Add inference checkpoint, portable metadata and component licenses

.gitattributes

@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 qwenimage21/processor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/fonts/DejaVuSans.ttf filter=lfs diff=lfs merge=lfs -text
+qwenimage21/assets/qr.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,79 @@
+---
+license: other
+license_name: component-specific-research-licenses
+license_link: https://huggingface.co/greyDonald/HumanAwareDesignGeneration/blob/main/THIRD_PARTY_NOTICES.md
+tags:
+- graphic-design
+- human-pose
+- smplx
+- qwen-image
+- image-to-image
+pipeline_tag: image-to-image
+language:
+- en
+---
+
+# Human-aware Design Generation — model resources
+
+Resources for **Human-aware Design Generation: Adding 3D Humans into Graphic Designs**, Zijin Hou and Ying Cao, ACM Multimedia 2026.
+
+[Paper](https://arxiv.org/abs/2609.17689) · [Code](https://github.com/GreyNails/HumanAwareDesignGeneration) · [Project page](https://greynails.github.io/HumanAwareDesignGeneration/)
+
+**Built with Qwen.** The default final renderer is native RGBA **Qwen Image 2.1**, conditioned on a predicted mannequin for pose and the non-human input design for appearance. This is a resource bundle for the released implementation, not a claim that the optional Qwen/SDXL extensions were the original paper's architecture.
+
+## Contents
+
+| Directory | Purpose |
+| --- | --- |
+| `humanaware/` | Trained layout and human decoders; inference-only checkpoint with portable configuration |
+| `flexdm/` | Frozen design encoder and structured-input vocabulary metadata |
+| `pose/` | Pose-token VQ-VAE decoder |
+| `assets/camera/` | Quantized camera centers |
+| `assets/fonts/` | Rendering font and its permission notice |
+| `qwenimage21/` | Native Qwen Image 2.1 transformer, text encoder, RGBA VAE, processor, scheduler and tokenizers |
+| `pose_diffusion/` | Optional SDXL, IP-Adapter, image encoder, VAE and LayerDiffuse resources |
+
+`manifest.json` records relative paths, file sizes, SHA-256 checksums and public-upload eligibility. Model parameters are copied unchanged; the HumanAware checkpoint export omits training history and rewrites resource paths without changing tensors. No training dataset, validation dataset, test examples or inference results are stored here.
+
+## Use
+
+Install the two Python environments described in the code README. From the code repository, download resources into the sibling `../weight` directory:
+
+```bash
+python scripts/download_weights.py --weights-dir ../weight
+# After separately installing your licensed SMPL-X model:
+python scripts/run_demo.py --weights-dir ../weight --render-gt
+```
+
+The default download includes the core model and Qwen. Pass `--include-sdxl` for optional SDXL resources, or `--revision <commit>` for a fixed release. Code and project-page publication are subject to the repository owner's final review; this model upload does not itself publish the code.
+
+## Separately obtained resources
+
+Two resources are deliberately **not redistributed in this public repository**:
+
+- `assets/body_models/smplx/SMPLX_NEUTRAL.npz`: obtain directly from the [official SMPL-X provider](https://smpl-x.is.tue.mpg.de/) under its [model license](https://smpl-x.is.tue.mpg.de/modellicense.html). Use the code's `scripts/install_smplx.py` to install your copy. It is required for white-model rendering and the default complete pipeline.
+- `pose_diffusion/controlnet/{config.json,diffusion_pytorch_model.safetensors}`: the optional [SDXL OpenPose ControlNet](https://huggingface.co/thibaud/controlnet-openpose-sdxl-1.0) refers to the restrictive [OpenPose license](https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/LICENSE). Obtain it from the original provider under applicable terms if using SDXL. The default Qwen pipeline does not use ControlNet.
+
+The owner's local resource bundle contains these files for authorized local use. Their entries and hashes remain in the manifest with `public_upload: false` so missing public downloads are explicit.
+
+## Licenses and attribution
+
+This is a mixed-license resource bundle. See [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md), `model_sources.json`, and the individual license texts. In particular, **Qwen Image 2.1 is licensed under the Qwen RESEARCH LICENSE AGREEMENT (September 20, 2026), for non-commercial use subject to its terms**. SDXL and LayerDiffuse weights have their own OpenRAIL terms; permissive code or conversion licenses do not replace upstream model restrictions. No blanket license is granted to all bundled components.
+
+Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved.
+
+## Validation and limitations
+
+The released core resources were checked through independent structured-input inference, white-model rendering and GT comparison on three original demonstration cases. Native Qwen RGBA rendering uses two image references, BF16, CPU offloading, 40 steps and no VAE tiling on an NVIDIA L40. Generated people can vary in pose detail, hand fidelity and clothing appearance; inspect results for your use case. GT is used for post-generation comparison only.
+
+## Citation
+
+```bibtex
+@inproceedings{hou2026humanaware,
+title     = {Human-aware Design Generation: Adding 3D Humans into Graphic Designs},
+author    = {Hou, Zijin and Cao, Ying},
+booktitle = {Proceedings of the 34th ACM International Conference on Multimedia},
+year      = {2026},
+doi       = {10.1145/3767308.3836019}
+}
+```

THIRD_PARTY_NOTICES.md

@@ -0,0 +1,26 @@
+# Third-party notices
+
+This release combines separately licensed source code, user-provided research checkpoints, model resources and demonstration materials. No single license is asserted over all of them. Preserve upstream licenses and follow the terms applicable to each component.
+
+| Component | Source and terms |
+| --- | --- |
+| FlexDM encoder source | [CyberAgentAILab/flex-dm](https://github.com/CyberAgentAILab/flex-dm), Apache License 2.0. The license is retained at `vendor/flexdm/LICENSE`. The supplied encoder checkpoint was extracted from the project's locally trained FlexDM model; provenance is recorded in `vendor/flexdm/provenance.json`. |
+| Pose token decoder | User-provided original project's VQ-VAE source and `52joints_tokenization.pth`. Source provenance is in `vendor/render/PROVENANCE.json`; no new blanket license is assigned to that checkpoint. |
+| Rotation utilities | Meta PyTorch3D, BSD-style license; retain the copyright header and accompanying `vendor/render/LICENSE.pytorch3d`. |
+| LayerDiffuse source | [rootonchair/diffusers-LayerDiffuse](https://github.com/rootonchair/diffusers-LayerDiffuse), based on [lllyasviel/LayerDiffuse](https://github.com/lllyasviel/LayerDiffuse). The upstream source license is retained in `vendor/pose_renderer/`. Model weights have separate terms. |
+| Qwen Image 2.1 | [Qwen/Qwen-Image-2.1](https://huggingface.co/Qwen/Qwen-Image-2.1). **Qwen RESEARCH LICENSE AGREEMENT**, September 20, 2026; non-commercial use subject to its terms. Full `LICENSE` and `NOTICE` are retained with the model resources. **Built with Qwen.** |
+| SMPL-X body model | [Official SMPL-X model license](https://smpl-x.is.tue.mpg.de/modellicense.html). Obtain an authorized copy directly from the provider. The public resource repository does not redistribute it. |
+| SDXL base (optional) | [stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0), CreativeML Open RAIL++-M. |
+| SDXL OpenPose ControlNet (optional) | [thibaud/controlnet-openpose-sdxl-1.0](https://huggingface.co/thibaud/controlnet-openpose-sdxl-1.0); the model card refers to the [OpenPose license](https://github.com/CMU-Perceptual-Computing-Lab/openpose/blob/master/LICENSE). That license restricts redistribution. The checkpoint is excluded from this public resource mirror; obtain it from its provider under the applicable terms. |
+| IP-Adapter (optional) | [h94/IP-Adapter](https://huggingface.co/h94/IP-Adapter), Apache License 2.0. Its CLIP ViT-H image encoder matches [laion/CLIP-ViT-H-14-laion2B-s32B-b79K](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K), MIT. |
+| SDXL fp16 VAE fix (optional) | [madebyollin/sdxl-vae-fp16-fix](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix), model-card license MIT; preserve upstream attribution and applicable base-model terms. |
+| LayerDiffuse weights (optional) | Original [LayerDiffusion](https://huggingface.co/LayerDiffusion/layerdiffusion) weights declare CreativeML Open RAIL-M. The [rootonchair conversion](https://huggingface.co/rootonchair/diffuser_layerdiffuse) declares MIT; conversion metadata does not replace original model terms. |
+| DejaVu font | Bitstream Vera permission notice, with DejaVu changes in the public domain. The font and notice are stored under `weight/assets/fonts/`. |
+
+The public weight bundle retains component-specific license texts and a source/license inventory. SMPL-X and the OpenPose ControlNet remain available only in the owner's local resource directory unless separate redistribution rights are established. Other downloaded packages retain their own licenses; see their distributions.
+
+Original example design elements and paper figures are included for demonstration and research. Their inclusion does not grant a new blanket license to the underlying artwork, imagery, fonts or depicted material. The project README and page display only original paper figures, not development inference results.
+
+Required Qwen notice:
+
+> Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved.

assets/camera/camera_centers.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f08c905c7461f86efeead881d4ba35d3d3bc7f7d8e9c4301894290efeaceb20
+size 3796

assets/fonts/DejaVuSans.ttf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:437a5ecec2ec177cba9284cbffc56055311347f3e9fe4f2b4b40323d0290a6db
+size 757076

assets/fonts/LICENSE-DejaVu.txt

@@ -0,0 +1,52 @@
+Format: http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
+Upstream-Name: DejaVu fonts
+Upstream-Author: Stepan Roh <src@users.sourceforge.net> (original author),
+                  see /usr/share/doc/ttf-dejavu/AUTHORS for full list
+Source: http://dejavu-fonts.org/
+
+Files: *
+Copyright: Copyright (c) 2003 by Bitstream, Inc. All Rights Reserved. 
+ Bitstream Vera is a trademark of Bitstream, Inc.
+ DejaVu changes are in public domain.
+License: bitstream-vera
+ Permission is hereby granted, free of charge, to any person obtaining a copy
+ of the fonts accompanying this license ("Fonts") and associated
+ documentation files (the "Font Software"), to reproduce and distribute the
+ Font Software, including without limitation the rights to use, copy, merge,
+ publish, distribute, and/or sell copies of the Font Software, and to permit
+ persons to whom the Font Software is furnished to do so, subject to the
+ following conditions:
+ .
+ The above copyright and trademark notices and this permission notice shall
+ be included in all copies of one or more of the Font Software typefaces.
+ .
+ The Font Software may be modified, altered, or added to, and in particular
+ the designs of glyphs or characters in the Fonts may be modified and
+ additional glyphs or characters may be added to the Fonts, only if the fonts
+ are renamed to names not containing either the words "Bitstream" or the word
+ "Vera".
+ .
+ This License becomes null and void to the extent applicable to Fonts or Font
+ Software that has been modified and is distributed under the "Bitstream
+ Vera" names.
+ .
+ The Font Software may be sold as part of a larger software package but no
+ copy of one or more of the Font Software typefaces may be sold by itself.
+ .
+ THE FONT SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTIES OF MERCHANTABILITY,
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF COPYRIGHT, PATENT,
+ TRADEMARK, OR OTHER RIGHT. IN NO EVENT SHALL BITSTREAM OR THE GNOME
+ FOUNDATION BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, INCLUDING
+ ANY GENERAL, SPECIAL, INDIRECT, INCIDENTAL, OR CONSEQUENTIAL DAMAGES,
+ WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF
+ THE USE OR INABILITY TO USE THE FONT SOFTWARE OR FROM OTHER DEALINGS IN THE
+ FONT SOFTWARE.
+ .
+ Except as contained in this notice, the names of Gnome, the Gnome
+ Foundation, and Bitstream Inc., shall not be used in advertising or
+ otherwise to promote the sale, use or other dealings in this Font Software
+ without prior written authorization from the Gnome Foundation or Bitstream
+ Inc., respectively. For further information, contact: fonts at gnome dot
+ org.
+

flexdm/design_encoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75c3dab8a1f5e4f9dd7b6fb8c43f82a4ec11143545329e9937e291a58fc5e01
+size 9859050

