init

.gitattributes

@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+emi.safetensors filter=lfs diff=lfs merge=lfs -text
+emi_stable.safetensors filter=lfs diff=lfs merge=lfs -text
+unet/diffusion_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text
+vae/diffusion_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text
+text_encoder/model.safetensors filter=lfs diff=lfs merge=lfs -text
+text_encoder_2/model.safetensors filter=lfs diff=lfs merge=lfs -text
+example_2.png filter=lfs diff=lfs merge=lfs -text
+example_4.png filter=lfs diff=lfs merge=lfs -text
+eyecatch.png filter=lfs diff=lfs merge=lfs -text
+example_1.jpg filter=lfs diff=lfs merge=lfs -text
+example_3.jpg filter=lfs diff=lfs merge=lfs -text
+eyecatch.jpg filter=lfs diff=lfs merge=lfs -text

LICENSE.md

@@ -0,0 +1,59 @@
+Copyright (c) 2023 AI Picasso Inc.
+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).

README.md

@@ -1,3 +1,226 @@
 ---
 license: openrail++
+tags:
+- stable-diffusion
+- text-to-image
+inference: false
+library_name: diffusers
 ---
+
+# Emi Model Card
+
+**このリポジトリはオリジナルのクローンです。最新のバージョンを落とすためにも、できる限り本のリポジトリから落としてください。**
+**This repository is clone of the original. Please use the original repository to use latest version as possible.**
+
+![eyecatch.jpg](eyecatch.jpg)
+[Original(PNG)](eyecatch.png)
+
+English: [Click Here](README_en.md)
+
+# はじめに
+Emi (Ethereal master of illustration) は、
+最先端の開発機材H100と画像生成Stable Diffusion XL 1.0を用いて
+AI Picasso社が開発したAIアートに特化した画像生成AIです。
+このモデルの特徴として、Danbooruなどにある無断転載画像を学習していないことがあげられます。
+
+# ライセンスについて
+ライセンスについては、これまでとは違い、 CreativeML Open RAIL++-M License です。
+したがって、**商用利用可能**です。
+これは次のように判断したためです。
+- 画像生成AIが普及するに伴い、創作業界に悪影響を及ぼさないように、マナーを守る人が増えてきたため
+- 他の画像生成AIが商用可能である以上、あまり非商用ライセンスである実効性がなくなってきたため
+
+# 使い方
+[ここ](https://huggingface.co/spaces/aipicasso/emi-latest-demo)からデモを利用することができます。
+本格的に利用する人は[ここ](emi.safetensors)からモデルをダウンロードできます。
+通常版で生成がうまく行かない場合は、[安定版](emi_stable.safetensors)をお使いください。
+
+# シンプルな作品例
+
+
+![example_1.jpg](example_1.jpg)
+
+```
+positive prompt: anime artwork, anime style, (1girl), (black bob hair:1.5), brown eyes, red maples, sky, ((transparent))
+negative prompt: (embedding:unaestheticXLv31:0.5), photo, deformed, realism, disfigured, low contrast, bad hand
+```
+
+![example_2.png](example_2.png)
+
+```
+positive prompt: monochrome, black and white, (japanese manga), mount fuji
+negative prompt: (embedding:unaestheticXLv31:0.5), photo, deformed, realism, disfigured, low contrast, bad hand
+```
+
+![example_3.jpg](example_3.jpg)
+```
+positive prompt: (1man), focus, white wavy short hair, blue eyes, black shirt, white background, simple background
+negative prompt: (embedding:unaestheticXLv31:0.5), photo, deformed, realism, disfigured, low contrast, bad hand
+```
+
+# モデルの出力向上について
+- プロンプトにtransparentという言葉を入れると、より最近の画風になります。
+- 全身 (full body) を描くとうまく行かない場合もあるため、そのときは[安定版](emi_stable.safetensors)をお試しください。
+- 使えるプロンプトはWaifu Diffusionと同じです。また、Stable Diffusionのように使うこともできます。
+- ネガティブプロンプトに[Textual Inversion](https://civitai.com/models/119032/unaestheticxl-or-negative-ti)を使用することをおすすめします。
+- 手が不安定なため、[DreamShaper XL1.0](https://civitai.com/models/112902?modelVersionId=126688)などの実写系モデルとのマージをおすすめします。
+- ChatGPTを用いてプロンプトを洗練すると、自分の枠を超えた作品に出会えます。
+- 最新のComfyUIにあるFreeUノードを次のパラメータで使うとさらに出力が上がる可能性があります。次の画像はFreeUを使った例です。
+	- b1 = 1.1, b2 = 1.2, s1 = 0.6, s2 = 0.4 [report](https://wandb.ai/nasirk24/UNET-FreeU-SDXL/reports/FreeU-SDXL-Optimal-Parameters--Vmlldzo1NDg4NTUw)
+
+
+![example_4.png](example_4.png)
+
+# 法律について
+本モデルは日本にて作成されました。したがって、日本の法律が適用されます。
+本モデルの学習は、著作権法第30条の4に基づき、合法であると主張します。
+また、本モデルの配布については、著作権法や刑法175条に照らしてみても、
+正犯や幇助犯にも該当しないと主張します。詳しくは柿沼弁護士の[見解](https://twitter.com/tka0120/status/1601483633436393473?s=20&t=yvM9EX0Em-_7lh8NJln3IQ)を御覧ください。
