Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,14 @@ 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
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+assets/DMDR.webp filter=lfs diff=lfs merge=lfs -text
+assets/architecture.webp filter=lfs diff=lfs merge=lfs -text
+assets/decoupled-dmd.webp filter=lfs diff=lfs merge=lfs -text
+assets/reasoning.png filter=lfs diff=lfs merge=lfs -text
+assets/showcase.jpg filter=lfs diff=lfs merge=lfs -text
+assets/showcase_editing.png filter=lfs diff=lfs merge=lfs -text
+assets/showcase_realistic.png filter=lfs diff=lfs merge=lfs -text
+assets/showcase_rendering.png filter=lfs diff=lfs merge=lfs -text
+assets/Z-Image-Gallery.pdf filter=lfs diff=lfs merge=lfs -text
+assets/leaderboard.png filter=lfs diff=lfs merge=lfs -text

LICENSE

@@ -0,0 +1,202 @@
+
+                                 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.

NOTICE

@@ -0,0 +1,9 @@
+Z-Image-Turbo is licensed under the Apache License, Version 2.0.
+Copyright Alibaba Group.
+
+This repository is an unmodified mirror of Tongyi-MAI/Z-Image-Turbo, republished by Unsloth so that a quantised
+checkpoint of this model can source its companion components (VAE, text encoder, tokenizer,
+scheduler) from a single org. The weights are byte for byte those of the source repository.
+Not an official Tongyi product and not endorsed by Tongyi.
+
+See LICENSE for the full terms, which are the upstream terms and are unchanged.