flexdm/metadata.json

@@ -0,0 +1,443 @@
+{
+  "columns": {
+    "type": {
+      "type": "categorical",
+      "input_dim": 6,
+      "shape": [
+        1
+      ],
+      "is_sequence": true,
+      "primary_label": 0
+    },
+    "left": {
+      "type": "categorical",
+      "input_dim": 64,
+      "shape": [
+        1
+      ],
+      "is_sequence": true,
+      "primary_label": null
+    },
+    "top": {
+      "type": "categorical",
+      "input_dim": 64,
+      "shape": [
+        1
+      ],
+      "is_sequence": true,
+      "primary_label": null
+    },
+    "width": {
+      "type": "categorical",
+      "input_dim": 64,
+      "shape": [
+        1
+      ],
+      "is_sequence": true,
+      "primary_label": null
+    },
+    "height": {
+      "type": "categorical",
+      "input_dim": 64,
+      "shape": [
+        1
+      ],
+      "is_sequence": true,
+      "primary_label": null
+    },
+    "opacity": {
+      "type": "categorical",
+      "input_dim": 8,
+      "shape": [
+        1
+      ],
+      "is_sequence": true,
+      "primary_label": null
+    },
+    "color": {
+      "type": "categorical",
+      "input_dim": 16,
+      "shape": [
+        3
+      ],
+      "is_sequence": true,
+      "primary_label": null,
+      "loss_condition": {
+        "key": "type",
+        "mask": [
+          false,
+          false,
+          true,
+          false,
+          true,
+          false
+        ]
+      }
+    },
+    "image_embedding": {
+      "type": "numerical",
+      "shape": [
+        512
+      ],
+      "is_sequence": true,
+      "primary_label": null,
+      "loss_condition": {
+        "key": "type",
+        "mask": [
+          false,
+          true,
+          false,
+          true,
+          false,
+          true
+        ]
+      }
+    },
+    "text_embedding": {
+      "type": "numerical",
+      "shape": [
+        512
+      ],
+      "is_sequence": true,
+      "primary_label": null,
+      "loss_condition": {
+        "key": "type",
+        "mask": [
+          false,
+          false,
+          true,
+          false,
+          false,
+          false
+        ]
+      }
+    },
+    "font_family": {
+      "type": "categorical",
+      "input_dim": 35,
+      "shape": [
+        1
+      ],
+      "is_sequence": true,
+      "primary_label": null,
+      "loss_condition": {
+        "key": "type",
+        "mask": [
+          false,
+          false,
+          true,
+          false,
+          false,
+          false
+        ]
+      }
+    }
+  },
+  "vocabularies": {
+    "length": [
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11,
+      12,
+      13,
+      14,
+      15,
+      16,
+      17,
+      18,
+      19,
+      20,
+      21,
+      22,
+      23,
+      24,
+      25,
+      26,
+      27,
+      28,
+      29,
+      30,
+      31,
+      32,
+      33,
+      34,
+      35,
+      36,
+      37,
+      38,
+      39,
+      40,
+      41,
+      42,
+      43,
+      44,
+      45,
+      46,
+      47,
+      48,
+      49,
+      50
+    ],
+    "group": [
+      "",
+      "[UNK]",
+      "SM",
+      "HC",
+      "MM",
+      "SMA",
+      "EO",
+      "BG"
+    ],
+    "format": [
+      "",
+      "[UNK]",
+      "Instagram Story",
+      "Instagram",
+      "Facebook",
+      "Facebook cover",
+      "Twitter",
+      "Facebook AD",
+      "Poster",
+      "Instagram AD",
+      "Tumblr",
+      "Image",
+      "Pinterest",
+      "Flayer",
+      "FB event cover",
+      "Postcard",
+      "Invitation",
+      "Youtube",
+      "Email header",
+      "Medium Rectangle",
+      "Poster US",
+      "Graphic",
+      "Large Rectangle",
+      "Card",
+      "Logo",
+      "Title",
+      "Skyscraper",
+      "Leaderboard",
+      "Presentation",
+      "Gift Certificate",
+      "Youtube Thumbnail",
+      "Business card",
+      "VK Universal Post",
+      "Book Cover",
+      "Presentation Wide",
+      "VK Community Cover",
+      "Certificate",
+      "Zoom Background",
+      "VK Post with Button",
+      "T-Shirt",
+      "Instagram Highlight Cover",
+      "Coupon",
+      "IGTV Cover",
+      "Album Cover",
+      "Invoice",
+      "Storyboard",
+      "Schedule Planner",
+      "Mood Board",
+      "Menu",
+      "Mind Map",
+      "Label",
+      "LinkedIn Cover",
+      "Recipe Card",
+      "Resume",
+      "Ticket",
+      "Brochure",
+      "Proposal",
+      "Snapchat Geofilter",
+      "Twitch Offline Banner",
+      "Snapchat Moment Filter",
+      "Twitch Profile Banner",
+      "Newsletter",
+      "Infographic",
+      "Mobile Presentation",
+      "Photo Book",
+      "Web Banner",
+      "Gallery Image",
+      "Letterhead",
+      "Calendar"
+    ],
+    "canvas_width": [
+      -1,
+      1080,
+      1200,
+      940,
+      851,
+      360,
+      1920,
+      1190,
+      419,
+      600,
+      1024,
+      1600,
+      735,
+      2560,
+      3000,
+      1500,
+      300,
+      540,
+      1296,
+      336,
+      500,
+      595,
+      432,
+      560,
+      160,
+      1280,
+      728,
+      241,
+      1000,
+      1590,
+      792,
+      576,
+      537,
+      1008,
+      420,
+      1128,
+      396,
+      841,
+      800,
+      240,
+      635,
+      842
+    ],
+    "canvas_height": [
+      -1,
+      1080,
+      1920,
+      315,
+      788,
+      628,
+      600,
+      504,
+      1683,
+      298,
+      500,
+      512,
+      1102,
+      1440,
+      200,
+      400,
+      250,
+      810,
+      1728,
+      1200,
+      280,
+      288,
+      90,
+      1055,
+      720,
+      768,
+      841,
+      142,
+      700,
+      612,
+      2560,
+      2000,
+      240,
+      216,
+      842,
+      1296,
+      2340,
+      654,
+      1600,
+      191,
+      297,
+      595,
+      480,
+      576,
+      320,
+      141,
+      380
+    ],
+    "category": [
+      "",
+      "[UNK]",
+      "holidaysCelebration",
+      "foodDrinks",
+      "fashionStyle",
+      "homeStuff",
+      "handcraftArt",
+      "businessFinance",
+      "beauty",
+      "leisureEntertainment",
+      "natureWildlife",
+      "educationScience",
+      "technology",
+      "medical",
+      "sportExtreme",
+      "realEstateBuilding",
+      "socialActivityCharity",
+      "travelsVacations",
+      "pets",
+      "religions",
+      "citiesPlaces",
+      "industry",
+      "transportation",
+      "kidsParents",
+      "all"
+    ],
+    "type": [
+      "",
+      "svgElement",
+      "textElement",
+      "imageElement",
+      "coloredBackground",
+      "maskElement"
+    ],
+    "font_family": [
+      "[UNK]",
+      "DummyFont",
+      "Montserrat",
+      "Bebas Neue",
+      "Raleway",
+      "Josefin Sans",
+      "Playfair Display",
+      "Oswald",
+      "Cantarell",
+      "Abril Fatface",
+      "Prompt",
+      "Blogger",
+      "Comfortaa",
+      "Rubik",
+      "Open Sans",
+      "Roboto",
+      "Libre Baskerville",
+      "Dosis",
+      "Quicksand",
+      "Podkova",
+      "Lato",
+      "Cormorant Infant",
+      "Amatic SC",
+      "Fjalla One",
+      "Arapey",
+      "Playlist Script",
+      "Baloo Tamma",
+      "Graduate",
+      "Kreon",
+      "Titillium Web",
+      "Nunito",
+      "Rammetto One",
+      "Anton",
+      "Poiret One",
+      "Alfa Slab One"
+    ]
+  },
+  "splits": {
+    "train": 18587,
+    "val": 2292,
+    "test": 2248
+  },
+  "zero_based_length": true,
+  "tensorflow_export_version": "2.11.0"
+}

humanaware/final.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64082b9a9a7273977679d6456c9f08ffefbe5a19bdeffef513c10566286e207c
+size 137593522

licenses/CreativeML_Open_RAIL_M_reference_LICENSE.txt

@@ -0,0 +1,82 @@
+Copyright (c) 2022 Robin Rombach and Patrick Esser and contributors
+
+CreativeML Open RAIL-M
+dated August 22, 2022
+
+Section I: PREAMBLE
+
+Multimodal generative models are being widely adopted and used, and have the potential to transform the way artists, among other individuals, conceive and benefit from AI or ML technologies as a tool for content creation.
+
+Notwithstanding the current and potential benefits that these artifacts can bring to society at large, there are also concerns about potential misuses of them, either due to their technical limitations or ethical considerations.
+
+In short, this license strives for both the open and responsible downstream use of the accompanying model. When it comes to the open character, we took inspiration from open source permissive licenses regarding the grant of IP rights. Referring to the downstream responsible use, we added use-based restrictions not permitting the use of the Model in very specific scenarios, in order for the licensor to be able to enforce the license in case potential misuses of the Model may occur. At the same time, we strive to promote open and responsible research on generative models for art and content generation.
+
+Even though downstream derivative versions of the model could be released under different licensing terms, the latter will always have to include - at minimum - the same use-based restrictions as the ones in the original license (this license). We believe in the intersection between open and responsible AI development; thus, this License aims to strike a balance between both in order to enable responsible open-science in the field of AI.
+
+This License governs the use of the model (and its derivatives) and is informed by the model card associated with the model.
+
+NOW THEREFORE, You and Licensor agree as follows:
+
+1. Definitions
+
+- "License" means the terms and conditions for use, reproduction, and Distribution as defined in this document.
+- "Data" means a collection of information and/or content extracted from the dataset used with the Model, including to train, pretrain, or otherwise evaluate the Model. The Data is not licensed under this License.
+- "Output" means the results of operating a Model as embodied in informational content resulting therefrom.
+- "Model" means any accompanying machine-learning based assemblies (including checkpoints), consisting of learnt weights, parameters (including optimizer states), corresponding to the model architecture as embodied in the Complementary Material, that have been trained or tuned, in whole or in part on the Data, using the Complementary Material.
+- "Derivatives of the Model" means all modifications to the Model, works based on the Model, or any other model which is created or initialized by transfer of patterns of the weights, parameters, activations or output of the Model, to the other model, in order to cause the other model to perform similarly to the Model, including - but not limited to - distillation methods entailing the use of intermediate data representations or methods based on the generation of synthetic data by the Model for training the other model.
+- "Complementary Material" means the accompanying source code and scripts used to define, run, load, benchmark or evaluate the Model, and used to prepare data for training or evaluation, if any. This includes any accompanying documentation, tutorials, examples, etc, if any.
+- "Distribution" means any transmission, reproduction, publication or other sharing of the Model or Derivatives of the Model to a third party, including providing the Model as a hosted service made available by electronic or other remote means - e.g. API-based or web access.
+- "Licensor" means the copyright owner or entity authorized by the copyright owner that is granting the License, including the persons or entities that may have rights in the Model and/or distributing the Model.
+- "You" (or "Your") means an individual or Legal Entity exercising permissions granted by this License and/or making use of the Model for whichever purpose and in any field of use, including usage of the Model in an end-use application - e.g. chatbot, translator, image generator.
+- "Third Parties" means individuals or legal entities that are not under common control with Licensor or You.
+- "Contribution" means any work of authorship, including the original version of the Model and any modifications or additions to that Model or Derivatives of the Model thereof, that is intentionally submitted to Licensor for inclusion in the Model 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 Model, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
+- "Contributor" means Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Model.
+
+Section II: INTELLECTUAL PROPERTY RIGHTS
+
+Both copyright and patent grants apply to the Model, Derivatives of the Model and Complementary Material. The Model and Derivatives of the Model are subject to additional terms as described in Section III.
+
+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, publicly display, publicly perform, sublicense, and distribute the Complementary Material, the Model, and Derivatives of the Model.
+3. Grant of Patent License. Subject to the terms and conditions of this License and where and as applicable, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this paragraph) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Model and the Complementary Material, 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 Model 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 Model and/or Complementary Material or a Contribution incorporated within the Model and/or Complementary Material constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for the Model and/or Work shall terminate as of the date such litigation is asserted or filed.
+
+Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
+
+4. Distribution and Redistribution. You may host for Third Party remote access purposes (e.g. software-as-a-service), reproduce and distribute copies of the Model or Derivatives of the Model thereof in any medium, with or without modifications, provided that You meet the following conditions:
+Use-based restrictions as referenced in paragraph 5 MUST be included as an enforceable provision by You in any type of legal agreement (e.g. a license) governing the use and/or distribution of the Model or Derivatives of the Model, and You shall give notice to subsequent users You Distribute to, that the Model or Derivatives of the Model are subject to paragraph 5. This provision does not apply to the use of Complementary Material.
+You must give any Third Party recipients of the Model or Derivatives of the Model a copy of this License;
+You must cause any modified files to carry prominent notices stating that You changed the files;
+You must retain all copyright, patent, trademark, and attribution notices excluding those notices that do not pertain to any part of the Model, Derivatives of the Model.
+You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions - respecting paragraph 4.a. - for use, reproduction, or Distribution of Your modifications, or for any such Derivatives of the Model as a whole, provided Your use, reproduction, and Distribution of the Model otherwise complies with the conditions stated in this License.
+5. Use-based restrictions. The restrictions set forth in Attachment A are considered Use-based restrictions. Therefore You cannot use the Model and the Derivatives of the Model for the specified restricted uses. You may use the Model subject to this License, including only for lawful purposes and in accordance with the License. Use may include creating any content with, finetuning, updating, running, training, evaluating and/or reparametrizing the Model. You shall require all of Your users who use the Model or a Derivative of the Model to comply with the terms of this paragraph (paragraph 5).
+6. The Output You Generate. Except as set forth herein, Licensor claims no rights in the Output You generate using the Model. You are accountable for the Output you generate and its subsequent uses. No use of the output can contravene any provision as stated in the License.
+
+Section IV: OTHER PROVISIONS
+
+7. Updates and Runtime Restrictions. To the maximum extent permitted by law, Licensor reserves the right to restrict (remotely or otherwise) usage of the Model in violation of this License, update the Model through electronic means, or modify the Output of the Model based on updates. You shall undertake reasonable efforts to use the latest version of the Model.
+8. Trademarks and related. Nothing in this License permits You to make use of Licensors’ trademarks, trade names, logos or to otherwise suggest endorsement or misrepresent the relationship between the parties; and any rights not expressly granted herein are reserved by the Licensors.
+9. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Model and the Complementary Material (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 Model, Derivatives of the Model, and the Complementary Material and assume any risks associated with Your exercise of permissions under this License.
+10. 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 Model and the Complementary Material (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.
+11. Accepting Warranty or Additional Liability. While redistributing the Model, Derivatives of the Model and the Complementary Material 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.
+12. If any provision of this License is held to be invalid, illegal or unenforceable, the remaining provisions shall be unaffected thereby and remain valid as if such provision had not been set forth herein.
+
+END OF TERMS AND CONDITIONS
+
+
+
+
+Attachment A
+
+Use Restrictions
+
+You agree not to use the Model or Derivatives of the Model:
+- In any way that violates any applicable national, federal, state, local or international law or regulation;
+- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
+- To generate or disseminate verifiably false information and/or content with the purpose of harming others;
+- To generate or disseminate personal identifiable information that can be used to harm an individual;
+- To defame, disparage or otherwise harass others;
+- For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation;
+- For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;
+- To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;
+- For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories;
+- To provide medical advice and medical results interpretation;
+- To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).

licenses/FlexDM_Apache_2.0_LICENSE.txt

@@ -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 2023 Naoto Inoue
+
+   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.

licenses/IP_Adapter_Apache_2.0_LICENSE.txt

@@ -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.

licenses/LayerDiffuse_conversion_MIT_LICENSE.txt

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Vinh H. Pham 
+
+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.

licenses/LayerDiffusion_original_code_Apache_2.0_LICENSE.txt

@@ -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.

licenses/MIT_template_SPDX_reference.txt

@@ -0,0 +1,18 @@
+MIT License
+
+Copyright (c) <year> <copyright holders>
+
+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.

licenses/OpenCLIP_MIT_LICENSE.txt

@@ -0,0 +1,23 @@
+Copyright (c) 2012-2021 Gabriel Ilharco, Mitchell Wortsman, 
+Nicholas Carlini, Rohan Taori, Achal Dave, Vaishaal Shankar, 
+John Miller, Hongseok Namkoong, Hannaneh Hajishirzi, Ali Farhadi, 
+Ludwig Schmidt
+
+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.