+ただし、ライセンスにもある通り、本モデルの生成物は各種法令に従って取り扱って下さい。
+
+# 連絡先
+support@aipicasso.app
+
+以下、一般的なモデルカードの日本語訳です。
+
+## モデル詳細
+- **モデルタイプ:** 拡散モデルベースの text-to-image 生成モデル
+- **言語:** 日本語
+- **ライセンス:** [CreativeML Open RAIL++-M License](LICENSE.md)
+- **モデルの説明:** このモデルはプロンプトに応じて適切な画像を生成することができます。アルゴリズムは [Latent Diffusion Model](https://arxiv.org/abs/2307.01952) と [OpenCLIP-ViT/G](https://github.com/mlfoundations/open_clip)、[CLIP-L](https://github.com/openai/CLIP) です。
+- **補足:**
+- **参考文献:**
+```bibtex
+@misc{podell2023sdxl,
+      title={SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis}, 
+      author={Dustin Podell and Zion English and Kyle Lacey and Andreas Blattmann and Tim Dockhorn and Jonas Müller and Joe Penna and Robin Rombach},
+      year={2023},
+      eprint={2307.01952},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```
+
+## モデルの使用例
+
+Stable Diffusion XL 1.0と同じ使い方です。
+たくさんの方法がありますが、3つのパターンを提供します。
+- ComfyUI
+- Fooocus
+- Diffusers
+
+### ComfyUIやFooocusの場合
+
+Stable Diffusion XL 1.0 の使い方と同じく、safetensor形式のモデルファイルを使ってください。
+詳しいインストール方法は、[こちらの記事](https://note.com/it_navi/n/n723d93bedd64)を参照してください。
+
+### Diffusersの場合
+
+[🤗's Diffusers library](https://github.com/huggingface/diffusers) を使ってください。
+
+まずは、以下のスクリプトを実行し、ライブラリをいれてください。
+
+```bash
+pip install invisible_watermark transformers accelerate safetensors　diffusers
+```
+
+次のスクリプトを実行し、画像を生成してください。
+
+```python
+from diffusers import StableDiffusionXLPipeline, EulerAncestralDiscreteScheduler
+import torch
+
+model_id = "aipicasso/emi"
+
+scheduler = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
+pipe = StableDiffusionXLPipeline.from_pretrained(model_id, scheduler=scheduler, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+
+prompt = "1girl, sunflowers, brown bob hair, brown eyes, sky, transparent"
+images = pipe(prompt, num_inference_steps=20).images
+images[0].save("girl.png")
+
+```
+
+複雑な操作は[デモのソースコード](https://huggingface.co/spaces/aipicasso/emi-latest-demo/blob/main/app.py)を参考にしてください。
+
+#### 想定される用途
+- イラストや漫画、アニメの作画補助
+  - 商用・非商用は問わない
+- 依頼の際のクリエイターとのコミュニケーション 
+- 画像生成サービスの商用提供
+  - 生成物の取り扱いには注意して使ってください。
+- 自己表現
+    - このAIを使い、「あなた」らしさを発信すること
+- 研究開発
+    - Discord上でのモデルの利用
+        - プロンプトエンジニアリング
+        - ファインチューニング（追加学習とも）
+            - DreamBooth など
+        - 他のモデルとのマージ
+    - 本モデルの性能をFIDなどで調べること
+    - 本モデルがStable Diffusion以外のモデルとは独立であることをチェックサムやハッシュ関数などで調べること
+- 教育
+    - 美大生や専門学校生の卒業制作
+    - 大学生の卒業論文や課題制作
+    - 先生が画像生成AIの現状を伝えること
+- Hugging Face の Community にかいてある用途
+    - 日本語か英語で質問してください
+
+#### 想定されない用途
+- 物事を事実として表現するようなこと
+- 先生を困らせるようなこと
+- その他、創作業界に悪影響を及ぼすこと
+
+# 使用してはいけない用途や悪意のある用途
+- マネー・ロンダリングに用いないでください
+- デジタル贋作 ([Digital Forgery](https://arxiv.org/abs/2212.03860)) は公開しないでください（著作権法に違反するおそれ）
+- 他人の作品を無断でImage-to-Imageしないでください（著作権法に違反するおそれ）
+- わいせつ物を頒布しないでください (刑法175条に違反するおそれ）
+    - いわゆる業界のマナーを守らないようなこと
+- 事実に基づかないことを事実のように語らないようにしてください（威力業務妨害罪が適用されるおそれ）
+    - フェイクニュース
+
+## モデルの限界やバイアス
+
+### モデルの限界
+
+- 拡散モデルや大規模言語モデルは、いまだに未知の部分が多く、その限界は判明していない。
+
+### バイアス
+
+- 拡散モデルや大規模言語モデルは、いまだに未知の部分が多く、バイアスは判明していない。
+
+## 学習
+
+**学習データ**
+
+- Stable Diffusionと同様のデータセットからDanbooruの無断転載画像を取り除いて手動で集めた約2000枚の画像
+- Stable Diffusionと同様のデータセットからDanbooruの無断転載画像を取り除いて自動で集めた約50万枚の画像
+
+**学習プロセス**
+
+- **ハードウェア:** H100
+
+## 評価結果
+
+第三者による評価を求めています。
+
+## 環境への影響
+
+- **ハードウェアタイプ:** H100
+- **使用時間（単位は時間）:** 500
+- **学習した場所:** 日本
+
+## 参考文献
+
+```bibtex
+@misc{podell2023sdxl,
+      title={SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis}, 
+      author={Dustin Podell and Zion English and Kyle Lacey and Andreas Blattmann and Tim Dockhorn and Jonas Müller and Joe Penna and Robin Rombach},
+      year={2023},
+      eprint={2307.01952},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```