README.md

@@ -0,0 +1,205 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-to-image
+library_name: diffusers
+---
+> Mirror of [Tongyi-MAI/Z-Image-Turbo](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo), republished by Unsloth. The weights
+> are unmodified. See NOTICE and the licence file in this repo for the terms, which are
+> the upstream terms and are unchanged.
+
+
+
+
+<h1 align="center">⚡️- Image<br><sub><sup>An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer</sup></sub></h1>
+
+<div align="center">
+
+[![Official Site](https://img.shields.io/badge/Official%20Site-333399.svg?logo=homepage)](https://tongyi-mai.github.io/Z-Image-blog/)&#160;
+[![GitHub](https://img.shields.io/badge/GitHub-Z--Image-181717?logo=github&logoColor=white)](https://github.com/Tongyi-MAI/Z-Image)&#160;
+[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Checkpoint-Z--Image--Turbo-yellow)](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo)&#160;
+[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Online_Demo-Z--Image--Turbo-blue)](https://huggingface.co/spaces/Tongyi-MAI/Z-Image-Turbo)&#160;
+[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Mobile_Demo-Z--Image--Turbo-red)](https://huggingface.co/spaces/akhaliq/Z-Image-Turbo)&#160;
+[![ModelScope Model](https://img.shields.io/badge/🤖%20Checkpoint-Z--Image--Turbo-624aff)](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo)&#160;
+[![ModelScope Space](https://img.shields.io/badge/🤖%20Online_Demo-Z--Image--Turbo-17c7a7)](https://www.modelscope.cn/aigc/imageGeneration?tab=advanced&versionId=469191&modelType=Checkpoint&sdVersion=Z_IMAGE_TURBO&modelUrl=modelscope%3A%2F%2FTongyi-MAI%2FZ-Image-Turbo%3Frevision%3Dmaster)&#160;
+[![Art Gallery PDF](https://img.shields.io/badge/%F0%9F%96%BC%20Art_Gallery-PDF-ff69b4)](assets/Z-Image-Gallery.pdf)&#160;
+[![Web Art Gallery](https://img.shields.io/badge/%F0%9F%8C%90%20Web_Art_Gallery-online-00bfff)](https://modelscope.cn/studios/Tongyi-MAI/Z-Image-Gallery/summary)&#160;
+<a href="https://arxiv.org/abs/2511.22699" target="_blank"><img src="https://img.shields.io/badge/Report-b5212f.svg?logo=arxiv" height="21px"></a>
+
+
+Welcome to the official repository for the Z-Image（造相）project!
+
+</div>
+
+
+
+## ✨ Z-Image
+
+Z-Image is a powerful and highly efficient image generation model family with **6B** parameters. Currently there are four variants:
+
+- 🚀 **Z-Image-Turbo** – A distilled version of Z-Image that matches or exceeds leading competitors with only **8 NFEs** (Number of Function Evaluations). It offers **⚡️sub-second inference latency⚡️** on enterprise-grade H800 GPUs and fits comfortably within **16G VRAM consumer devices**. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence.
+
+- 🎨 **Z-Image** – The foundation model behind Z-Image-Turbo. Z-Image focuses on **high-quality generation**, **rich aesthetics**, **strong diversity**, and **controllability**, well-suited for creative generation, **fine-tuning**, and downstream development. It supports a wide range of artistic styles, effective negative prompting, and high diversity across identities, poses, compositions, and layouts.
+
+- 🧱 **Z-Image-Omni-Base** – The versatile foundation model capable of both **generation and editing tasks**. By releasing this checkpoint, we aim to unlock the full potential for community-driven fine-tuning and custom development, providing the most "raw" and diverse starting point for the open-source community.
+
+- ✍️ **Z-Image-Edit** – A variant fine-tuned on Z-Image specifically for image editing tasks. It supports creative image-to-image generation with impressive instruction-following capabilities, allowing for precise edits based on natural language prompts.
+
+### 📥 Model Zoo
+
+| Model | Pre-Training | SFT | RL | Step | CFG | Task | Visual Quality | Diversity | Fine-Tunability | Hugging Face | ModelScope |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
+| **Z-Image-Omni-Base** | ✅ | ❌ | ❌ | 50 | ✅ | Gen. / Editing | Medium | High | Easy | *To be released* | *To be released* |
+| **Z-Image** | ✅ | ✅ | ❌ | 50 | ✅ | Gen. | High | Medium | Easy | [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Checkpoint%20-Z--Image-yellow)](https://huggingface.co/Tongyi-MAI/Z-Image) <br> [![Hugging Face Space](https://img.shields.io/badge/%F0%9F%A4%97%20Demo-Z--Image-blue)](https://huggingface.co/spaces/Tongyi-MAI/Z-Image) | [![ModelScope Model](https://img.shields.io/badge/🤖%20%20Checkpoint-Z--Image-624aff)](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image) <br> [![ModelScope Space](https://img.shields.io/badge/%F0%9F%A4%96%20Demo-Z--Image-17c7a7)](https://www.modelscope.cn/aigc/imageGeneration?tab=advanced&versionId=569345&modelType=Checkpoint&sdVersion=Z_IMAGE&modelUrl=modelscope%3A%2F%2FTongyi-MAI%2FZ-Image%3Frevision%3Dmaster) |
+| **Z-Image-Turbo** | ✅ | ✅ | ✅ | 8 | ❌ | Gen. | Very High | Low | N/A | [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Checkpoint%20-Z--Image--Turbo-yellow)](https://huggingface.co/Tongyi-MAI/Z-Image-Turbo) <br> [![Hugging Face Space](https://img.shields.io/badge/%F0%9F%A4%97%20Demo-Z--Image--Turbo-blue)](https://huggingface.co/spaces/Tongyi-MAI/Z-Image-Turbo) | [![ModelScope Model](https://img.shields.io/badge/🤖%20%20Checkpoint-Z--Image--Turbo-624aff)](https://www.modelscope.cn/models/Tongyi-MAI/Z-Image-Turbo) <br> [![ModelScope Space](https://img.shields.io/badge/%F0%9F%A4%96%20Demo-Z--Image--Turbo-17c7a7)](https://www.modelscope.cn/aigc/imageGeneration?tab=advanced&versionId=469191&modelType=Checkpoint&sdVersion=Z_IMAGE_TURBO&modelUrl=modelscope%3A%2F%2FTongyi-MAI%2FZ-Image-Turbo%3Frevision%3Dmaster) |
+| **Z-Image-Edit** | ✅ | ✅ | ❌ | 50 | ✅ | Editing | High | Medium | Easy | *To be released* | *To be released* |                                                                                                                                                                                                                                                                                           | *To be released*                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+
+### 🖼️ Showcase
+
+📸 **Photorealistic Quality**: **Z-Image-Turbo** delivers strong photorealistic image generation while maintaining excellent aesthetic quality.
+
+![Showcase of Z-Image on Photo-realistic image Generation](assets/showcase_realistic.png)
+
+📖 **Accurate Bilingual Text Rendering**: **Z-Image-Turbo** excels at accurately rendering complex Chinese and English text.
+
+![Showcase of Z-Image on Bilingual Text Rendering](assets/showcase_rendering.png)
+