licenses/OpenPose_RESTRICTED_reference_LICENSE.txt

@@ -0,0 +1,108 @@
+OPENPOSE: MULTIPERSON KEYPOINT DETECTION
+SOFTWARE LICENSE AGREEMENT
+ACADEMIC OR NON-PROFIT ORGANIZATION NONCOMMERCIAL RESEARCH USE ONLY
+
+BY USING OR DOWNLOADING THE SOFTWARE, YOU ARE AGREEING TO THE TERMS OF THIS LICENSE AGREEMENT.  IF YOU DO NOT AGREE WITH THESE TERMS, YOU MAY NOT USE OR DOWNLOAD THE SOFTWARE.
+
+This is a license agreement ("Agreement") between your academic institution or non-profit organization or self (called "Licensee" or "You" in this Agreement) and Carnegie Mellon University (called "Licensor" in this Agreement).  All rights not specifically granted to you in this Agreement are reserved for Licensor. 
+
+RESERVATION OF OWNERSHIP AND GRANT OF LICENSE: 
+Licensor retains exclusive ownership of any copy of the Software (as defined below) licensed under this Agreement and hereby grants to Licensee a personal, non-exclusive, 
+non-transferable license to use the Software for noncommercial research purposes, without the right to sublicense, pursuant to the terms and conditions of this Agreement.  As used in this Agreement, the term "Software" means (i) the actual copy of all or any portion of code for program routines made accessible to Licensee by Licensor pursuant to this Agreement, inclusive of backups, updates, and/or merged copies permitted hereunder or subsequently supplied by Licensor,  including all or any file structures, programming instructions, user interfaces and screen formats and sequences as well as any and all documentation and instructions related to it, and (ii) all or any derivatives and/or modifications created or made by You to any of the items specified in (i).
+
+CONFIDENTIALITY: Licensee acknowledges that the Software is proprietary to Licensor, and as such, Licensee agrees to receive all such materials in confidence and use the Software only in accordance with the terms of this Agreement.  Licensee agrees to use reasonable effort to protect the Software from unauthorized use, reproduction, distribution, or publication.
+
+COPYRIGHT: The Software is owned by Licensor and is protected by United 
+States copyright laws and applicable international treaties and/or conventions.
+
+PERMITTED USES:  The Software may be used for your own noncommercial internal research purposes. You understand and agree that Licensor is not obligated to implement any suggestions and/or feedback you might provide regarding the Software, but to the extent Licensor does so, you are not entitled to any compensation related thereto.
+
+DERIVATIVES: You may create derivatives of or make modifications to the Software, however, You agree that all and any such derivatives and modifications will be owned by Licensor and become a part of the Software licensed to You under this Agreement.  You may only use such derivatives and modifications for your own noncommercial internal research purposes, and you may not otherwise use, distribute or copy such derivatives and modifications in violation of this Agreement.
+
+BACKUPS:  If Licensee is an organization, it may make that number of copies of the Software necessary for internal noncommercial use at a single site within its organization provided that all information appearing in or on the original labels, including the copyright and trademark notices are copied onto the labels of the copies.
+
+USES NOT PERMITTED:  You may not distribute, copy or use the Software except as explicitly permitted herein. Licensee has not been granted any trademark license as part of this Agreement and may not use the name or mark “OpenPose", "Carnegie Mellon" or any renditions thereof without the prior written permission of Licensor.
+
+You may not sell, rent, lease, sublicense, lend, time-share or transfer, in whole or in part, or provide third parties access to prior or present versions (or any parts thereof) of the Software.
+
+ASSIGNMENT: You may not assign this Agreement or your rights hereunder without the prior written consent of Licensor. Any attempted assignment without such consent shall be null and void.
+
+TERM: The term of the license granted by this Agreement is from Licensee's acceptance of this Agreement by downloading the Software or by using the Software until terminated as provided below.
+
+The Agreement automatically terminates without notice if you fail to comply with any provision of this Agreement.  Licensee may terminate this Agreement by ceasing using the Software.  Upon any termination of this Agreement, Licensee will delete any and all copies of the Software. You agree that all provisions which operate to protect the proprietary rights of Licensor shall remain in force should breach occur and that the obligation of confidentiality described in this Agreement is binding in perpetuity and, as such, survives the term of the Agreement.
+
+FEE: Provided Licensee abides completely by the terms and conditions of this Agreement, there is no fee due to Licensor for Licensee's use of the Software in accordance with this Agreement.
+
+DISCLAIMER OF WARRANTIES:  THE SOFTWARE IS PROVIDED "AS-IS" WITHOUT WARRANTY OF ANY KIND INCLUDING ANY WARRANTIES OF PERFORMANCE OR MERCHANTABILITY OR FITNESS FOR A PARTICULAR USE OR PURPOSE OR OF NON-INFRINGEMENT.  LICENSEE BEARS ALL RISK RELATING TO QUALITY AND PERFORMANCE OF THE SOFTWARE AND RELATED MATERIALS.
+
+SUPPORT AND MAINTENANCE: No Software support or training by the Licensor is provided as part of this Agreement.  
+
+EXCLUSIVE REMEDY AND LIMITATION OF LIABILITY: To the maximum extent permitted under applicable law, Licensor shall not be liable for direct, indirect, special, incidental, or consequential damages or lost profits related to Licensee's use of and/or inability to use the Software, even if Licensor is advised of the possibility of such damage.
+
+EXPORT REGULATION: Licensee agrees to comply with any and all applicable 
+U.S. export control laws, regulations, and/or other laws related to embargoes and sanction programs administered by the Office of Foreign Assets Control.
+
+SEVERABILITY: If any provision(s) of this Agreement shall be held to be invalid, illegal, or unenforceable by a court or other tribunal of competent jurisdiction, the validity, legality and enforceability of the remaining provisions shall not in any way be affected or impaired thereby.
+
+NO IMPLIED WAIVERS: No failure or delay by Licensor in enforcing any right or remedy under this Agreement shall be construed as a waiver of any future or other exercise of such right or remedy by Licensor.
+
+GOVERNING LAW: This Agreement shall be construed and enforced in accordance with the laws of the Commonwealth of Pennsylvania without reference to conflict of laws principles.  You consent to the personal jurisdiction of the courts of this County and waive their rights to venue outside of Allegheny County, Pennsylvania.
+
+ENTIRE AGREEMENT AND AMENDMENTS: This Agreement constitutes the sole and entire agreement between Licensee and Licensor as to the matter set forth herein and supersedes any previous agreements, understandings, and arrangements between the parties relating hereto.
+
+
+
+************************************************************************
+
+THIRD-PARTY SOFTWARE NOTICES AND INFORMATION
+
+This project incorporates material from the project(s) listed below (collectively, "Third Party Code").  This Third Party Code is licensed to you under their original license terms set forth below.  We reserves all other rights not expressly granted, whether by implication, estoppel or otherwise.
+ 
+1.	Caffe, version 1.0.0, (https://github.com/BVLC/caffe/)
+
+COPYRIGHT
+
+All contributions by the University of California:
+Copyright (c) 2014-2017 The Regents of the University of California (Regents)
+All rights reserved.
+
+All other contributions:
+Copyright (c) 2014-2017, the respective contributors
+All rights reserved.
+
+Caffe uses a shared copyright model: each contributor holds copyright over
+their contributions to Caffe. The project versioning records all such
+contribution and copyright details. If a contributor wants to further mark
+their specific copyright on a particular contribution, they should indicate
+their copyright solely in the commit message of the change when it is
+committed.
+
+LICENSE
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met: 
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer. 
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution. 
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+CONTRIBUTION AGREEMENT
+
+By contributing to the BVLC/caffe repository through pull-request, comment,
+or otherwise, the contributor releases their content to the
+license and copyright terms herein.
+
+************END OF THIRD-PARTY SOFTWARE NOTICES AND INFORMATION**********

licenses/PyTorch3D_BSD_LICENSE.txt

@@ -0,0 +1,30 @@
+BSD License
+
+For PyTorch3D software
+
+Copyright (c) Meta Platforms, Inc. and affiliates. All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification,
+are permitted provided that the following conditions are met:
+
+ * Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+ * Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+ * Neither the name Meta nor the names of its contributors may be used to
+   endorse or promote products derived from this software without specific
+   prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
+ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR
+ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

licenses/SDXL_CreativeML_Open_RAIL_pp_M_LICENSE.md

@@ -0,0 +1,60 @@
+Copyright (c) 2023 Stability AI
+CreativeML Open RAIL++-M License dated July 26, 2023
+
+Section I: PREAMBLE
+Multimodal generative models are being widely adopted and used, and have the potential to transform the way artists, among other individuals, conceive and benefit from AI or ML technologies as a tool for content creation.
+Notwithstanding the current and potential benefits that these artifacts can bring to society at large, there are also concerns about potential misuses of them, either due to their technical limitations or ethical considerations.
+In short, this license strives for both the open and responsible downstream use of the accompanying model. When it comes to the open character, we took inspiration from open source permissive licenses regarding the grant of IP rights. Referring to the downstream responsible use, we added use-based restrictions not permitting the use of the model in very specific scenarios, in order for the licensor to be able to enforce the license in case potential misuses of the Model may occur. At the same time, we strive to promote open and responsible research on generative models for art and content generation.
+Even though downstream derivative versions of the model could be released under different licensing terms, the latter will always have to include - at minimum - the same use-based restrictions as the ones in the original license (this license). We believe in the intersection between open and responsible AI development; thus, this agreement aims to strike a balance between both in order to enable responsible open-science in the field of AI.
+This CreativeML Open RAIL++-M License governs the use of the model (and its derivatives) and is informed by the model card associated with the model.
+NOW THEREFORE, You and Licensor agree as follows:
+Definitions
+"License" means the terms and conditions for use, reproduction, and Distribution as defined in this document.
+"Data" means a collection of information and/or content extracted from the dataset used with the Model, including to train, pretrain, or otherwise evaluate the Model. The Data is not licensed under this License.
+"Output" means the results of operating a Model as embodied in informational content resulting therefrom.
+"Model" means any accompanying machine-learning based assemblies (including checkpoints), consisting of learnt weights, parameters (including optimizer states), corresponding to the model architecture as embodied in the Complementary Material, that have been trained or tuned, in whole or in part on the Data, using the Complementary Material.
+"Derivatives of the Model" means all modifications to the Model, works based on the Model, or any other model which is created or initialized by transfer of patterns of the weights, parameters, activations or output of the Model, to the other model, in order to cause the other model to perform similarly to the Model, including - but not limited to - distillation methods entailing the use of intermediate data representations or methods based on the generation of synthetic data by the Model for training the other model.
+"Complementary Material" means the accompanying source code and scripts used to define, run, load, benchmark or evaluate the Model, and used to prepare data for training or evaluation, if any. This includes any accompanying documentation, tutorials, examples, etc, if any.
+"Distribution" means any transmission, reproduction, publication or other sharing of the Model or Derivatives of the Model to a third party, including providing the Model as a hosted service made available by electronic or other remote means - e.g. API-based or web access.
+"Licensor" means the copyright owner or entity authorized by the copyright owner that is granting the License, including the persons or entities that may have rights in the Model and/or distributing the Model.
+"You" (or "Your") means an individual or Legal Entity exercising permissions granted by this License and/or making use of the Model for whichever purpose and in any field of use, including usage of the Model in an end-use application - e.g. chatbot, translator, image generator.
+"Third Parties" means individuals or legal entities that are not under common control with Licensor or You.
+"Contribution" means any work of authorship, including the original version of the Model and any modifications or additions to that Model or Derivatives of the Model thereof, that is intentionally submitted to Licensor for inclusion in the Model 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 Model, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
+"Contributor" means Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Model.
+
+Section II: INTELLECTUAL PROPERTY RIGHTS
+Both copyright and patent grants apply to the Model, Derivatives of the Model and Complementary Material. The Model and Derivatives of the Model are subject to additional terms as described in 
+
+Section III.
+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, publicly display, publicly perform, sublicense, and distribute the Complementary Material, the Model, and Derivatives of the Model.
+Grant of Patent License. Subject to the terms and conditions of this License and where and as applicable, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this paragraph) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Model and the Complementary Material, 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 Model 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 Model and/or Complementary Material or a Contribution incorporated within the Model and/or Complementary Material constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for the Model and/or Work shall terminate as of the date such litigation is asserted or filed.
+Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
+Distribution and Redistribution. You may host for Third Party remote access purposes (e.g. software-as-a-service), reproduce and distribute copies of the Model or Derivatives of the Model thereof in any medium, with or without modifications, provided that You meet the following conditions: Use-based restrictions as referenced in paragraph 5 MUST be included as an enforceable provision by You in any type of legal agreement (e.g. a license) governing the use and/or distribution of the Model or Derivatives of the Model, and You shall give notice to subsequent users You Distribute to, that the Model or Derivatives of the Model are subject to paragraph 5. This provision does not apply to the use of Complementary Material. You must give any Third Party recipients of the Model or Derivatives of the Model a copy of this License; You must cause any modified files to carry prominent notices stating that You changed the files; You must retain all copyright, patent, trademark, and attribution notices excluding those notices that do not pertain to any part of the Model, Derivatives of the Model. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions - respecting paragraph 4.a. - for use, reproduction, or Distribution of Your modifications, or for any such Derivatives of the Model as a whole, provided Your use, reproduction, and Distribution of the Model otherwise complies with the conditions stated in this License.
+Use-based restrictions. The restrictions set forth in Attachment A are considered Use-based restrictions. Therefore You cannot use the Model and the Derivatives of the Model for the specified restricted uses. You may use the Model subject to this License, including only for lawful purposes and in accordance with the License. Use may include creating any content with, finetuning, updating, running, training, evaluating and/or reparametrizing the Model. You shall require all of Your users who use the Model or a Derivative of the Model to comply with the terms of this paragraph (paragraph 5).
+The Output You Generate. Except as set forth herein, Licensor claims no rights in the Output You generate using the Model. You are accountable for the Output you generate and its subsequent uses. No use of the output can contravene any provision as stated in the License.
+
+Section IV: OTHER PROVISIONS
+Updates and Runtime Restrictions. To the maximum extent permitted by law, Licensor reserves the right to restrict (remotely or otherwise) usage of the Model in violation of this License.
+Trademarks and related. Nothing in this License permits You to make use of Licensors’ trademarks, trade names, logos or to otherwise suggest endorsement or misrepresent the relationship between the parties; and any rights not expressly granted herein are reserved by the Licensors.
+Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Model and the Complementary Material (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 Model, Derivatives of the Model, and the Complementary Material and assume any risks associated with Your exercise of permissions under this License.
+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 Model and the Complementary Material (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.
+Accepting Warranty or Additional Liability. While redistributing the Model, Derivatives of the Model and the Complementary Material 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.
+If any provision of this License is held to be invalid, illegal or unenforceable, the remaining provisions shall be unaffected thereby and remain valid as if such provision had not been set forth herein.
+
+END OF TERMS AND CONDITIONS
+
+Attachment A
+Use Restrictions
+You agree not to use the Model or Derivatives of the Model:
+In any way that violates any applicable national, federal, state, local or international law or regulation;
+For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
+To generate or disseminate verifiably false information and/or content with the purpose of harming others;
+To generate or disseminate personal identifiable information that can be used to harm an individual;
+To defame, disparage or otherwise harass others;
+For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation;
+For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;
+To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;
+For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories;
+To provide medical advice and medical results interpretation;
+To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).
+

