stability AI Materials for any Research or Non-Commercial Purpose. “Research Purpose” means academic or scientific advancement, and in each case, is not primarily intended for commercial advantage or monetary compensation to You or others. “Non-Commercial Purpose” means any purpose other than a Research Purpose that is not primarily intended for commercial advantage or monetary compensation to You or others, such as personal use (i.e., hobbyist) or evaluation and testing.  
+
+3. COMMERCIAL USE LICENSE
+
+Subject to the terms of this Agreement (including the remainder of this Section III), Stability AI grants You a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable and royalty-free limited license under Stability AI’s intellectual property or other rights owned by Stability AI embodied in the Stability AI Materials to use, reproduce, distribute, and create Derivative Works of, and make modifications to, the Stability AI Materials for any Commercial Purpose. “Commercial Purpose” means any purpose other than a Research Purpose or Non-Commercial Purpose that is primarily intended for commercial advantage or monetary compensation to You or others, including but not limited to, (i) creating, modifying, or distributing Your product or service, including via a hosted service or application programming interface, and (ii) for Your business’s or organization’s internal operations. 
+If You are using or distributing the Stability AI Materials for a Commercial Purpose, You must register with Stability AI at (https://stability.ai/community-license). If at any time You or Your Affiliate(s), either individually or in aggregate, generate more than USD $1,000,000 in annual revenue (or the equivalent thereof in Your local currency), regardless of whether that revenue is generated directly or indirectly from the Stability AI Materials or Derivative Works, any licenses granted to You under this Agreement shall terminate as of such date. You must request a license from Stability AI at (https://stability.ai/enterprise) , which Stability AI may grant to You in its sole discretion. If you receive Stability AI Materials, or any Derivative Works thereof, from a Licensee as part of an integrated end user product, then Section III of this Agreement will not apply to you.
+
+4. GENERAL TERMS
+
+Your Research, Non-Commercial, and Commercial License(s) under this Agreement are subject to the following terms.
+a.  Distribution & Attribution. If You distribute or make available the Stability AI Materials or a Derivative Work to a third party, or a product or service that uses any portion of them, You shall: (i) provide a copy of this Agreement to that third party, (ii) retain the following attribution notice within a "Notice" text file distributed as a part of such copies: "This Stability AI Model is licensed under the Stability AI Community License, Copyright ©  Stability AI Ltd. All Rights Reserved”, and (iii) prominently display “Powered by Stability AI” on a related website, user interface, blogpost, about page, or product documentation.  If You create a Derivative Work, You may add your own attribution notice(s) to the “Notice” text file included with that Derivative Work, provided that You clearly indicate which attributions apply to the Stability AI Materials and state in the “Notice” text file that You changed the Stability AI Materials and how it was modified.
+b.  Use Restrictions. Your use of the Stability AI Materials and Derivative Works, including any output or results of the Stability AI Materials or Derivative Works, must comply with applicable laws and regulations (including Trade Control Laws and equivalent regulations) and adhere to the Documentation and Stability AI’s AUP, which is hereby incorporated by reference. Furthermore, You will not use the Stability AI Materials or Derivative Works, or any output or results of the Stability AI Materials or Derivative Works, to create or improve any foundational generative AI model (excluding the Models or Derivative Works). 
+c.  Intellectual Property. 
+(i) Trademark License.  No trademark licenses are granted under this Agreement, and in connection with the Stability AI Materials or Derivative Works, You may not use any name or mark owned by or associated with Stability AI or any of its Affiliates, except as required under Section IV(a) herein.
+(ii)  Ownership of Derivative Works.  As between You and Stability AI, You are the owner of Derivative Works You create, subject to Stability AI’s ownership of the Stability AI Materials and any Derivative Works made by or for Stability AI.