+💡  **Prompt Enhancing & Reasoning**: Prompt Enhancer empowers the model with reasoning capabilities, enabling it to transcend surface-level descriptions and tap into underlying world knowledge.
+
+![reasoning.jpg](assets/reasoning.png)
+
+🧠 **Creative Image Editing**: **Z-Image-Edit** shows a strong understanding of bilingual editing instructions, enabling imaginative and flexible image transformations.
+
+![Showcase of Z-Image-Edit on Image Editing](assets/showcase_editing.png)
+
+### 🏗️ Model Architecture
+We adopt a **Scalable Single-Stream DiT** (S3-DiT) architecture. In this setup, text, visual semantic tokens, and image VAE tokens are concatenated at the sequence level to serve as a unified input stream, maximizing parameter efficiency compared to dual-stream approaches.
+
+![Architecture of Z-Image and Z-Image-Edit](assets/architecture.webp)
+
+### 📈 Performance
+According to the Elo-based Human Preference Evaluation (on [*Alibaba AI Arena*](https://aiarena.alibaba-inc.com/corpora/arena/leaderboard?arenaType=T2I)), Z-Image-Turbo shows highly competitive performance against other leading models, while achieving state-of-the-art results among open-source models.
+
+<p align="center">
+  <a href="https://aiarena.alibaba-inc.com/corpora/arena/leaderboard?arenaType=T2I">
+    <img src="assets/leaderboard.png" alt="Z-Image Elo Rating on AI Arena"/><br />
+    <span style="font-size:1.05em; cursor:pointer; text-decoration:underline;"> Click to view the full leaderboard</span>
+  </a>
+</p>
+
+### 🚀 Quick Start
+Install the latest version of diffusers, use the following command:
+<details>
+  <summary><sup>Click here for details for why you need to install diffusers from source</sup></summary>
+
+  We have submitted two pull requests ([#12703](https://github.com/huggingface/diffusers/pull/12703) and [#12715](https://github.com/huggingface/diffusers/pull/12715)) to the 🤗 diffusers repository to add support for Z-Image. Both PRs have been merged into the latest official diffusers release.
+  Therefore, you need to install diffusers from source for the latest features and Z-Image support.
+
+</details>
+
+```bash
+pip install git+https://github.com/huggingface/diffusers
+```
+
+```python
+import torch
+from diffusers import ZImagePipeline
+
+# 1. Load the pipeline
+# Use bfloat16 for optimal performance on supported GPUs
+pipe = ZImagePipeline.from_pretrained(
+    "Tongyi-MAI/Z-Image-Turbo",
+    torch_dtype=torch.bfloat16,
+    low_cpu_mem_usage=False,
+)
+pipe.to("cuda")
+
+# [Optional] Attention Backend
+# Diffusers uses SDPA by default. Switch to Flash Attention for better efficiency if supported:
+# pipe.transformer.set_attention_backend("flash")    # Enable Flash-Attention-2
+# pipe.transformer.set_attention_backend("_flash_3") # Enable Flash-Attention-3
+
+# [Optional] Model Compilation
+# Compiling the DiT model accelerates inference, but the first run will take longer to compile.
+# pipe.transformer.compile()
+
+# [Optional] CPU Offloading
+# Enable CPU offloading for memory-constrained devices.
+# pipe.enable_model_cpu_offload()
+
+prompt = "Young Chinese woman in red Hanfu, intricate embroidery. Impeccable makeup, red floral forehead pattern. Elaborate high bun, golden phoenix headdress, red flowers, beads. Holds round folding fan with lady, trees, bird. Neon lightning-bolt lamp (⚡️), bright yellow glow, above extended left palm. Soft-lit outdoor night background, silhouetted tiered pagoda (西安大雁塔), blurred colorful distant lights."
+
+# 2. Generate Image
+image = pipe(
+    prompt=prompt,
+    height=1024,
+    width=1024,
+    num_inference_steps=9,  # This actually results in 8 DiT forwards
+    guidance_scale=0.0,     # Guidance should be 0 for the Turbo models
+    generator=torch.Generator("cuda").manual_seed(42),
+).images[0]
+
+image.save("example.png")
+```
+
+## 🔬 Decoupled-DMD: The Acceleration Magic Behind Z-Image
+
+[![arXiv](https://img.shields.io/badge/arXiv-2511.22677-b31b1b.svg)](https://arxiv.org/abs/2511.22677)
+
+Decoupled-DMD is the core few-step distillation algorithm that empowers the 8-step Z-Image model.
+
+Our core insight in Decoupled-DMD  is that the success of existing DMD (Distributaion Matching Distillation) methods is the result of two independent, collaborating mechanisms:
+
+-   **CFG Augmentation (CA)**: The primary **engine** 🚀 driving the distillation process, a factor largely overlooked in previous work.
+-   **Distribution Matching (DM)**: Acts more as a **regularizer** ⚖️, ensuring the stability and quality of the generated output.
+
+By recognizing and decoupling these two mechanisms, we were able to study and optimize them in isolation. This ultimately motivated us to develop an improved distillation process that significantly enhances the performance of few-step generation.
+
+![Diagram of Decoupled-DMD](assets/decoupled-dmd.webp)
+
+## 🤖 DMDR: Fusing DMD with Reinforcement Learning
+
+[![arXiv](https://img.shields.io/badge/arXiv-2511.13649-b31b1b.svg)](https://arxiv.org/abs/2511.13649)
+
+Building upon the strong foundation of Decoupled-DMD, our 8-step Z-Image model has already demonstrated exceptional capabilities. To achieve further improvements in terms of semantic alignment, aesthetic quality, and structural coherence—while producing images with richer high-frequency details—we present **DMDR**.
+
+Our core insight behind DMDR is that Reinforcement Learning (RL) and Distribution Matching Distillation (DMD) can be synergistically integrated during the post-training of few-step models. We demonstrate that:
+
+-   **RL Unlocks the Performance of DMD** 🚀
+-   **DMD Effectively Regularizes RL** ⚖️
+
+![Diagram of DMDR](assets/DMDR.webp)
+
+## ⏬ Download
+```bash
+pip install -U huggingface_hub
+HF_XET_HIGH_PERFORMANCE=1 hf download Tongyi-MAI/Z-Image-Turbo
+```
+
+## 📜 Citation
+
+If you find our work useful in your research, please consider citing:
+
+```bibtex
+@article{team2025zimage,
+  title={Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer},
+  author={Z-Image Team},
+  journal={arXiv preprint arXiv:2511.22699},
+  year={2025}
+}
+
+@article{liu2025decoupled,
+  title={Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield},
+  author={Dongyang Liu and Peng Gao and David Liu and Ruoyi Du and Zhen Li and Qilong Wu and Xin Jin and Sihan Cao and Shifeng Zhang and Hongsheng Li and Steven Hoi},
+  journal={arXiv preprint arXiv:2511.22677},
+  year={2025}
+}
+
+@article{jiang2025distribution,
+  title={Distribution Matching Distillation Meets Reinforcement Learning},
+  author={Jiang, Dengyang and Liu, Dongyang and Wang, Zanyi and Wu, Qilong and Jin, Xin and Liu, David and Li, Zhen and Wang, Mengmeng and Gao, Peng and Yang, Harry},
+  journal={arXiv preprint arXiv:2511.13649},
+  year={2025}
+}
+```