licenses/model_cards/clip_h__README.md

@@ -0,0 +1,165 @@
+---
+license: mit
+widget:
+- src: >-
+    https://huggingface.co/datasets/mishig/sample_images/resolve/main/cat-dog-music.png
+  candidate_labels: playing music, playing sports
+  example_title: Cat & Dog
+library_name: open_clip
+pipeline_tag: zero-shot-image-classification
+---
+# Model Card for CLIP ViT-H/14 - LAION-2B
+
+#  Table of Contents
+
+1. [Model Details](#model-details)
+2. [Uses](#uses)
+3. [Training Details](#training-details)
+4. [Evaluation](#evaluation)
+5. [Acknowledgements](#acknowledgements)
+6. [Citation](#citation)
+7. [How To Get Started With the Model](#how-to-get-started-with-the-model)
+
+
+# Model Details
+
+## Model Description
+
+A CLIP ViT-H/14 model trained with the LAION-2B English subset of LAION-5B (https://laion.ai/blog/laion-5b/) using OpenCLIP (https://github.com/mlfoundations/open_clip).
+
+Model training done by Romain Beaumont on the [stability.ai](https://stability.ai/) cluster. 
+
+# Uses
+
+As per the original [OpenAI CLIP model card](https://github.com/openai/CLIP/blob/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1/model-card.md), this model is intended as a research output for research communities. We hope that this model will enable researchers to better understand and explore zero-shot, arbitrary image classification. We also hope it can be used for interdisciplinary studies of the potential impact of such model. 
+
+The OpenAI CLIP paper includes a discussion of potential downstream impacts to provide an example for this sort of analysis. Additionally, the LAION-5B blog (https://laion.ai/blog/laion-5b/) and upcoming paper include additional discussion as it relates specifically to the training dataset. 
+
+## Direct Use
+
+Zero-shot image classification, image and text retrieval, among others.
+
+## Downstream Use
+
+Image classification and other image task fine-tuning, linear probe image classification, image generation guiding and conditioning, among others.
+
+## Out-of-Scope Use
+
+As per the OpenAI models,
+
+**Any** deployed use case of the model - whether commercial or not - is currently out of scope. Non-deployed use cases such as image search in a constrained environment, are also not recommended unless there is thorough in-domain testing of the model with a specific, fixed class taxonomy. This is because our safety assessment demonstrated a high need for task specific testing especially given the variability of CLIP’s performance with different class taxonomies. This makes untested and unconstrained deployment of the model in any use case currently potentially harmful. 
+
+Certain use cases which would fall under the domain of surveillance and facial recognition are always out-of-scope regardless of performance of the model. This is because the use of artificial intelligence for tasks such as these can be premature currently given the lack of testing norms and checks to ensure its fair use.
+
+Since the model has not been purposefully trained in or evaluated on any languages other than English, its use should be limited to English language use cases.
+
+Further the above notice, the LAION-5B dataset used in training of these models has additional considerations, see below.
+
+# Training Details
+
+## Training Data
+
+This model was trained with the 2 Billion sample English subset of LAION-5B (https://laion.ai/blog/laion-5b/).
+
+**IMPORTANT NOTE:** The motivation behind dataset creation is to democratize research and experimentation around large-scale multi-modal model training and handling of uncurated, large-scale datasets crawled from publically available internet. Our recommendation is therefore to use the dataset for research purposes. Be aware that this large-scale dataset is uncurated. Keep in mind that the uncurated nature of the dataset means that collected links may lead to strongly discomforting and disturbing content for a human viewer. Therefore, please use the demo links with caution and at your own risk. It is possible to extract a “safe” subset by filtering out samples based on the safety tags (using a customized trained NSFW classifier that we built). While this strongly reduces the chance for encountering potentially harmful content when viewing, we cannot entirely exclude the possibility for harmful content being still present in safe mode, so that the warning holds also there. We think that providing the dataset openly to broad research and other interested communities will allow for transparent investigation of benefits that come along with training large-scale models as well as pitfalls and dangers that may stay unreported or unnoticed when working with closed large datasets that remain restricted to a small community. Providing our dataset openly, we however do not recommend using it for creating ready-to-go industrial products, as the basic research about general properties and safety of such large-scale models, which we would like to encourage with this release, is still in progress.
+
+## Training Procedure
+
+Please see [training notes](https://docs.google.com/document/d/1EFbMLRWSSV0LUf9Du1pWzWqgeiIRPwEWX2s1C6mAk5c) and [wandb logs](https://wandb.ai/rom1504/eval_openclip/reports/H-14--VmlldzoyNDAxODQ3).
+
+# Evaluation
+
+Evaluation done with code in the [LAION CLIP Benchmark suite](https://github.com/LAION-AI/CLIP_benchmark).
+
+## Testing Data, Factors & Metrics
+
+### Testing Data
+
+The testing is performed with VTAB+ (A combination of VTAB (https://arxiv.org/abs/1910.04867) w/ additional robustness datasets) for classification and COCO and Flickr for retrieval.
+
+**TODO** - more detail
+
+## Results
+
+The model achieves a 78.0 zero-shot top-1 accuracy on ImageNet-1k.
+
+An initial round of benchmarks have been performed on a wider range of datasets, currently viewable at https://github.com/LAION-AI/CLIP_benchmark/blob/main/benchmark/results.ipynb
+
+**TODO** - create table for just this model's metrics.
+
+# Acknowledgements
+
+Acknowledging [stability.ai](https://stability.ai/) for the compute used to train this model.
+
+# Citation
+
+**BibTeX:**
+
+LAION-5B
+```bibtex
+@inproceedings{schuhmann2022laionb,
+  title={{LAION}-5B: An open large-scale dataset for training next generation image-text models},
+  author={Christoph Schuhmann and
+          Romain Beaumont and
+          Richard Vencu and
+          Cade W Gordon and
+          Ross Wightman and
+          Mehdi Cherti and
+          Theo Coombes and
+          Aarush Katta and
+          Clayton Mullis and
+          Mitchell Wortsman and
+          Patrick Schramowski and
+          Srivatsa R Kundurthy and
+          Katherine Crowson and
+          Ludwig Schmidt and
+          Robert Kaczmarczyk and
+          Jenia Jitsev},
+  booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
+  year={2022},
+  url={https://openreview.net/forum?id=M3Y74vmsMcY}
+}
+```
+
+OpenAI CLIP paper
+```
+@inproceedings{Radford2021LearningTV,
+  title={Learning Transferable Visual Models From Natural Language Supervision},
+  author={Alec Radford and Jong Wook Kim and Chris Hallacy and A. Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever},
+  booktitle={ICML},
+  year={2021}
+}
+```
+
+OpenCLIP software
+```
+@software{ilharco_gabriel_2021_5143773,
+  author       = {Ilharco, Gabriel and
+                  Wortsman, Mitchell and
+                  Wightman, Ross and
+                  Gordon, Cade and
+                  Carlini, Nicholas and
+                  Taori, Rohan and
+                  Dave, Achal and
+                  Shankar, Vaishaal and
+                  Namkoong, Hongseok and
+                  Miller, John and
+                  Hajishirzi, Hannaneh and
+                  Farhadi, Ali and
+                  Schmidt, Ludwig},
+  title        = {OpenCLIP},
+  month        = jul,
+  year         = 2021,
+  note         = {If you use this software, please cite it as below.},
+  publisher    = {Zenodo},
+  version      = {0.1},
+  doi          = {10.5281/zenodo.5143773},
+  url          = {https://doi.org/10.5281/zenodo.5143773}
+}
+```
+
+# How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+** TODO ** - Hugging Face transformers, OpenCLIP, and timm getting started snippets

licenses/model_cards/controlnet__README.md

@@ -0,0 +1,99 @@
+---
+license: other
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+tags:
+- stable-diffusion-xl
+- stable-diffusion-xl-diffusers
+- text-to-image
+- diffusers
+- controlnet
+inference: false
+---
+    
+# SDXL-controlnet: OpenPose (v2)
+
+These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with OpenPose (v2) conditioning. You can find some example images in the following. 
+
+prompt: a ballerina, romantic sunset, 4k photo
+![images_0)](./screenshot_ballerina.png)
+
+
+### Comfy Workflow
+![images_0)](./out_ballerina.png)
+
+
+(Image is from ComfyUI, you can drag and drop in Comfy to use it as workflow)
+
+License: refers to the OpenPose's one.
+
+### Using in 🧨 diffusers
+
+First, install all the libraries:
+
+```bash
+pip install -q controlnet_aux transformers accelerate
+pip install -q git+https://github.com/huggingface/diffusers
+```
+
+Now, we're ready to make Darth Vader dance:
+
+```python
+from diffusers import AutoencoderKL, StableDiffusionXLControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
+import torch
+from controlnet_aux import OpenposeDetector
+from diffusers.utils import load_image
+
+
+# Compute openpose conditioning image.
+openpose = OpenposeDetector.from_pretrained("lllyasviel/ControlNet")
+
+image = load_image(
+    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/person.png"
+)
+openpose_image = openpose(image)
+
+# Initialize ControlNet pipeline.
+controlnet = ControlNetModel.from_pretrained("thibaud/controlnet-openpose-sdxl-1.0", torch_dtype=torch.float16)
+pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0", controlnet=controlnet, torch_dtype=torch.float16
+)
+pipe.enable_model_cpu_offload()
+
+
+# Infer.
+prompt = "Darth vader dancing in a desert, high quality"
+negative_prompt = "low quality, bad quality"
+images = pipe(
+    prompt, 
+    negative_prompt=negative_prompt,
+    num_inference_steps=25,
+    num_images_per_prompt=4,
+    image=openpose_image.resize((1024, 1024)),
+    generator=torch.manual_seed(97),
+).images
+images[0]
+```
+
+Here are some gemerated examples:
+
+![](./darth_vader_grid.png)
+
+
+### Training
+
+Use of the training script by HF🤗 [here](https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sdxl.md). 
+
+#### Training data
+This checkpoint was first trained for 15,000 steps on laion 6a resized to a max minimum dimension of 768. 
+
+#### Compute
+one 1xA100 machine (Thanks a lot HF🤗 to provide the compute!)
+
+#### Batch size
+Data parallel with a single gpu batch size of 2 with gradient accumulation 8.
+
+#### Hyper Parameters
+Constant learning rate of 8e-5
+
+#### Mixed precision
+fp16

licenses/model_cards/ip_adapter__README.md

@@ -0,0 +1,46 @@
+---
+tags:
+- text-to-image
+- stable-diffusion
+license: apache-2.0
+language:
+- en
+library_name: diffusers
+---
+
+# IP-Adapter Model Card
+
+
+<div align="center">
+
+[**Project Page**](https://ip-adapter.github.io) **|** [**Paper (ArXiv)**](https://arxiv.org/abs/2308.06721) **|** [**Code**](https://github.com/tencent-ailab/IP-Adapter)
+</div>
+
+---
+
+
+## Introduction
+
+we present IP-Adapter, an effective and lightweight adapter to achieve image prompt capability for the pre-trained text-to-image diffusion models. An IP-Adapter with only 22M parameters can achieve comparable or even better performance to a fine-tuned image prompt model. IP-Adapter can be generalized not only to other custom models fine-tuned from the same base model, but also to controllable generation using existing controllable tools. Moreover, the image prompt can also work well with the text prompt to accomplish multimodal image generation.
+
+![arch](./fig1.png)
+
+## Models
+
+### Image Encoder
+- [models/image_encoder](https://huggingface.co/h94/IP-Adapter/tree/main/models/image_encoder): [OpenCLIP-ViT-H-14](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K) with 632.08M parameter
+- [sdxl_models/image_encoder](https://huggingface.co/h94/IP-Adapter/tree/main/sdxl_models/image_encoder): [OpenCLIP-ViT-bigG-14](https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k) with 1844.9M parameter
+
+More information can be found [here](https://laion.ai/blog/giant-openclip/)
+
+### IP-Adapter for SD 1.5
+- [ip-adapter_sd15.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter_sd15.bin): use global image embedding from OpenCLIP-ViT-H-14 as condition
+- [ip-adapter_sd15_light.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter_sd15_light.bin): same as ip-adapter_sd15, but more compatible with text prompt
+- [ip-adapter-plus_sd15.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter-plus_sd15.bin): use patch image embeddings from OpenCLIP-ViT-H-14 as condition, closer to the reference image than ip-adapter_sd15
+- [ip-adapter-plus-face_sd15.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter-plus-face_sd15.bin): same as ip-adapter-plus_sd15, but use cropped face image as condition
+
+### IP-Adapter for SDXL 1.0
+- [ip-adapter_sdxl.bin](https://huggingface.co/h94/IP-Adapter/blob/main/sdxl_models/ip-adapter_sdxl.bin): use global image embedding from OpenCLIP-ViT-bigG-14 as condition
+- [ip-adapter_sdxl_vit-h.bin](https://huggingface.co/h94/IP-Adapter/blob/main/sdxl_models/ip-adapter_sdxl_vit-h.bin): same as ip-adapter_sdxl, but use OpenCLIP-ViT-H-14
+- [ip-adapter-plus_sdxl_vit-h.bin](https://huggingface.co/h94/IP-Adapter/blob/main/sdxl_models/ip-adapter-plus_sdxl_vit-h.bin): use patch image embeddings from OpenCLIP-ViT-H-14 as condition, closer to the reference image than ip-adapter_xl and ip-adapter_sdxl_vit-h
+- [ip-adapter-plus-face_sdxl_vit-h.bin](https://huggingface.co/h94/IP-Adapter/blob/main/sdxl_models/ip-adapter-plus-face_sdxl_vit-h.bin): same as ip-adapter-plus_sdxl_vit-h, but use cropped face image as condition

licenses/model_cards/layerdiffuse_attention__README.md

@@ -0,0 +1,62 @@
+---
+license: mit
+pipeline_tag: text-to-image
+library_name: diffusers
+---
+# Diffusers API of Transparent Image Layer Diffusion using Latent Transparency
+Create transparent image with Diffusers!
+![corgi](result_sdxl.png)
+Please check the Github repo here: https://github.com/rootonchair/diffuser_layerdiffuse
+
+This is a port to Diffuser from original [SD Webui's Layer Diffusion](https://github.com/layerdiffusion/sd-forge-layerdiffuse) to extend the ability to generate transparent image with your favorite API
+
+
+Paper: [Transparent Image Layer Diffusion using Latent Transparency](https://arxiv.org/abs/2402.17113)
+
+## What's new
+
+- Added Diffusers-ready SDXL LayerDiffuse conditional weights for foreground-to-blending, background-to-blending, foreground-and-blend-to-background, and background-and-blend-to-foreground workflows.
+- New remote weights: `diffuser_layer_xl_fg2ble.safetensors`, `diffuser_layer_xl_bg2ble.safetensors`, `diffuser_layer_xl_fgble2bg.safetensors`, and `diffuser_layer_xl_bgble2fg.safetensors`.
+- The GitHub examples load these weights from this Hugging Face repo through the local HF cache by default.
+- SDXL Forge weight conversion is now consolidated in `scripts/convert_xl_layerdiffuse.py` with `--mode fg2ble|bg2ble|fgble2bg|bgble2fg`.
+- Demo scripts now expose CLI options for model, prompt, seed, output path, `--variant`, and `--cpu-offload`; run any script with `--help` for details.
+
+## Quickstart
+
+Generate transparent image with SD1.5 models. In this example, we will use [digiplay/Juggernaut_final](https://huggingface.co/digiplay/Juggernaut_final) as the base model
+
+```python
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+import torch
+
+from diffusers import StableDiffusionPipeline
+
+from models import TransparentVAEDecoder
+from loaders import load_lora_to_unet
+
+
+
+if __name__ == "__main__":
+
+    model_path = hf_hub_download(
+        'LayerDiffusion/layerdiffusion-v1',
+        'layer_sd15_vae_transparent_decoder.safetensors',
+    )
+
+    vae_transparent_decoder = TransparentVAEDecoder.from_pretrained("digiplay/Juggernaut_final", subfolder="vae", torch_dtype=torch.float16).to("cuda")
+    vae_transparent_decoder.set_transparent_decoder(load_file(model_path))
+
+    pipeline = StableDiffusionPipeline.from_pretrained("digiplay/Juggernaut_final", vae=vae_transparent_decoder, torch_dtype=torch.float16, safety_checker=None).to("cuda")
+
+    model_path = hf_hub_download(
+        'LayerDiffusion/layerdiffusion-v1',
+        'layer_sd15_transparent_attn.safetensors'
+    )
+
+    load_lora_to_unet(pipeline.unet, model_path, frames=1)
+    
+    image = pipeline(prompt="a dog sitting in room, high quality", 
+                       width=512, height=512,
+                       num_images_per_prompt=1, return_dict=False)[0]
+```

licenses/model_cards/layerdiffuse_decoder__README.md

@@ -0,0 +1,5 @@
+---
+license: creativeml-openrail-m
+---
+
+model card under construction