+(iii)  Ownership of Outputs. As between You and Stability AI, You own any outputs generated from the Models or Derivative Works to the extent permitted by applicable law. 
+(iv)  Disputes.  If You or Your Affiliate(s) institute litigation or other proceedings against Stability AI (including a cross-claim or counterclaim in a lawsuit) alleging that the Stability AI Materials, Derivative Works or associated outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by You, then any licenses granted to You under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Stability AI from and against any claim by any third party arising out of or related to Your use or distribution of the Stability AI Materials or Derivative Works in violation of this Agreement.
+(v)  Feedback.  From time to time, You may provide Stability AI with verbal and/or written suggestions, comments or other feedback related to Stability AI’s existing or prospective technology, products or services (collectively, “Feedback”). You are not obligated to provide Stability AI with Feedback, but to the extent that You do, You hereby grant Stability AI a perpetual, irrevocable, royalty-free, fully-paid, sub-licensable, transferable, non-exclusive, worldwide right and license to exploit the Feedback in any manner without restriction. Your Feedback is provided “AS IS” and You make no warranties whatsoever about any Feedback.
+d.  Disclaimer Of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE STABILITY AI MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OR LAWFULNESS OF USING OR REDISTRIBUTING THE STABILITY AI MATERIALS, DERIVATIVE WORKS OR ANY OUTPUT OR RESULTS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE STABILITY AI MATERIALS, DERIVATIVE WORKS AND ANY OUTPUT AND RESULTS.
+e.  Limitation Of Liability. IN NO EVENT WILL STABILITY AI OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY DIRECT, INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF STABILITY AI OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+f.  Term And Termination. The term of this Agreement will commence upon Your acceptance of this Agreement or access to the Stability AI Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Stability AI may terminate this Agreement if You are in breach of any term or condition of this Agreement. Upon termination of this Agreement, You shall delete and cease use of any Stability AI Materials or Derivative Works. Section IV(d), (e), and (g) shall survive the termination of this Agreement.
+g.  Governing Law.  This Agreement will be governed by and constructed in accordance with the laws of the United States and the State of California without regard to choice of law principles, and the UN Convention on Contracts for International Sale of Goods does not apply to this Agreement.
+
+5. DEFINITIONS 
+
+“Affiliate(s)” means any entity that directly or indirectly controls, is controlled by, or is under common control with the subject entity; for purposes of this definition, “control” means direct or indirect ownership or control of more than 50% of the voting interests of the subject entity.
+
+"Agreement" means this Stability AI Community License Agreement.
+
+“AUP” means the Stability AI Acceptable Use Policy available at (https://stability.ai/use-policy), as may be updated from time to time.
+
+"Derivative Work(s)” means (a) any derivative work of the Stability AI Materials as recognized by U.S. copyright laws and (b) any modifications to a Model, and any other model created which is based on or derived from the Model or the Model’s output, including “fine tune” and “low-rank adaptation” models derived from a Model or a Model’s output, but do not include the output of any Model.
+
+“Documentation” means any specifications, manuals, documentation, and other written information provided by Stability AI related to the Software or Models.
+
+“Model(s)" means, collectively, Stability AI’s proprietary models and algorithms, including machine-learning models, trained model weights and other elements of the foregoing listed on Stability’s Core Models Webpage available at (https://stability.ai/core-models), as may be updated from time to time.
+
+"Stability AI" or "we" means Stability AI Ltd. and its Affiliates.
+
+"Software" means Stability AI’s proprietary software made available under this Agreement now or in the future.
+
+“Stability AI Materials” means, collectively, Stability’s proprietary Models, Software and Documentation (and any portion or combination thereof) made available under this Agreement. 
+
+“Trade Control Laws” means any applicable U.S. and non-U.S. export control and trade sanctions laws and regulations.