README_en.md

@@ -0,0 +1,54 @@
+# Emi Model Card
+
+![eyecatch.png](eyecatch.png)
+
+# Introduction
+Emi (Ethereal master of illustration) is a text-to-image specialized in AI Art by AI Picasso Inc. using H100 and SDXL 1.0.
+Emi is NOT made of unauthorized reproduction images on Danbooru.
+
+# Licence
+Emi's licence is CreativeML Open RAIL++-M License.
+Therefore, you can use Emi for **commercial purpose**.
+
+# Usage
+[Click Here](https://huggingface.co/spaces/aipicasso/emi-latest-demo) to use Demo..
+
+[Click Here](emi.safetensors) to get Emi.
+
+[Click Here](emi.safetensors) to get Emi stable.
+
+# Examples
+
+
+![example_1.jpg](example_1.jpg)
+
+```
+positive prompt: anime artwork, anime style, (1girl), (black bob hair:1.5), brown eyes, red maples, sky, ((transparent))
+negative prompt: (embedding:unaestheticXLv31:0.5), photo, deformed, realism, disfigured, low contrast, bad hand
+```
+
+![example_2.png](example_2.png)
+
+```
+positive prompt: monochrome, black and white, (japanese manga), mount fuji
+negative prompt: (embedding:unaestheticXLv31:0.5), photo, deformed, realism, disfigured, low contrast, bad hand
+```
+
+![example_3.jpg](example_3.jpg)
+```
+positive prompt: (1man), focus, white wavy short hair, blue eyes, black shirt, white background, simple background
+negative prompt: (embedding:unaestheticXLv31:0.5), photo, deformed, realism, disfigured, low contrast, bad hand
+```
+
+# Toward improving output
+- Use "transparent" in your prompt.
+- You can use the prompts of Waifu Diffusion and Stable Diffusion.
+- Use [Textual Inversion](https://civitai.com/models/119032/unaestheticxl-or-negative-ti) in your negative prompt.
+- You can use ChatGPT to improve your prompt.
+
+# Legal information
+We made Emi legally in Japan because Japanese government allows to use images for information analysis such as machine learning.
+
+# Contact
+Please feel free to send email: support@aipicasso.app
+

emi.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab8e2059d2c842b7c73dc8f93a7d857ebcbe2214544dc56da962683f7145eb3
+size 6938043538

emi_stable.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c0e2b8f05beb3d606f7651896bfaafe3008ea6e8624fb969029e94a3149c32
+size 6939235916

model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.21.0.dev0",
+  "force_zeros_for_empty_prompt": true,
+  "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"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.21.0.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
+}

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": "4.26.0",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c055a60adab406b88992676cc0d44f010f6c8e2e5d2bea00fa886232d23aa1a
+size 246144864

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": "4.26.0",
+  "vocab_size": 49408
+}

text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbb7eeb5c3205b9d3cbaf8ee77e8c3c22fc23810065a564c23807174959a27c
+size 1389382880

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
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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,
+  "name_or_path": "openai/clip-vit-large-patch14",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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
+  }
+}

tokenizer_2/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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,
+  "name_or_path": "laion/CLIP-ViT-bigG-14-laion2B-39B-b160k",
+  "pad_token": "!",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,70 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.21.0.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
+  ],
+  "attention_type": "default",
+  "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
+}

unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b77a6dd55b6e068b2ad2e99fc0961366ecd8cf922e3615aaf7ea0b06a5e6b73
+size 5135149760

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.21.0.dev0",
+  "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"
+  ]
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7727b5494a1ec3bf57b86c9d0a0f0cb266fba42e6be2840775a6e7347e5a2e5
+size 167335342