licenses/model_cards/sdxl__README.md

@@ -0,0 +1,215 @@
+---
+license: openrail++
+tags:
+- text-to-image
+- stable-diffusion
+---
+# SD-XL 1.0-base Model Card
+![row01](01.png)
+
+## Model
+
+![pipeline](pipeline.png)
+
+[SDXL](https://arxiv.org/abs/2307.01952) consists of an [ensemble of experts](https://arxiv.org/abs/2211.01324) pipeline for latent diffusion: 
+In a first step, the base model is used to generate (noisy) latents, 
+which are then further processed with a refinement model (available here: https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0/) specialized for the final denoising steps.
+Note that the base model can be used as a standalone module.
+
+Alternatively, we can use a two-stage pipeline as follows: 
+First, the base model is used to generate latents of the desired output size. 
+In the second step, we use a specialized high-resolution model and apply a technique called SDEdit (https://arxiv.org/abs/2108.01073, also known as "img2img") 
+to the latents generated in the first step, using the same prompt. This technique is slightly slower than the first one, as it requires more function evaluations.
+
+Source code is available at https://github.com/Stability-AI/generative-models .
+
+### Model Description
+
+- **Developed by:** Stability AI
+- **Model type:** Diffusion-based text-to-image generative model
+- **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md)
+- **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses two fixed, pretrained text encoders ([OpenCLIP-ViT/G](https://github.com/mlfoundations/open_clip) and [CLIP-ViT/L](https://github.com/openai/CLIP/tree/main)).
+- **Resources for more information:** Check out our [GitHub Repository](https://github.com/Stability-AI/generative-models) and the [SDXL report on arXiv](https://arxiv.org/abs/2307.01952).
+
+### Model Sources
+
+For research purposes, we recommend our `generative-models` Github repository (https://github.com/Stability-AI/generative-models), which implements the most popular diffusion frameworks (both training and inference) and for which new functionalities like distillation will be added over time.
+[Clipdrop](https://clipdrop.co/stable-diffusion) provides free SDXL inference.
+
+- **Repository:** https://github.com/Stability-AI/generative-models
+- **Demo:** https://clipdrop.co/stable-diffusion
+
+
+## Evaluation
+![comparison](comparison.png)
+The chart above evaluates user preference for SDXL (with and without refinement) over SDXL 0.9 and Stable Diffusion 1.5 and 2.1. 
+The SDXL base model performs significantly better than the previous variants, and the model combined with the refinement module achieves the best overall performance.
+
+
+### 🧨 Diffusers 
+
+Make sure to upgrade diffusers to >= 0.19.0:
+```
+pip install diffusers --upgrade
+```
+
+In addition make sure to install `transformers`, `safetensors`, `accelerate` as well as the invisible watermark:
+```
+pip install invisible_watermark transformers accelerate safetensors
+```
+
+To just use the base model, you can run:
+
+```py
+from diffusers import DiffusionPipeline
+import torch
+
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
+pipe.to("cuda")
+
+# if using torch < 2.0
+# pipe.enable_xformers_memory_efficient_attention()
+
+prompt = "An astronaut riding a green horse"
+
+images = pipe(prompt=prompt).images[0]
+```
+
+To use the whole base + refiner pipeline as an ensemble of experts you can run:
+
+```py
+from diffusers import DiffusionPipeline
+import torch
+
+# load both base & refiner
+base = DiffusionPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+)
+base.to("cuda")
+refiner = DiffusionPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-refiner-1.0",
+    text_encoder_2=base.text_encoder_2,
+    vae=base.vae,
+    torch_dtype=torch.float16,
+    use_safetensors=True,
+    variant="fp16",
+)
+refiner.to("cuda")
+
+# Define how many steps and what % of steps to be run on each experts (80/20) here
+n_steps = 40
+high_noise_frac = 0.8
+
+prompt = "A majestic lion jumping from a big stone at night"
+
+# run both experts
+image = base(
+    prompt=prompt,
+    num_inference_steps=n_steps,
+    denoising_end=high_noise_frac,
+    output_type="latent",
+).images
+image = refiner(
+    prompt=prompt,
+    num_inference_steps=n_steps,
+    denoising_start=high_noise_frac,
+    image=image,
+).images[0]
+```
+
+When using `torch >= 2.0`, you can improve the inference speed by 20-30% with torch.compile. Simple wrap the unet with torch compile before running the pipeline:
+```py
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+```
+
+If you are limited by GPU VRAM, you can enable *cpu offloading* by calling `pipe.enable_model_cpu_offload`
+instead of `.to("cuda")`:
+
+```diff
+- pipe.to("cuda")
++ pipe.enable_model_cpu_offload()
+```
+
+For more information on how to use Stable Diffusion XL with `diffusers`, please have a look at [the Stable Diffusion XL Docs](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl).
+
+### Optimum
+[Optimum](https://github.com/huggingface/optimum) provides a Stable Diffusion pipeline compatible with both [OpenVINO](https://docs.openvino.ai/latest/index.html) and [ONNX Runtime](https://onnxruntime.ai/).
+
+#### OpenVINO
+
+To install Optimum with the dependencies required for OpenVINO :
+
+```bash
+pip install optimum[openvino]
+```
+
+To load an OpenVINO model and run inference with OpenVINO Runtime, you need to replace `StableDiffusionXLPipeline` with Optimum `OVStableDiffusionXLPipeline`. In case you want to load a PyTorch model and convert it to the OpenVINO format on-the-fly, you can set `export=True`.
+
+```diff
+- from diffusers import StableDiffusionXLPipeline
++ from optimum.intel import OVStableDiffusionXLPipeline
+
+model_id = "stabilityai/stable-diffusion-xl-base-1.0"
+- pipeline = StableDiffusionXLPipeline.from_pretrained(model_id)
++ pipeline = OVStableDiffusionXLPipeline.from_pretrained(model_id)
+prompt = "A majestic lion jumping from a big stone at night"
+image = pipeline(prompt).images[0]
+```
+
+You can find more examples (such as static reshaping and model compilation) in optimum [documentation](https://huggingface.co/docs/optimum/main/en/intel/inference#stable-diffusion-xl).
+
+
+#### ONNX
+
+To install Optimum with the dependencies required for ONNX Runtime inference :
+
+```bash
+pip install optimum[onnxruntime]
+```
+
+To load an ONNX model and run inference with ONNX Runtime, you need to replace `StableDiffusionXLPipeline` with Optimum `ORTStableDiffusionXLPipeline`. In case you want to load a PyTorch model and convert it to the ONNX format on-the-fly, you can set `export=True`.
+
+```diff
+- from diffusers import StableDiffusionXLPipeline
++ from optimum.onnxruntime import ORTStableDiffusionXLPipeline
+
+model_id = "stabilityai/stable-diffusion-xl-base-1.0"
+- pipeline = StableDiffusionXLPipeline.from_pretrained(model_id)
++ pipeline = ORTStableDiffusionXLPipeline.from_pretrained(model_id)
+prompt = "A majestic lion jumping from a big stone at night"
+image = pipeline(prompt).images[0]
+```
+
+You can find more examples in optimum [documentation](https://huggingface.co/docs/optimum/main/en/onnxruntime/usage_guides/models#stable-diffusion-xl).
+
+
+## Uses
+
+### Direct Use
+
+The model is intended for research purposes only. Possible research areas and tasks include
+
+- Generation of artworks and use in design and other artistic processes.
+- Applications in educational or creative tools.
+- Research on generative models.
+- Safe deployment of models which have the potential to generate harmful content.
+- Probing and understanding the limitations and biases of generative models.
+
+Excluded uses are described below.
+
+### Out-of-Scope Use
+
+The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
+
+## Limitations and Bias
+
+### Limitations
+
+- The model does not achieve perfect photorealism
+- The model cannot render legible text
+- The model struggles with more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
+- Faces and people in general may not be generated properly.
+- The autoencoding part of the model is lossy.
+
+### Bias
+While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.

licenses/model_cards/vae__README.md

@@ -0,0 +1,67 @@
+---
+license: mit
+tags:
+- stable-diffusion
+- stable-diffusion-diffusers
+inference: false
+---
+# SDXL-VAE-FP16-Fix
+
+SDXL-VAE-FP16-Fix is the [SDXL VAE](https://huggingface.co/stabilityai/sdxl-vae)*, but modified to run in fp16 precision without generating NaNs.
+
+| VAE                   | Decoding in `float32` / `bfloat16` precision | Decoding in `float16` precision |
+| --------------------- | -------------------------------------------- | ------------------------------- |
+| SDXL-VAE              | ✅ ![](./images/orig-fp32.png)              | ⚠️ ![](./images/orig-fp16.png)  |
+| SDXL-VAE-FP16-Fix     | ✅ ![](./images/fix-fp32.png)               | ✅ ![](./images/fix-fp16.png)   |
+
+## 🧨 Diffusers Usage
+
+Just load this checkpoint via `AutoencoderKL`:
+
+```py
+import torch
+from diffusers import DiffusionPipeline, AutoencoderKL
+
+vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
+pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", vae=vae, torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
+pipe.to("cuda")
+
+refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", vae=vae, torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
+refiner.to("cuda")
+
+n_steps = 40
+high_noise_frac = 0.7
+
+prompt = "A majestic lion jumping from a big stone at night"
+
+image = pipe(prompt=prompt, num_inference_steps=n_steps, denoising_end=high_noise_frac, output_type="latent").images
+image = refiner(prompt=prompt, num_inference_steps=n_steps, denoising_start=high_noise_frac, image=image).images[0]
+image
+```
+
+![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/lion_refined.png)
+
+## Automatic1111 Usage
+
+1. Download the fixed [sdxl.vae.safetensors](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/resolve/main/sdxl.vae.safetensors?download=true) file
+2. Move this `sdxl.vae.safetensors` file into the webui folder under `stable-diffusion-webui/models/VAE`
+3. In your webui settings, select the fixed VAE you just added
+4. If you were using the `--no-half-vae` command line arg for SDXL (in `webui-user.bat` or wherever), you can now remove it
+
+(Disclaimer - I haven't tested this, just aggregating various instructions I've seen elsewhere :P PRs to improve these instructions are welcomed!)
+
+## Details
+
+SDXL-VAE generates NaNs in fp16 because the internal activation values are too big:
+![](./images/activation-magnitudes.jpg)
+
+SDXL-VAE-FP16-Fix was created by finetuning the SDXL-VAE to:
+1. keep the final output the same, but
+2. make the internal activation values smaller, by
+3. scaling down weights and biases within the network
+
+There are slight discrepancies between the output of SDXL-VAE-FP16-Fix and SDXL-VAE, but the decoded images should be [close enough for most purposes](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/discussions/7#64c5c0f8e2e5c94bd04eaa80).
+
+---
+
+\* `sdxl-vae-fp16-fix` is specifically based on [SDXL-VAE (0.9)](https://huggingface.co/stabilityai/sdxl-vae/discussions/6#64acea3f7ac35b7de0554490), but it works with SDXL 1.0 too