NOTICE.txt

@@ -0,0 +1,9 @@
+This Stability AI Model is licensed under the Stability AI Community License, Copyright ©  Stability AI Ltd. All Rights Reserved
+
+Modifications in the Refocus Any Video model bundle:
+- VDD LoRA adapters adapt Stable Video Diffusion for video defocus deblurring.
+- VBR LoRA adapters and a learned, extended UNet input convolution condition the model on RGB video and a depth/focal-plane defocus map for video bokeh rendering.
+- Identity Adapter weights add ArcFace/FaRL reference-face projections, keypoint encoding, and identity-conditioned attention; the Track4Gen variant additionally supplies refiner weights.
+The complete Stable Video Diffusion base-model weights are not included in this bundle and must be obtained separately from their provider.
+
+The included MTCNN pnet/rnet/onet weights are from facenet-pytorch; its MIT license and copyright notice are retained in facenet/LICENSE.md. This MTCNN attribution applies to those detector weights, separately from the SVD-derived adapters.

README.md

@@ -1,5 +1,149 @@
 ---
+library_name: diffusers
+base_model: stabilityai/stable-video-diffusion-img2vid
+tags:
+- video-restoration
+- video-refocusing
+- video-diffusion
+- lora
+model-index: []
 license: other
 license_name: stable-video-diffusion-community
-license_link: LICENSE
+license_link: https://huggingface.co/nickchiu/Refocusing-Any-Video/blob/main/LICENSE-SVD.txt
 ---
+
+# Refocus Any Video: inference checkpoints
+
+Powered by Stability AI.
+
+Model bundle for Refocusing Any Video (RAV). Video Defocus Deblurring (VDD) recovers an all-in-focus video from an out-of-focus input; Video Bokeh Rendering (VBR) renders a target focal plane using the recovered video and a depth sequence. Optional Identity Adapter and Track4Gen Refiner variants condition VDD on reference faces.
+
+Use these weights with the accompanying Refocus Any Video source implementation and its README. This bundle contains adapters and a learned input convolution; it is not a standalone Diffusers pipeline and does not include the Stable Video Diffusion base model.
+
+## Included files
+
+The repository root maps directly to the source repository's `checkpoints/` directory:
+
+```text
+vdd_weights/checkpoint-90000/
+  unet_lora/adapter_config.json
+  unet_lora/adapter_model.safetensors
+vbr_weights/checkpoint-100000/
+  unet_lora/adapter_config.json
+  unet_lora/adapter_model.safetensors
+  unet_conv_in_refocus.pt
+identity_adapter/ip_adapter.bin
+identity_adapter_track4gen/ip_adapter.bin
+facenet/
+  pnet.pt
+  rnet.pt
+  onet.pt
+  LICENSE.md
+README.md
+LICENSE-SVD.txt
+NOTICE.txt
+bundle_manifest.json
+```
+
+| Component | Purpose and checkpoint provenance |
+| --- | --- |
+| VDD LoRA | SVD UNet adapters from the supplied `checkpoint-90000` directory. |
+| VBR LoRA and input convolution | Adapters and learned 12-channel input convolution from the supplied `checkpoint-100000` directory. Both files are required for VBR. |
+| Identity Adapter | Copied from the supplied identity experiment's `checkpoint-5000/ip_adapter.bin`. Use with `infer_vdd_identity.sh`. |
+| Identity Adapter + Track4Gen Refiner | Copied from the supplied Track4Gen experiment's `checkpoint-25000/ip_adapter.bin`. Use with `infer_vdd_identity_track4gen.sh`. |
+| MTCNN | Third-party `pnet`, `rnet`, and `onet` detector weights from the implementation's vendored facenet-pytorch assets. The upstream MIT license is retained in `facenet/LICENSE.md`. |
+