manifest.json

@@ -0,0 +1,632 @@
+{
+  "format_version": 1,
+  "status": "complete",
+  "default_renderer": "qwen21",
+  "bytes_total": 51319092596,
+  "public_upload_excludes": [
+    "assets/body_models/smplx/**",
+    "pose_diffusion/controlnet/**"
+  ],
+  "restricted_resources": [
+    {
+      "path": "assets/body_models/smplx/SMPLX_NEUTRAL.npz",
+      "size": 108752058,
+      "sha256": "376021446ddc86e99acacd795182bbef903e61d33b76b9d8b359c2b0865bd992",
+      "group": "smplx_restricted",
+      "public_upload": false
+    },
+    {
+      "path": "pose_diffusion/controlnet/config.json",
+      "size": 1235,
+      "sha256": "b5b8f9a7619c9452f19407ef73a01ce3f061fcf932de43ddbaca336d12d02801",
+      "group": "openpose_controlnet_restricted",
+      "public_upload": false
+    },
+    {
+      "path": "pose_diffusion/controlnet/diffusion_pytorch_model.safetensors",
+      "size": 5004167829,
+      "sha256": "5a4b928cb1e93748217900cb66d4135bf70d932d2924232f925910fad9e43a92",
+      "group": "openpose_controlnet_restricted",
+      "public_upload": false
+    }
+  ],
+  "verification": "SHA256 streamed over every source byte while independently copying and fsyncing; large destination files are not reread a second time.",
+  "files": [
+    {
+      "path": "README.md",
+      "size": 5184,
+      "sha256": "8ee4dc5613cfb485245614dfb54de3423d33cb7626a55a1decc11884767a4f1b",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "THIRD_PARTY_NOTICES.md",
+      "size": 4144,
+      "sha256": "f38cdddf6b21ccc0cac687b4a2c64654c949671495cf4c4905efa9f0735736ae",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "assets/body_models/smplx/SMPLX_NEUTRAL.npz",
+      "size": 108752058,
+      "sha256": "376021446ddc86e99acacd795182bbef903e61d33b76b9d8b359c2b0865bd992",
+      "group": "smplx_restricted",
+      "public_upload": false
+    },
+    {
+      "path": "assets/camera/camera_centers.npz",
+      "size": 3796,
+      "sha256": "9f08c905c7461f86efeead881d4ba35d3d3bc7f7d8e9c4301894290efeaceb20",
+      "group": "core",
+      "public_upload": true
+    },
+    {
+      "path": "assets/fonts/DejaVuSans.ttf",
+      "size": 757076,
+      "sha256": "437a5ecec2ec177cba9284cbffc56055311347f3e9fe4f2b4b40323d0290a6db",
+      "group": "core",
+      "public_upload": true
+    },
+    {
+      "path": "assets/fonts/LICENSE-DejaVu.txt",
+      "size": 2719,
+      "sha256": "1df59b3c0ea60034ac57bdb7dd1bdaa51edad4eefd78e891a74739d32bfbfba7",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "flexdm/design_encoder.pt",
+      "size": 9859050,
+      "sha256": "b75c3dab8a1f5e4f9dd7b6fb8c43f82a4ec11143545329e9937e291a58fc5e01",
+      "group": "core",
+      "public_upload": true
+    },
+    {
+      "path": "flexdm/metadata.json",
+      "size": 7107,
+      "sha256": "4bb38d9c34ff43b3418f644c18a7727dd615b0518d09c0891577c09b9d648759",
+      "group": "core",
+      "public_upload": true
+    },
+    {
+      "path": "humanaware/final.pt",
+      "size": 137593522,
+      "sha256": "64082b9a9a7273977679d6456c9f08ffefbe5a19bdeffef513c10566286e207c",
+      "group": "core",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/CreativeML_Open_RAIL_M_reference_LICENSE.txt",
+      "size": 14385,
+      "sha256": "be351ebe7ac01bcdbb018639aadcfd38f136b7dc3f2a3d4d3a24db51d1b210ef",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/FlexDM_Apache_2.0_LICENSE.txt",
+      "size": 11340,
+      "sha256": "58264dfa6354a97ed41de2a64de739aa6af14ef233aeebc9115f53a43b9334fb",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/IP_Adapter_Apache_2.0_LICENSE.txt",
+      "size": 11357,
+      "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/LayerDiffuse_conversion_MIT_LICENSE.txt",
+      "size": 1070,
+      "sha256": "7f1094b4293aa01c739838c15fe9d661813aeebc4fe006b4293972a7cc54de6b",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/LayerDiffusion_original_code_Apache_2.0_LICENSE.txt",
+      "size": 11357,
+      "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/MIT_template_SPDX_reference.txt",
+      "size": 1078,
+      "sha256": "b05785f9f18e6716bab63424b11454513b9943a222595b70411009202fc592b5",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/OpenCLIP_MIT_LICENSE.txt",
+      "size": 1229,
+      "sha256": "4a5b4f13ea4792a8211a69f32d2b460b6d520e57cd23c6301e707c76a6e97a55",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/OpenPose_RESTRICTED_reference_LICENSE.txt",
+      "size": 9686,
+      "sha256": "be0b0fc17147b2c5f85fdfde41ea8cd08dacef8ea846082a3f727672104718a6",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/PyTorch3D_BSD_LICENSE.txt",
+      "size": 1534,
+      "sha256": "6da05663049417a91409fa349bfad5778ed56c9ef68226dde28dffd541481579",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/SDXL_CreativeML_Open_RAIL_pp_M_LICENSE.md",
+      "size": 14109,
+      "sha256": "19b6998b569b53ac1fc2158a8a3202c8699a9a4605b47075715d9c96be7fb6d0",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/model_cards/clip_h__README.md",
+      "size": 8209,
+      "sha256": "14db420f00ddf78a07194dc4cdc57977d979e0f2c34994137679046defdf6577",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/model_cards/controlnet__README.md",
+      "size": 2666,
+      "sha256": "09d8f79fba241dba87d5983f48cb5635367e3b057e68aaed99ffbd9b064fee80",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/model_cards/ip_adapter__README.md",
+      "size": 3091,
+      "sha256": "ba3a50dc2093d0eb075890e9af7409382874669d83939e64323246d0c4403cf8",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/model_cards/layerdiffuse_attention__README.md",
+      "size": 2802,
+      "sha256": "c106ddf21b8ca1f0d7b6902c7fd1960b2513c4b0bfef8ddd8cd0fe475fea9d88",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/model_cards/layerdiffuse_decoder__README.md",
+      "size": 70,
+      "sha256": "0317746748035546dce1d8fd756a9142ca3b5ce7bad53c4f9681ae33cc9ec588",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/model_cards/sdxl__README.md",
+      "size": 8668,
+      "sha256": "40d263065b8a3e9a41996c257e11463fd97ae956ebf4e3f8b9625e0d78183893",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "licenses/model_cards/vae__README.md",
+      "size": 3143,
+      "sha256": "76045882b4ee98c62244b56225d7e709f0e29ba89471700732bf20d8a682ec50",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "model_sources.json",
+      "size": 20897,
+      "sha256": "a44dd84ddd54d4b2f75c60862f24d285962f0ed8d03f13c0292b08ab4afd5604",
+      "group": "attribution",
+      "public_upload": true
+    },
+    {
+      "path": "pose/52joints_tokenization.pth",
+      "size": 52630720,
+      "sha256": "0893481b5b6941f965c125dd10626fb91d28a51e04b3f3c3f330bb9e19a6d92d",
+      "group": "core",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/controlnet/config.json",
+      "size": 1235,
+      "sha256": "b5b8f9a7619c9452f19407ef73a01ce3f061fcf932de43ddbaca336d12d02801",
+      "group": "openpose_controlnet_restricted",
+      "public_upload": false
+    },
+    {
+      "path": "pose_diffusion/controlnet/diffusion_pytorch_model.safetensors",
+      "size": 5004167829,
+      "sha256": "5a4b928cb1e93748217900cb66d4135bf70d932d2924232f925910fad9e43a92",
+      "group": "openpose_controlnet_restricted",
+      "public_upload": false
+    },
+    {
+      "path": "pose_diffusion/ip_adapter/image_encoder_h2/config.json",
+      "size": 4725,
+      "sha256": "50150597fccadc90f3198d1c2caf2c41d88a40908c38fb428ea56c249b501d85",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/ip_adapter/image_encoder_h2/model.safetensors",
+      "size": 3944552236,
+      "sha256": "036e6e2bd49697511f4f8b8cb5ee465f93025f7a69a145eadeb9a881ace9b18d",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/ip_adapter/ip-adapter_sdxl_vit-h.safetensors",
+      "size": 698391064,
+      "sha256": "ebf05d918348aec7abb02a5e9ecef77e0aaea6914a5c4ea13f50d45eb1681831",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/layerdiffuse/diffuser_layer_xl_transparent_attn.safetensors",
+      "size": 743345968,
+      "sha256": "2626f9aa142f260c12336af754e6003661fbd75c467ecb3906f94783cc2b1b42",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/layerdiffuse/vae_transparent_decoder.safetensors",
+      "size": 208266320,
+      "sha256": "59dc8feefe40d26b6cb7186aed7af70c60d94ac4f9db8ebe7f121a01ba27a2fc",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/model_index.json",
+      "size": 609,
+      "sha256": "6d7b93508390ab91ac5bfbe4aeb4dc2d83f7bb1b05fb069d714b5b0c75f70d44",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/scheduler/scheduler_config.json",
+      "size": 479,
+      "sha256": "af3e45a949aff8b8341ab8b811429ec03fee857a700a1d9477363e4fff9666e2",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/text_encoder/config.json",
+      "size": 565,
+      "sha256": "39b8b2e4b1949e36969caa425b6c81c68bace99198dd9078ce05d16ad401fe7f",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/text_encoder/model.fp16.safetensors",
+      "size": 246144152,
+      "sha256": "660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/text_encoder_2/config.json",
+      "size": 575,
+      "sha256": "a892d1c3a69a7e9247a24de2bc1d5891e3109a54696e53be20093af671072c34",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/text_encoder_2/model.fp16.safetensors",
+      "size": 1389382176,
+      "sha256": "ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/tokenizer/merges.txt",
+      "size": 524619,
+      "sha256": "9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/tokenizer/special_tokens_map.json",
+      "size": 472,
+      "sha256": "c4864a9376a8401918425bed71fc14fc0e81f9b59ec45c1cf96cccb2df508eac",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/tokenizer/tokenizer_config.json",
+      "size": 737,
+      "sha256": "19d7b034cb0cc3ce9766c2231373ab8aa8991fc72e2c8f76558bfaae3de0d563",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/tokenizer/vocab.json",
+      "size": 1059962,
+      "sha256": "e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/tokenizer_2/merges.txt",
+      "size": 524619,
+      "sha256": "9fd691f7c8039210e0fced15865466c65820d09b63988b0174bfe25de299051a",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/tokenizer_2/special_tokens_map.json",
+      "size": 460,
+      "sha256": "f118ab3a983206e4f32583448de6bd6aae4ee21869135cef1f5848a753cdaab6",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/tokenizer_2/tokenizer_config.json",
+      "size": 725,
+      "sha256": "c9d23941f76a41cbd50eda9290f57be7828f0a7a677939e9ef181f7e12bd1bdf",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/tokenizer_2/vocab.json",
+      "size": 1059962,
+      "sha256": "e089ad92ba36837a0d31433e555c8f45fe601ab5c221d4f607ded32d9f7a4349",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/unet/config.json",
+      "size": 1680,
+      "sha256": "30ebc70750223e59006f7f2b4e1e6c102570aa19a9c4ae3e1fbe7591332dbae6",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/unet/diffusion_pytorch_model.fp16.safetensors",
+      "size": 5135149760,
+      "sha256": "83e012a805b84c7ca28e5646747c90a243c65c8ba4f070e2d7ddc9d74661e139",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/vae/config.json",
+      "size": 642,
+      "sha256": "0b331c8ac22ded5f9997a144a575c1d113d6169aff262c353f39015bd24a6264",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/sdxl/vae/diffusion_pytorch_model.fp16.safetensors",
+      "size": 167335342,
+      "sha256": "bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/vae/config.json",
+      "size": 631,
+      "sha256": "f18b16fa4381c90ab44a3d7abd2e90afd05a2c31b8ca69998bc93c6453aeb7b7",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "pose_diffusion/vae/diffusion_pytorch_model.safetensors",
+      "size": 334643238,
+      "sha256": "1b909373b28f2137098b0fd9dbc6f97f8410854f31f84ddc9fa04b077b0ace2c",
+      "group": "sdxl_optional",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/.gitattributes",
+      "size": 2312,
+      "sha256": "e2084e8b0bcc1a160e299fbfd868671fb3baf443aaab086675fc0b333eef094d",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/LICENSE",
+      "size": 7831,
+      "sha256": "8dc973f024ff95966bea25866efa443fd16776dcb1001e681e3d467ea572b28d",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/NOTICE",
+      "size": 148,
+      "sha256": "efa09ff399c8e4426b6e57e707c14e5db35258a290a15368a5bacd3e1e8381ab",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/README.md",
+      "size": 5398,
+      "sha256": "d4ec4b7e18642528b64ddadacc4a95a0ceb1bff1d5074f1d408a9ad2c253c483",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/assets/qr.png",
+      "size": 3172431,
+      "sha256": "9c3465cbd9fe1bdd974b91ef472890b98e43e9111f53477b5e8c2224761a2829",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/configuration.json",
+      "size": 34,
+      "sha256": "049315aecd90cb6b68dba11d203b118183bae4470b84b15a7945a4637b1e05f2",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/model_index.json",
+      "size": 447,
+      "sha256": "cf1ecd104ea090855d60d8cec0895c1e9d6ee41b2f87e231b678beecd1cf7809",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/processor/added_tokens.json",
+      "size": 707,
+      "sha256": "c0284b582e14987fbd3d5a2cb2bd139084371ed9acbae488829a1c900833c680",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/processor/chat_template.jinja",
+      "size": 5292,
+      "sha256": "3636d0f0bd6bef02654cdffdc447b79cb2cef8ab02cc75267345946291a489e4",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/processor/merges.txt",
+      "size": 1671853,
+      "sha256": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/processor/preprocessor_config.json",
+      "size": 782,
+      "sha256": "93585062a80db5e8ca038efc7726a3e6411d9db948472d81d63c6303993be8c5",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/processor/special_tokens_map.json",
+      "size": 613,
+      "sha256": "76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/processor/tokenizer.json",
+      "size": 11422654,
+      "sha256": "aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/processor/tokenizer_config.json",
+      "size": 5445,
+      "sha256": "81ec7bb9530159b326c0bef1d0b6c33d392090524014ea3f0123a3c1eb9c2af5",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/processor/video_preprocessor_config.json",
+      "size": 817,
+      "sha256": "59c5c9eb52182eb14c06ffb10ca9effd29adce5f238a95de23ca14a38dbd2cb1",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/processor/vocab.json",
+      "size": 2776833,
+      "sha256": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/scheduler/scheduler_config.json",
+      "size": 485,
+      "sha256": "5895f3a167c14a967fe9ac70c64924ae5acc79799e0679fd12907e594a713cd1",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/text_encoder/config.json",
+      "size": 1517,
+      "sha256": "6001331949f7f86ab6d791a80b12246d4f8da5159fa08c3e62368a39f36d63a9",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/text_encoder/generation_config.json",
+      "size": 213,
+      "sha256": "4d9818c3d27895c0058828a5f68bc7a4de80c3ae1bcdac90936ce24178063f59",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/text_encoder/model-00001-of-00004.safetensors",
+      "size": 4998056552,
+      "sha256": "dde00291b5f7fb92013895310a3da0ddba78674df9f10d505d375243dc01fc6f",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/text_encoder/model-00002-of-00004.safetensors",
+      "size": 4915962464,
+      "sha256": "9047faccc0a6d98496a52d55f27be1c94a9c259d1e283fbea0128d054a948d42",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/text_encoder/model-00003-of-00004.safetensors",
+      "size": 4915962496,
+      "sha256": "8c54187654c0176b73ae73785bf791dc9a14c9df7fb4310083a09d42048cb57e",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/text_encoder/model-00004-of-00004.safetensors",
+      "size": 2704357976,
+      "sha256": "5311532aaaeae3259eb6a7b2c600636be1159adf7ded35f53579f7d0e7d43cdd",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/text_encoder/model.safetensors.index.json",
+      "size": 67795,
+      "sha256": "859146bff8db1d617fca8b457a5223edff963bb70076b3645f2189fe0540a147",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/transformer/config.json",
+      "size": 370,
+      "sha256": "56ae3281c4e6c2d1aa3658252d187488071815fd79bef15808bb0205fc1a2241",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/transformer/diffusion_pytorch_model-00001-of-00002.safetensors",
+      "size": 9968332504,
+      "sha256": "9e6bc2d641e67bf277895ea8777141044a38f3edb7101bc469b2961dd7c36b4b",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/transformer/diffusion_pytorch_model-00002-of-00002.safetensors",
+      "size": 4261951904,
+      "sha256": "3aaf234dcbe128530479735854a346b5e3e66283b7c11db56f836bbd1c13ebaa",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/transformer/diffusion_pytorch_model.safetensors.index.json",
+      "size": 30283,
+      "sha256": "17987f6623b1c814d0ef55a137d99142b7b3b040eb1bf241b5575dd35af803a2",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/vae/config.json",
+      "size": 2079,
+      "sha256": "9785d527b278cb8b210e9f48a8028d92a4190968ce7e24c8fc85d9d1b82f6ba2",
+      "group": "qwen21",
+      "public_upload": true
+    },
+    {
+      "path": "qwenimage21/vae/diffusion_pytorch_model.safetensors",
+      "size": 1350989512,
+      "sha256": "a07a1b7c4ee2966a1b3bdc37de9b4f983d56937e46619f709a80b6e490675417",
+      "group": "qwen21",
+      "public_upload": true
+    }
+  ],
+  "public_bytes_total": 46206171474
+}

model_sources.json

@@ -0,0 +1,403 @@
+{
+  "format_version": 1,
+  "components": [
+    {
+      "component": "sdxl",
+      "local_paths": [
+        "pose_diffusion/sdxl/**"
+      ],
+      "upstream_repository": "stabilityai/stable-diffusion-xl-base-1.0",
+      "source_revision": "462165984030d82259a11f4367a4eed129e94a7b",
+      "model_license_declared": "CreativeML Open RAIL++-M, dated July 26, 2023",
+      "evidence_url": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/462165984030d82259a11f4367a4eed129e94a7b/README.md",
+      "sha256_identity_matches": [
+        {
+          "file": "unet/diffusion_pytorch_model.fp16.safetensors",
+          "sha256": "83e012a805b84c7ca28e5646747c90a243c65c8ba4f070e2d7ddc9d74661e139"
+        }
+      ],
+      "license_documents": [
+        "SDXL_CreativeML_Open_RAIL_pp_M_LICENSE.md"
+      ],
+      "redistribution_assessment": "subject_to_license",
+      "notes": [
+        "Official SDXL model license applies to base weights. Retain license, model card, notices, and applicable downstream use restrictions.",
+        "UNet fp16 SHA matches official repository; remainder provenance is in local_weights_copy_manifest.json."
+      ]
+    },
+    {
+      "component": "controlnet",
+      "local_paths": [
+        "pose_diffusion/controlnet/**"
+      ],
+      "upstream_repository": "thibaud/controlnet-openpose-sdxl-1.0",
+      "source_revision": "1db673ed3dad75181fcf2e24f827597fe34e97b7",
+      "model_license_declared": "other; model card refers to OpenPose license",
+      "evidence_url": "https://huggingface.co/thibaud/controlnet-openpose-sdxl-1.0/blob/1db673ed3dad75181fcf2e24f827597fe34e97b7/README.md",
+      "sha256_identity_matches": [],
+      "license_documents": [
+        "OpenPose_RESTRICTED_reference_LICENSE.txt"
+      ],
+      "redistribution_assessment": "restricted_do_not_mirror",
+      "notes": [
+        "Pinned model card says: License refers to OpenPose\u2019s one.",
+        "OpenPose license grants non-transferable, noncommercial internal research use and prohibits distribution/sublicensing/third-party access.",
+        "Keep local complete weights; omit ControlNet binary from public Hugging Face mirror unless separate redistribution permission is documented. Point users to upstream and its terms.",
+        "This is an evidence-based conservative release assessment of the model card reference, not a claim that OpenPose software itself is embedded in the ControlNet file."
+      ]
+    },
+    {
+      "component": "ip_adapter",
+      "local_paths": [
+        "pose_diffusion/ip_adapter/ip-adapter_sdxl_vit-h.safetensors"
+      ],
+      "upstream_repository": "h94/IP-Adapter",
+      "source_revision": "018e402774aeeddd60609b4ecdb7e298259dc729",
+      "model_license_declared": "Apache-2.0",
+      "evidence_url": "https://huggingface.co/h94/IP-Adapter/blob/018e402774aeeddd60609b4ecdb7e298259dc729/README.md",
+      "sha256_identity_matches": [
+        {
+          "file": "sdxl_models/ip-adapter_sdxl_vit-h.safetensors",
+          "sha256": "ebf05d918348aec7abb02a5e9ecef77e0aaea6914a5c4ea13f50d45eb1681831"
+        }
+      ],
+      "license_documents": [
+        "IP_Adapter_Apache_2.0_LICENSE.txt"
+      ],
+      "redistribution_assessment": "subject_to_license",
+      "notes": [
+        "Adapter binary SHA exactly matches h94/IP-Adapter sdxl_models/ip-adapter_sdxl_vit-h.safetensors.",
+        "Model card declares Apache-2.0; full text available from official Tencent IP-Adapter source. Preserve license and source notices."
+      ]
+    },
+    {
+      "component": "clip_h",
+      "local_paths": [
+        "pose_diffusion/ip_adapter/image_encoder_h2/**"
+      ],
+      "upstream_repository": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
+      "source_revision": "1c2b8495b28150b8a4922ee1c8edee224c284c0c",
+      "model_license_declared": "MIT",
+      "evidence_url": "https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K/blob/1c2b8495b28150b8a4922ee1c8edee224c284c0c/README.md",
+      "sha256_identity_matches": [
+        {
+          "file": "model.safetensors",
+          "sha256": "036e6e2bd49697511f4f8b8cb5ee465f93025f7a69a145eadeb9a881ace9b18d"
+        }
+      ],
+      "license_documents": [
+        "OpenCLIP_MIT_LICENSE.txt",
+        "MIT_template_SPDX_reference.txt"
+      ],
+      "redistribution_assessment": "subject_to_license",
+      "notes": [
+        "The local complete CLIPModel safetensors SHA exactly matches laion/CLIP-ViT-H-14-laion2B-s32B-b79K/model.safetensors. Identification is based on the weight digest, not architecture alone.",
+        "The model card declares MIT. Preserve its model card; OpenCLIP upstream MIT text is saved with original copyright names."
+      ]
+    },
+    {
+      "component": "vae",
+      "local_paths": [
+        "pose_diffusion/vae/**"
+      ],
+      "upstream_repository": "madebyollin/sdxl-vae-fp16-fix",
+      "source_revision": "207b116dae70ace3637169f1ddd2434b91b3a8cd",
+      "model_license_declared": "MIT",
+      "evidence_url": "https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/blob/207b116dae70ace3637169f1ddd2434b91b3a8cd/README.md",
+      "sha256_identity_matches": [
+        {
+          "file": "diffusion_pytorch_model.safetensors",
+          "sha256": "1b909373b28f2137098b0fd9dbc6f97f8410854f31f84ddc9fa04b077b0ace2c"
+        }
+      ],
+      "license_documents": [
+        "MIT_template_SPDX_reference.txt",
+        "SDXL_CreativeML_Open_RAIL_pp_M_LICENSE.md"
+      ],
+      "redistribution_assessment": "subject_to_license",
+      "notes": [
+        "The local weight SHA exactly matches madebyollin/sdxl-vae-fp16-fix/diffusion_pytorch_model.safetensors.",
+        "The repository declares MIT but does not contain a dedicated LICENSE/NOTICE file. Retain its original model card and full MIT reference text; do not invent a copyright holder.",
+        "The model card identifies this as a modified SDXL-VAE 0.9 model. Preserve underlying SDXL provenance/restrictions as applicable rather than describing every SDXL component as solely MIT."
+      ]
+    },
+    {
+      "component": "layerdiffuse_decoder",
+      "local_paths": [
+        "pose_diffusion/layerdiffuse/vae_transparent_decoder.safetensors"
+      ],
+      "upstream_repository": "LayerDiffusion/layerdiffusion-v1",
+      "source_revision": "e337e9d7a0f2a6fee6c3580374327380f88d065b",
+      "model_license_declared": "CreativeML Open RAIL-M",
+      "evidence_url": "https://huggingface.co/LayerDiffusion/layerdiffusion-v1/blob/e337e9d7a0f2a6fee6c3580374327380f88d065b/README.md",
+      "sha256_identity_matches": [],
+      "license_documents": [
+        "CreativeML_Open_RAIL_M_reference_LICENSE.txt",
+        "LayerDiffusion_original_code_Apache_2.0_LICENSE.txt"
+      ],
+      "redistribution_assessment": "subject_to_license",
+      "notes": [
+        "Pinned HF model metadata declares creativeml-openrail-m. No dedicated LICENSE file is present in that model repository.",
+        "Original LayerDiffusion implementation code has Apache-2.0, which is distinct from the model-card weight license.",
+        "CreativeML Open RAIL-M full text from original CompVis release is stored as an explicitly labeled license reference; retain the LayerDiffusion model card and attribution. Do not relabel the decoder as Apache-2.0 or MIT."
+      ]
+    },
+    {
+      "component": "layerdiffuse_attention",
+      "local_paths": [
+        "pose_diffusion/layerdiffuse/diffuser_layer_xl_transparent_attn.safetensors"
+      ],
+      "upstream_repository": "rootonchair/diffuser_layerdiffuse",
+      "source_revision": "2c97b46a3c3f997ef31906b00f3db4f54ebf3f42",
+      "model_license_declared": "MIT in conversion repository; original LayerDiffusion weight terms retained",
+      "evidence_url": "https://huggingface.co/rootonchair/diffuser_layerdiffuse/blob/2c97b46a3c3f997ef31906b00f3db4f54ebf3f42/README.md",
+      "sha256_identity_matches": [],
+      "license_documents": [
+        "LayerDiffuse_conversion_MIT_LICENSE.txt",
+        "CreativeML_Open_RAIL_M_reference_LICENSE.txt"
+      ],
+      "redistribution_assessment": "subject_to_license",
+      "notes": [
+        "Pinned rootonchair model card declares MIT for the Diffusers port. Its source repository identifies a port of original sd-forge-layerdiffuse weights.",
+        "Treat MIT as conversion/source license; preserve original LayerDiffusion Open RAIL-M model provenance and use restrictions for the converted original weight rather than claiming a conversion removes upstream terms.",
+        "Local binary SHA/revision verification is recorded in download_manifest_extra.json."
+      ]
+    },
+    {
+      "component": "flexdm_design_encoder",
+      "local_paths": [
+        "flexdm/design_encoder.pt",
+        "flexdm/metadata.json",
+        "flexdm/provenance.json"
+      ],
+      "upstream_code_repository": "https://github.com/CyberAgentAILab/flex-dm",
+      "upstream_code_license": "Apache-2.0",
+      "model_license_declared": "No separate explicit model-weight license located; locally trained project checkpoint supplied by owner. Do not automatically assign code license to checkpoint.",
+      "local_training_source": {
+        "checkpoint": "opensource/flexdm/runs/full_20261013/exp_ft/best.pt",
+        "sha256": "6ed6cb3e12eb0f83107b73da4e401d404ad56a1c782650c96d0fe82cac1c486a",
+        "epoch": 90,
+        "global_step": 6570,
+        "selection": "EXP-FT best validation checkpoint after IMP 500 epochs"
+      },
+      "extracted_checkpoint_sha256": "b75c3dab8a1f5e4f9dd7b6fb8c43f82a4ec11143545329e9937e291a58fc5e01",
+      "tensor_count": 78,
+      "source_model_tensor_count": 98,
+      "notes": [
+        "The release encoder is strictly extracted from the local full-training best checkpoint, not a renamed public TensorFlow checkpoint.",
+        "Original public FlexDM Crello pretrained weights are separately linked by upstream README at https://storage.googleapis.com/ailab-public/flexdm/pretrained_weights/crello.zip; they are not the immediate source checkpoint of this encoder.",
+        "Local supplied source LICENSE is byte-identical to official CyberAgentAILab/flex-dm/LICENSE. The owner can specify license for locally trained model weights separately from upstream code."
+      ],
+      "license_documents": [
+        "FlexDM_Apache_2.0_LICENSE.txt"
+      ],
+      "redistribution_assessment": "owner_supplied_locally_trained_model_separate_license_not_found"
+    },
+    {
+      "component": "pose_tokenizer",
+      "local_paths": [
+        "pose/52joints_tokenization.pth"
+      ],
+      "immediate_source": "Design-pose-MM/design2pose_dualTrainning/pretrained_model/52joints_tokenization.pth",
+      "source_evidence": "HumanAware/vendor/render/PROVENANCE.json",
+      "upstream_public_repository": null,
+      "model_license_declared": null,
+      "notes": [
+        "User-provided original-project model; no public source/license identified from original project directory or exact-filename/class-name web searches.",
+        "Checkpoint has top-level net and hparams. hparams identifies amass_pose and 52-joint processed data; this does not establish checkpoint ownership or a redistribution license.",
+        "Do not describe this checkpoint as Apache-2.0 merely because nearby FlexDM code uses Apache. Record provenance and retain any owner-supplied terms."
+      ],
+      "redistribution_assessment": "owner_supplied_original_project_model_public_license_not_found"
+    },
+    {
+      "component": "qwenimage21",
+      "local_paths": [
+        "qwenimage21/**"
+      ],
+      "model_license_declared": "Qwen RESEARCH LICENSE AGREEMENT, Release Date September 20, 2026",
+      "source_evidence": "weight/qwenimage21/LICENSE",
+      "redistribution_assessment": "noncommercial_research_or_evaluation_only_subject_to_redistribution_conditions",
+      "notes": [
+        "Parent release workflow independently confirmed this model license. The local license allows noncommercial redistribution with its agreement, modification notices, and specified Notice attribution.",
+        "Keep original LICENSE and README; do not call Qwen Image 2.1 Apache-2.0."
+      ]
+    },
+    {
+      "component": "smplx_body_model",
+      "local_paths": [
+        "body_models/smplx/SMPLX_NEUTRAL.npz"
+      ],
+      "redistribution_assessment": "excluded_from_public_upload_separate_user_license_required",
+      "notes": [
+        "Not part of public model mirror. Users must obtain authorized SMPL-X model assets separately under original terms. Parent workflow confirmed this restriction."
+      ]
+    }
+  ],
+  "official_license_document_urls": {
+    "sdxl": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/raw/main/LICENSE.md",
+    "ip_adapter": "https://raw.githubusercontent.com/tencent-ailab/IP-Adapter/main/LICENSE",
+    "openclip": "https://raw.githubusercontent.com/mlfoundations/open_clip/main/LICENSE",
+    "flexdm": "https://raw.githubusercontent.com/CyberAgentAILab/flex-dm/main/LICENSE",
+    "layerdiffuse_port": "https://raw.githubusercontent.com/rootonchair/diffuser_layerdiffuse/main/LICENSE",
+    "layerdiffuse_original_code": "https://raw.githubusercontent.com/lllyasviel/sd-forge-layerdiffuse/main/LICENSE",
+    "layerdiffuse_openrail_m_reference": "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/LICENSE",
+    "pytorch3d": "https://raw.githubusercontent.com/facebookresearch/pytorch3d/main/LICENSE",
+    "openpose_restricted": "https://raw.githubusercontent.com/CMU-Perceptual-Computing-Lab/openpose/master/LICENSE",
+    "mit_template_reference": "https://raw.githubusercontent.com/spdx/license-list-data/main/text/MIT.txt"
+  },
+  "verified_server_copy_sources": [
+    {
+      "path_in_repo": "pose_diffusion/ip_adapter/image_encoder_h2/model.safetensors",
+      "size": 3944552236,
+      "sha256": "036e6e2bd49697511f4f8b8cb5ee465f93025f7a69a145eadeb9a881ace9b18d",
+      "src_repo_id": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
+      "src_repo_type": "model",
+      "src_revision": "1c2b8495b28150b8a4922ee1c8edee224c284c0c",
+      "src_path_in_repo": "model.safetensors"
+    },
+    {
+      "path_in_repo": "pose_diffusion/ip_adapter/ip-adapter_sdxl_vit-h.safetensors",
+      "size": 698391064,
+      "sha256": "ebf05d918348aec7abb02a5e9ecef77e0aaea6914a5c4ea13f50d45eb1681831",
+      "src_repo_id": "h94/IP-Adapter",
+      "src_repo_type": "model",
+      "src_revision": "018e402774aeeddd60609b4ecdb7e298259dc729",
+      "src_path_in_repo": "sdxl_models/ip-adapter_sdxl_vit-h.safetensors"
+    },
+    {
+      "path_in_repo": "pose_diffusion/layerdiffuse/diffuser_layer_xl_transparent_attn.safetensors",
+      "size": 743345968,
+      "sha256": "2626f9aa142f260c12336af754e6003661fbd75c467ecb3906f94783cc2b1b42",
+      "src_repo_id": "rootonchair/diffuser_layerdiffuse",
+      "src_repo_type": "model",
+      "src_revision": "2c97b46a3c3f997ef31906b00f3db4f54ebf3f42",
+      "src_path_in_repo": "diffuser_layer_xl_transparent_attn.safetensors"
+    },
+    {
+      "path_in_repo": "pose_diffusion/layerdiffuse/vae_transparent_decoder.safetensors",
+      "size": 208266320,
+      "sha256": "59dc8feefe40d26b6cb7186aed7af70c60d94ac4f9db8ebe7f121a01ba27a2fc",
+      "src_repo_id": "LayerDiffusion/layerdiffusion-v1",
+      "src_repo_type": "model",
+      "src_revision": "e337e9d7a0f2a6fee6c3580374327380f88d065b",
+      "src_path_in_repo": "vae_transparent_decoder.safetensors"
+    },
+    {
+      "path_in_repo": "pose_diffusion/sdxl/text_encoder/model.fp16.safetensors",
+      "size": 246144152,
+      "sha256": "660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd",
+      "src_repo_id": "stabilityai/stable-diffusion-xl-base-1.0",
+      "src_repo_type": "model",
+      "src_revision": "462165984030d82259a11f4367a4eed129e94a7b",
+      "src_path_in_repo": "text_encoder/model.fp16.safetensors"
+    },
+    {
+      "path_in_repo": "pose_diffusion/sdxl/text_encoder_2/model.fp16.safetensors",
+      "size": 1389382176,
+      "sha256": "ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4",
+      "src_repo_id": "stabilityai/stable-diffusion-xl-base-1.0",
+      "src_repo_type": "model",
+      "src_revision": "462165984030d82259a11f4367a4eed129e94a7b",
+      "src_path_in_repo": "text_encoder_2/model.fp16.safetensors"
+    },
+    {
+      "path_in_repo": "pose_diffusion/sdxl/unet/diffusion_pytorch_model.fp16.safetensors",
+      "size": 5135149760,
+      "sha256": "83e012a805b84c7ca28e5646747c90a243c65c8ba4f070e2d7ddc9d74661e139",
+      "src_repo_id": "stabilityai/stable-diffusion-xl-base-1.0",
+      "src_repo_type": "model",
+      "src_revision": "462165984030d82259a11f4367a4eed129e94a7b",
+      "src_path_in_repo": "unet/diffusion_pytorch_model.fp16.safetensors"
+    },
+    {
+      "path_in_repo": "pose_diffusion/sdxl/vae/diffusion_pytorch_model.fp16.safetensors",
+      "size": 167335342,
+      "sha256": "bcb60880a46b63dea58e9bc591abe15f8350bde47b405f9c38f4be70c6161e68",
+      "src_repo_id": "stabilityai/stable-diffusion-xl-base-1.0",
+      "src_repo_type": "model",
+      "src_revision": "462165984030d82259a11f4367a4eed129e94a7b",
+      "src_path_in_repo": "vae/diffusion_pytorch_model.fp16.safetensors"
+    },
+    {
+      "path_in_repo": "pose_diffusion/vae/diffusion_pytorch_model.safetensors",
+      "size": 334643238,
+      "sha256": "1b909373b28f2137098b0fd9dbc6f97f8410854f31f84ddc9fa04b077b0ace2c",
+      "src_repo_id": "madebyollin/sdxl-vae-fp16-fix",
+      "src_repo_type": "model",
+      "src_revision": "207b116dae70ace3637169f1ddd2434b91b3a8cd",
+      "src_path_in_repo": "diffusion_pytorch_model.safetensors"
+    },
+    {
+      "path_in_repo": "qwenimage21/processor/tokenizer.json",
+      "size": 11422654,
+      "sha256": "aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4",
+      "src_repo_id": "Qwen/Qwen-Image-2.1",
+      "src_repo_type": "model",
+      "src_revision": "d26bb61231c349cf6b7896fa83353113880e1ba3",
+      "src_path_in_repo": "processor/tokenizer.json"
+    },
+    {
+      "path_in_repo": "qwenimage21/text_encoder/model-00001-of-00004.safetensors",
+      "size": 4998056552,
+      "sha256": "dde00291b5f7fb92013895310a3da0ddba78674df9f10d505d375243dc01fc6f",
+      "src_repo_id": "Qwen/Qwen-Image-2.1",
+      "src_repo_type": "model",
+      "src_revision": "d26bb61231c349cf6b7896fa83353113880e1ba3",
+      "src_path_in_repo": "text_encoder/model-00001-of-00004.safetensors"
+    },
+    {
+      "path_in_repo": "qwenimage21/text_encoder/model-00002-of-00004.safetensors",
+      "size": 4915962464,
+      "sha256": "9047faccc0a6d98496a52d55f27be1c94a9c259d1e283fbea0128d054a948d42",
+      "src_repo_id": "Qwen/Qwen-Image-2.1",
+      "src_repo_type": "model",
+      "src_revision": "d26bb61231c349cf6b7896fa83353113880e1ba3",
+      "src_path_in_repo": "text_encoder/model-00002-of-00004.safetensors"
+    },
+    {
+      "path_in_repo": "qwenimage21/text_encoder/model-00003-of-00004.safetensors",
+      "size": 4915962496,
+      "sha256": "8c54187654c0176b73ae73785bf791dc9a14c9df7fb4310083a09d42048cb57e",
+      "src_repo_id": "Qwen/Qwen-Image-2.1",
+      "src_repo_type": "model",
+      "src_revision": "d26bb61231c349cf6b7896fa83353113880e1ba3",
+      "src_path_in_repo": "text_encoder/model-00003-of-00004.safetensors"
+    },
+    {
+      "path_in_repo": "qwenimage21/text_encoder/model-00004-of-00004.safetensors",
+      "size": 2704357976,
+      "sha256": "5311532aaaeae3259eb6a7b2c600636be1159adf7ded35f53579f7d0e7d43cdd",
+      "src_repo_id": "Qwen/Qwen-Image-2.1",
+      "src_repo_type": "model",
+      "src_revision": "d26bb61231c349cf6b7896fa83353113880e1ba3",
+      "src_path_in_repo": "text_encoder/model-00004-of-00004.safetensors"
+    },
+    {
+      "path_in_repo": "qwenimage21/transformer/diffusion_pytorch_model-00001-of-00002.safetensors",
+      "size": 9968332504,
+      "sha256": "9e6bc2d641e67bf277895ea8777141044a38f3edb7101bc469b2961dd7c36b4b",
+      "src_repo_id": "Qwen/Qwen-Image-2.1",
+      "src_repo_type": "model",
+      "src_revision": "d26bb61231c349cf6b7896fa83353113880e1ba3",
+      "src_path_in_repo": "transformer/diffusion_pytorch_model-00001-of-00002.safetensors"
+    },
+    {
+      "path_in_repo": "qwenimage21/transformer/diffusion_pytorch_model-00002-of-00002.safetensors",
+      "size": 4261951904,
+      "sha256": "3aaf234dcbe128530479735854a346b5e3e66283b7c11db56f836bbd1c13ebaa",
+      "src_repo_id": "Qwen/Qwen-Image-2.1",
+      "src_repo_type": "model",
+      "src_revision": "d26bb61231c349cf6b7896fa83353113880e1ba3",
+      "src_path_in_repo": "transformer/diffusion_pytorch_model-00002-of-00002.safetensors"
+    },
+    {
+      "path_in_repo": "qwenimage21/vae/diffusion_pytorch_model.safetensors",
+      "size": 1350989512,
+      "sha256": "a07a1b7c4ee2966a1b3bdc37de9b4f983d56937e46619f709a80b6e490675417",
+      "src_repo_id": "Qwen/Qwen-Image-2.1",
+      "src_repo_type": "model",
+      "src_revision": "d26bb61231c349cf6b7896fa83353113880e1ba3",
+      "src_path_in_repo": "vae/diffusion_pytorch_model.safetensors"
+    }
+  ]
+}