+The VDD and VBR PEFT configurations both specify LoRA rank 32 and alpha 32. VDD also adapts `conv_in`; VBR saves its expanded input convolution separately from its LoRA. The identity variants load on top of the VDD checkpoint, rather than replacing it.
+
+Checkpoint step numbers above are the source directory labels. They do not independently establish dataset size, number of epochs, or training duration. Optimizer, scheduler, and random-state snapshots and large full-UNet experiment snapshots are excluded; this is an inference release rather than an exact training-resume bundle. `bundle_manifest.json` records repository-relative file paths, sizes, and SHA-256 checksums for the distributed assets.
+
+## Download
+
+From the source repository root, install and activate the environment described in its README, then run:
+
+```bash
+python tools/checkpoints/transfer_checkpoints.py download \
+  --repo-id nickchiu/Refocusing-Any-Video --local-dir ./checkpoints
+```
+
+Alternatively, download with the Hugging Face Python client:
+
+```python
+from huggingface_hub import snapshot_download
+
+snapshot_download(repo_id="nickchiu/Refocusing-Any-Video", local_dir="./checkpoints")
+```
+
+The download writes `checkpoints/vdd_weights/`, `checkpoints/vbr_weights/`, and the other folders shown above.
+
+## Base and auxiliary models
+
+Obtain these models separately from their providers. Their weights and licenses are separate from the authors' RAV assets.
+
+| Model | Source | Local path from source repository root |
+| --- | --- | --- |
+| Stable Video Diffusion, 14-frame img2vid | [stabilityai/stable-video-diffusion-img2vid](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid) | `checkpoints/svdh/` |
+| Video Depth Anything, relative-depth Large | [Video Depth Anything](https://github.com/DepthAnything/Video-Depth-Anything) | `checkpoints/video_depth_anything_vitl.pth` |
+| FaRL ViT-B/16, ep16 | [FaRL pretrained backbones](https://github.com/FacePerceiver/FaRL#pre-trained-backbones) | `checkpoints/farl/FaRL-Base-Patch16-LAIONFace20M-ep16.pth` |
+| ArcFace IR-SE50 | [pSp pretrained-model instructions](https://github.com/eladrich/pixel2style2pixel#pretrained-models) | `checkpoints/arcface/model_ir_se50.pth` |
+| OpenAI CLIP ViT-B/16 | [OpenAI CLIP](https://github.com/openai/CLIP) | Downloaded into the CLIP cache by `clip.load("ViT-B/16")` for FaRL initialization. |
+
+The provided `python tools/checkpoints/download_svd_weights.py` helper downloads SVD to `checkpoints/svdh/`. Retain the SVD VAE and UNet `fp16` weight variants: the inference loaders request these files even when inference precision is changed. Follow each provider's authentication/access instructions when required.
+
+The shared VDD wrapper constructs ArcFace, FaRL, and MTCNN even when identity conditioning is disabled, so baseline VDD also requires these auxiliary models and the CLIP cache. Optional keypoint preprocessing, facial landmark extraction, and training/data generation have additional external model requirements documented in the code repository; these are not needed for the basic VDD → VBR example below.
+
+## Inference
+
+Run from the source repository root after completing the environment and all checkpoint setup. Put the input video at `inputs/input.mp4`.
+
+```bash
+mkdir -p inputs results
+
+# Estimate depth from the input video.
+python VideoDepthAnything/infer_video_depth.py \
+  --input ./inputs/input.mp4 --output ./inputs/depth.mp4 \
+  --checkpoint ./checkpoints/video_depth_anything_vitl.pth \
+  --encoder vitl --device cuda
+
+# Recover an all-in-focus video.
+INPUT_VIDEO=./inputs/input.mp4 \
+CHECKPOINT=./checkpoints/vdd_weights/checkpoint-90000 \
+OUTPUT_DIR=./results/vdd OUTPUT_FPS=24 FP16=1 \
+  bash infer_vdd.sh
+
+# Render a focal plane using the all-in-focus video and depth.
+INPUT_VIDEO=./results/vdd/output.mp4 DEPTH_INPUT=./inputs/depth.mp4 \
+CHECKPOINT=./checkpoints/vbr_weights/checkpoint-100000 \
+FOCAL_PLANE=0.5 COC=27 OUTPUT_DIR=./results/vbr OUTPUT_FPS=24 FP16=1 \
+  bash infer_vbr_defocus_map.sh
+```
+
+The final video is `results/vbr/output.mp4`. Keep RGB and depth frame counts, order, and framing aligned. `FOCAL_PLANE` uses normalized disparity in `[0, 1]`, with larger values focusing nearer. `COC` controls the defocus scale. The launchers save at the requested integer playback FPS without resampling and do not preserve audio. See the source README for environment setup, dry runs, time-varying focal planes, resolution controls, and troubleshooting.
+
+For optional identity-guided VDD, provide a clear reference face image and select the matching adapter:
+
+```bash
+MODE=single INPUT_VIDEO=./inputs/input.mp4 \
+REFERENCE_IMAGE=./inputs/reference_face.jpg KEYPOINT_VIDEO="" \
+IP_ADAPTER_PATH=./checkpoints/identity_adapter/ip_adapter.bin \
+HEIGHT="" WIDTH="" OUTPUT_DIR=./results/vdd_identity \
+OUTPUT_FPS=24 FP16=1 bash infer_vdd_identity.sh
+```
+
+For Track4Gen, use `infer_vdd_identity_track4gen.sh` and `IP_ADAPTER_PATH=./checkpoints/identity_adapter_track4gen/ip_adapter.bin`. Both use `checkpoints/vdd_weights/checkpoint-90000` by default. Missing adapter files can cause the current implementation to continue with initialized weights; supply the matching trained file for meaningful results.
+
+## Training and evaluation information
+
+The source distribution includes training runners, historical experiment configuration templates, losses, renderers, and dataset split identifiers. This release does not provide an independently verified, checkpoint-specific training-data description, complete training logs, or benchmark metrics. No quantitative performance claims are made here.
+
+The release preparation checked file inventory and source hashes, adapter configuration and stored tensor keys/headers, Python/shell syntax, and transfer previews. A full GPU end-to-end inference or training run was not performed during release preparation. These checks do not establish reconstruction quality, temporal consistency, or identity fidelity.
+
+## Intended use and limitations
+
+Use the implementation to explore video defocus deblurring, depth-guided refocusing, and reference-conditioned face restoration. Recovered details are model predictions and may differ from the original scene or identity. Depth errors, severe blur, motion, occlusions, or mismatched references can affect results. Hardware requirements and usable resolution depend on the input and available GPU memory; no measured minimum-memory guarantee is provided.
+
+## Licensing and third-party attribution
+
+No additional license for the authors' project-specific model weights was supplied in the source material; this card does not assign one. Stable Video Diffusion and any applicable derivatives remain subject to the base model's terms. The base SVD weights are downloaded separately from the provider. Refer to the retained `LICENSE-SVD.txt`, `NOTICE.txt`, and the provider's model page.
+
+MTCNN assets are redistributed with their upstream MIT notice, copyright © 2019 Timothy Esler, in `facenet/LICENSE.md`; that notice applies to those assets rather than to the complete RAV bundle. Other auxiliary models are obtained separately under their respective providers' terms.