pose/52joints_tokenization.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0893481b5b6941f965c125dd10626fb91d28a51e04b3f3c3f330bb9e19a6d92d
+size 52630720

pose_diffusion/ip_adapter/image_encoder_h2/config.json

@@ -0,0 +1,179 @@
+{
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 1024,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 1024,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.21.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": {
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "projection_dim": 1024
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 5120,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 32,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 1024,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.21.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "intermediate_size": 5120,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "patch_size": 14,
+    "projection_dim": 1024
+  }
+}

pose_diffusion/sdxl/model_index.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.19.0.dev0",
+  "force_zeros_for_empty_prompt": true,
+  "add_watermarker": null,
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

pose_diffusion/sdxl/scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.19.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

pose_diffusion/sdxl/text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0.dev0",
+  "vocab_size": 49408
+}

pose_diffusion/sdxl/text_encoder_2/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0.dev0",
+  "vocab_size": 49408
+}

pose_diffusion/sdxl/tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

pose_diffusion/sdxl/tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

pose_diffusion/sdxl/tokenizer_2/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

pose_diffusion/sdxl/tokenizer_2/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

pose_diffusion/sdxl/unet/config.json

@@ -0,0 +1,69 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.19.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

pose_diffusion/sdxl/vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.20.0.dev0",
+  "_name_or_path": "../sdxl-vae/",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

pose_diffusion/vae/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.18.0.dev0",
+  "_name_or_path": ".",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.13025,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "force_upcast": false
+}

qwenimage21/.gitattributes

@@ -0,0 +1,51 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+"/processor/merges.txt" filter=lfs diff=lfs merge=lfs -text
+"/processor/tokenizer.json" filter=lfs diff=lfs merge=lfs -text
+"/processor/vocab.json" filter=lfs diff=lfs merge=lfs -text
+"/assets/qr.png" filter=lfs diff=lfs merge=lfs -text

qwenimage21/LICENSE

@@ -0,0 +1,55 @@
+Qwen RESEARCH LICENSE AGREEMENT
+
+Qwen RESEARCH LICENSE AGREEMENT Release Date: September 20, 2026
+
+By clicking to agree or by using or distributing any portion or element of the Qwen Materials, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately.
+
+1. Definitions
+    a. This Qwen RESEARCH LICENSE AGREEMENT (this "Agreement") shall mean the terms and conditions for use, reproduction, distribution and modification of the Materials as defined by this Agreement.
+    b. "We" (or "Us") shall mean Hangzhou Tongyi Laboratory Technology Co., Ltd.
+    c. "You" (or "Your") shall mean a natural person or legal entity exercising the rights granted by this Agreement and/or using the Materials for any purpose and in any field of use.
+    d. "Third Parties" shall mean individuals or legal entities that are not under common control with us or you.
+    e. "Qwen" shall mean the large language models, diffusion models, and software and algorithms, consisting of trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by us.
+    f. "Materials" shall mean, collectively, our proprietary Qwen and Documentation (and any portion thereof) made available under this Agreement.
+    g. "Source" form shall mean the preferred form for making modifications, including but not limited to model source code, documentation source, and configuration files.
+    h. "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.
+    i. "Non-Commercial" shall mean for research or evaluation purposes only.
+
+2. Grant of Rights
+    a. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under our intellectual property or other rights owned by us embodied in the Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Materials FOR NON-COMMERCIAL PURPOSES ONLY. 
+    b. You shall not use the Materials for any commercial purpose without obtaining a separate commercial license from us. If you wish to use the Materials commercially, you shall request a license from us at model-business@notice.qwencloud.com.
+
+3. Redistribution
+Subject to Section 2 (Grant of Rights), you may distribute copies or make the Materials, or derivative works thereof, available as part of a product or service that contains any of them, with or without modifications, and in Source or Object form, provided that you meet the following conditions:
+    a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement;
+    b. You shall cause any modified files to carry prominent notices stating that you changed the files;
+    c. You shall retain in all copies of the Materials that you distribute the following attribution notices within a "Notice" text file distributed as a part of such copies: "Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved."; and
+    d. 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 terms and conditions of this Agreement.
+
+4. Rules of use
+    a. The Materials may be subject to export controls or restrictions in China, the United States or other countries or regions. You shall comply with applicable laws and regulations in your use of the Materials.
+    b. If you use the Materials or any outputs or results therefrom to create, train, fine-tune, or improve an AI model that is distributed or made available, you shall prominently display “Built with Qwen” or “Improved using Qwen” in the related product documentation.
+    c. You shall not use "Qwen" as the primary name or identifier of any derivative works or products; reasonable descriptive use (e.g., "fine-tuned from Qwen Image") is permitted.
+
+5. Intellectual Property
+    a. We retain ownership of all intellectual property rights in and to the Materials and derivatives made by or for us. Conditioned upon compliance with the terms and conditions of this Agreement, with respect to any derivative works and modifications of the Materials that are made by you, you are and will be the owner of such derivative works and modifications.
+    b. No trademark license is granted to use the trade names, trademarks, service marks, or product names of us, except as required to fulfill notice requirements under this Agreement or as required for reasonable and customary use in describing and redistributing the Materials.
+    c. If you commence a lawsuit or other proceedings (including a cross-claim or counterclaim in a lawsuit) against us or any entity alleging that the Materials or any output therefrom, or any part of the foregoing, infringe any intellectual property or other right owned or licensable by you, then all licenses granted to you under this Agreement shall terminate as of the date such lawsuit or other proceeding is commenced or brought.
+
+6. Disclaimer of Warranty and Limitation of Liability
+    a. We are not obligated to support, update, provide training for, or develop any further version of the Qwen Materials or to grant any license thereto.
+    b. THE MATERIALS ARE PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. WE MAKE NO WARRANTY AND ASSUME NO RESPONSIBILITY FOR THE SAFETY OR STABILITY OF THE MATERIALS AND ANY OUTPUT THEREFROM.
+    c. IN NO EVENT SHALL WE BE LIABLE TO YOU FOR ANY DAMAGES, INCLUDING, BUT NOT LIMITED TO ANY DIRECT, OR INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OR INABILITY TO USE THE MATERIALS OR ANY OUTPUT OF IT, NO MATTER HOW IT’S CAUSED.
+    d. You will defend, indemnify and hold harmless us from and against any claim by any third party arising out of or related to your use or distribution of the Materials.
+
+7. Survival and Termination.
+    a. The term of this Agreement shall commence upon your acceptance of this Agreement or access to the Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein.
+    b. We may terminate this Agreement if you breach any of the terms or conditions of this Agreement. Upon termination of this Agreement, you must delete and cease use of the Materials. Sections 6 and 8 shall survive the termination of this Agreement.
+
+8. Governing Law and Jurisdiction.
+    a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of China, without regard to conflict of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
+    b. The People's Courts in Hangzhou City shall have exclusive jurisdiction over any dispute arising out of this Agreement.
+
+9. Other Terms and Conditions.
+    a. Any arrangements, understandings, or agreements regarding the Material not stated herein are separate from and independent of the terms and conditions of this Agreement. You shall request a separate license from us, if you use the Materials in ways not expressly agreed to in this Agreement. 
+    b. We shall not be bound by any additional or different terms or conditions communicated by you unless expressly agreed.

qwenimage21/NOTICE

@@ -0,0 +1 @@
+Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) 2026 Hangzhou Tongyi Laboratory Technology Co., Ltd. All Rights Reserved.

qwenimage21/README.md

@@ -0,0 +1,162 @@
+---
+base_model:
+- ""
+frameworks:
+- ""
+license: other
+license_link: LICENSE
+license_name: qwen-research
+pipeline_tag: text-to-image
+tags:
+- diffusers
+- qwen
+- image-generation
+- image-editing
+- rgba
+---
+
+<p align="center">
+    <img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/image2.1/logo.png" width="400"/>
+</p>
+<p align="center">
+    🤖 <a href="https://modelscope.cn/models/Qwen/Qwen-Image-2.1">ModelScope</a>&nbsp;&nbsp;|
+    &nbsp;&nbsp;🤗 <a href="https://huggingface.co/Qwen/Qwen-Image-2.1">HuggingFace</a>&nbsp;&nbsp;|
+    &nbsp;&nbsp;📑 <a href="https://qwen.ai/blog?id=qwen-image-2.1">Blog</a>&nbsp;&nbsp;|
+    &nbsp;&nbsp;🖥️ <a href="https://huggingface.co/spaces/Qwen/Qwen-Image-2.1">Demo</a>&nbsp;&nbsp;|
+    &nbsp;&nbsp;🫨 <a href="https://discord.gg/BEYSk3pkSu">Discord</a>&nbsp;&nbsp;|
+    &nbsp;&nbsp;💬 <a href="https://modelscope.cn/models/Qwen/Qwen-Image-2.1/file/view/master/assets%2Fqr.png">WeChat</a>
+</p>
+
+## Introduction
+
+We are excited to open-source **Qwen-Image-2.1**, a unified text-to-image generation and image editing model in the Qwen family. With just **7B parameters in its visual generation component** (32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility.
+
+Four key improvements define this release:
+
+- **Compact and Efficient** — A lightweight architecture with mixed-granularity attention and prefix KV cache reuse delivers strong image quality at low computational cost.
+- **Native Transparency, Unified Creation and Editing** — Generate regular or transparent (RGBA) images from text, edit transparent layers, and extract subjects from photographs—all in one model.
+- **Versatile Editing** — Support up to **10 reference images**, specify local edits via circles, painted annotations, or separate masks, and preserve identity for people and products.
+- **Realistic Textures and Refined Aesthetics** — Improved typography, portrait lighting, and fine details for more visually compelling results.
+
+<p align="center">
+    <img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-01.png" width="100%"/>
+</p>
+
+For more details, see the [GitHub repo](https://github.com/QwenLM/Qwen-Image-2.1) and [Blog](https://qwen.ai/blog?id=qwen-image-2.1).
+
+## Quick Start
+
+### Installation
+
+```bash
+pip install torch>=2.4.0
+pip install transformers>=5.17
+pip install git+https://github.com/huggingface/diffusers
+pip install accelerate pillow
+```
+
+### Text-to-Image
+
+```python
+import torch
+from diffusers import QwenImage21Pipeline
+
+pipe = QwenImage21Pipeline.from_pretrained(
+    "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16
+).to("cuda")
+
+image = pipe(
+    prompt="A neon shop sign that reads \"QWEN IMAGE 2.1\", rainy night, reflections on wet pavement",
+    width=2048, height=2048,
+    num_inference_steps=40,
+    generator=torch.Generator("cuda").manual_seed(42),
+).images[0]
+
+image.save("t2i_example.png")
+```
+
+### Image Editing
+
+```python
+import torch
+from PIL import Image
+from diffusers import QwenImage21Pipeline
+
+pipe = QwenImage21Pipeline.from_pretrained(
+    "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16
+).to("cuda")
+
+input_image = Image.open("input.png")
+
+image = pipe(
+    prompt="Change the background to a sunset beach",
+    image=input_image,
+    num_inference_steps=40,
+    generator=torch.Generator("cuda").manual_seed(42),
+).images[0]
+
+image.save("edit_example.png")
+```
+
+### Transparent Image Generation (RGBA)
+
+Use the recommended prompt format for transparent images:
+
+```python
+image = pipe(
+    prompt="This is an RGBA image with transparency. A cute cartoon dragon sticker. The image has alpha channel and the background is transparent.",
+    width=2048, height=2048,
+    num_inference_steps=40,
+    generator=torch.Generator("cuda").manual_seed(42),
+).images[0]
+
+image.save("transparent_example.png")
+```
+
+### Supported Aspect Ratios
+
+```python
+aspect_ratios = {
+    "1:1":  (2048, 2048),
+    "4:3":  (2400, 1792),
+    "3:4":  (1792, 2400),
+    "3:2":  (2528, 1696),
+    "2:3":  (1696, 2528),
+    "16:9": (2752, 1536),
+    "9:16": (1536, 2752),
+}
+```
+
+### Memory Optimization
+
+```python
+pipe = QwenImage21Pipeline.from_pretrained(
+    "Qwen/Qwen-Image-2.1", torch_dtype=torch.bfloat16
+)
+pipe.enable_model_cpu_offload()
+```
+
+## Showcase
+
+<p align="center">
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-04.png" width="30%"/>
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-05.png" width="30%"/>
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-06.png" width="30%"/>
+</p>
+<p align="center"><em>Native transparent image generation</em></p>
+
+<p align="center">
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-15.png" width="100%"/>
+</p>
+<p align="center"><em>Group photograph generated from six portrait references</em></p>
+
+<p align="center">
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-43.png" width="48%"/>
+<img src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen-Image/image2.1/images/example-44.png" width="48%"/>
+</p>
+<p align="center"><em>Text rendering</em></p>
+
+## License
+
+This model is licensed under the [Qwen Research License Agreement](./LICENSE).
+