bundle_manifest.json

@@ -0,0 +1,56 @@
+{
+  "format_version": 1,
+  "base_model": "stabilityai/stable-video-diffusion-img2vid",
+  "artifacts": [
+    {
+      "path": "vdd_weights/checkpoint-90000/unet_lora/adapter_config.json",
+      "bytes": 971,
+      "sha256": "b20b517bf96d33ffb045e6fa688d30f58770514af16e74e982ed6a59d02a7e55"
+    },
+    {
+      "path": "vdd_weights/checkpoint-90000/unet_lora/adapter_model.safetensors",
+      "bytes": 98000712,
+      "sha256": "c9b724f49648973a8228224939bb9191adb35320bceed1b07063948a5dfcecbc"
+    },
+    {
+      "path": "vbr_weights/checkpoint-100000/unet_lora/adapter_config.json",
+      "bytes": 933,
+      "sha256": "fa9d650f3b9c81a2a5e44bf73a0ec0c8f11b47bdf91850cdbc597d1127ee1bfa"
+    },
+    {
+      "path": "vbr_weights/checkpoint-100000/unet_lora/adapter_model.safetensors",
+      "bytes": 97950320,
+      "sha256": "df3a2e7b3bcd8b57fa556d8dd73942982814f939406316eafe15c740b56bbc9e"
+    },
+    {
+      "path": "vbr_weights/checkpoint-100000/unet_conv_in_refocus.pt",
+      "bytes": 141581,
+      "sha256": "bee1c87dd015f040439db7a8f9356005bad633af6ccf5e845194736cc886cb42"
+    },
+    {
+      "path": "identity_adapter/ip_adapter.bin",
+      "bytes": 320049019,
+      "sha256": "f20ec5a9c8a43c0ae3929fb74cad2388c3039121c88bc89e7356189cde6ae7f2"
+    },
+    {
+      "path": "identity_adapter_track4gen/ip_adapter.bin",
+      "bytes": 439764592,
+      "sha256": "d95e76b4367cad505f5742450cc46b12a99b4a9f42a654db8c553b2f7b5b188f"
+    },
+    {
+      "path": "facenet/pnet.pt",
+      "bytes": 28570,
+      "sha256": "a2a71925e0b9996a42f63e47efc1ca19043e69558b5c523b978d611dfae49c8f"
+    },
+    {
+      "path": "facenet/rnet.pt",
+      "bytes": 403147,
+      "sha256": "bbb937de72efc9ef83b186c49f5f558467a1d7e3453a8ece0d71a886633f6a86"
+    },
+    {
+      "path": "facenet/onet.pt",
+      "bytes": 1559269,
+      "sha256": "165bfbe42940416ccfb977545cf0e976d5bf321f67083ae2aaaa5c764280118d"
+    }
+  ]
+}

facenet/LICENSE.md

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2019 Timothy Esler
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

facenet/onet.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165bfbe42940416ccfb977545cf0e976d5bf321f67083ae2aaaa5c764280118d
+size 1559269

facenet/pnet.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a71925e0b9996a42f63e47efc1ca19043e69558b5c523b978d611dfae49c8f
+size 28570

facenet/rnet.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbb937de72efc9ef83b186c49f5f558467a1d7e3453a8ece0d71a886633f6a86
+size 403147

identity_adapter/ip_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f20ec5a9c8a43c0ae3929fb74cad2388c3039121c88bc89e7356189cde6ae7f2
+size 320049019

identity_adapter_track4gen/ip_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d95e76b4367cad505f5742450cc46b12a99b4a9f42a654db8c553b2f7b5b188f
+size 439764592

vbr_weights/checkpoint-100000/unet_conv_in_refocus.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bee1c87dd015f040439db7a8f9356005bad633af6ccf5e845194736cc886cb42
+size 141581

vbr_weights/checkpoint-100000/unet_lora/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "UNetSpatioTemporalConditionModel",
+    "parent_library": "unet_spatio_temporal_condition"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "to_out.0",
+    "ff.net.2",
+    "to_k",
+    "to_q",
+    "ff.net.0.proj",
+    "to_v"
+  ],
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

vbr_weights/checkpoint-100000/unet_lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df3a2e7b3bcd8b57fa556d8dd73942982814f939406316eafe15c740b56bbc9e
+size 97950320

vdd_weights/checkpoint-90000/unet_lora/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "UNetSpatioTemporalConditionModel",
+    "parent_library": "diffusers.models.unets.unet_spatio_temporal_condition"
+  },
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "to_out.0",
+    "to_v",
+    "conv_in",
+    "to_k",
+    "to_q",
+    "ff.net.0.proj",
+    "ff.net.2"
+  ],
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

vdd_weights/checkpoint-90000/unet_lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b724f49648973a8228224939bb9191adb35320bceed1b07063948a5dfcecbc
+size 98000712