assets/Z-Image-Gallery.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f9895b3246d2547bac74bbe0be975da500eaae93f2cad4248ad3281786b1ac6
+size 15767436

model_index.json

@@ -0,0 +1,24 @@
+{
+    "_class_name": "ZImagePipeline",
+    "_diffusers_version": "0.36.0.dev0",
+    "scheduler": [
+        "diffusers",
+        "FlowMatchEulerDiscreteScheduler"
+    ],
+    "text_encoder": [
+        "transformers",
+        "Qwen3Model"
+    ],
+    "tokenizer": [
+        "transformers",
+        "Qwen2Tokenizer"
+    ],
+    "transformer": [
+        "diffusers",
+        "ZImageTransformer2DModel"
+    ],
+    "vae": [
+        "diffusers",
+        "AutoencoderKL"
+    ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,7 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.36.0.dev0",
+  "num_train_timesteps": 1000,
+  "use_dynamic_shifting": false,
+  "shift": 3.0
+}

text_encoder/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

text_encoder/generation_config.json

@@ -0,0 +1,13 @@
+{
+    "bos_token_id": 151643,
+    "do_sample": true,
+    "eos_token_id": [
+        151645,
+        151643
+    ],
+    "pad_token_id": 151643,
+    "temperature": 0.6,
+    "top_k": 20,
+    "top_p": 0.95,
+    "transformers_version": "4.51.0"
+}

text_encoder/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328a91d3122359d5547f9d79521205bc0a46e1f79a792dfe650e99fc2d651223
+size 3957900840

text_encoder/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cd087b316306a68c562436b5492edbcf6e16c6dba3a1308279caa5a58e21ca5
+size 3987450520

text_encoder/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ca841ee75b9c61267c0c6148fd8d096d3d21b6d3e161256a9b878154f91fc52
+size 99630640

text_encoder/model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

transformer/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "ZImageTransformer2DModel",
+  "_diffusers_version": "0.36.0.dev0",
+  "all_f_patch_size": [
+    1
+  ],
+  "all_patch_size": [
+    2
+  ],
+  "axes_dims": [
+    32,
+    48,
+    48
+  ],
+  "axes_lens": [
+    1536,
+    512,
+    512
+  ],
+  "cap_feat_dim": 2560,
+  "dim": 3840,
+  "in_channels": 16,
+  "n_heads": 30,
+  "n_kv_heads": 30,
+  "n_layers": 30,
+  "n_refiner_layers": 2,
+  "norm_eps": 1e-05,
+  "qk_norm": true,
+  "rope_theta": 256.0,
+  "t_scale": 1000.0
+}

transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95facd593e2549e8252acb571c653d57f7ddb7f1060d4e81712f152555a88804
+size 9973693184

transformer/diffusion_pytorch_model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4bbe43ee184a1fb5af4b412d27555f532893bdc3165b1149e304ed82b5d7015
+size 9973714824

transformer/diffusion_pytorch_model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba4e37a590e63210878160a718d916d80398f4e1f78ab6c9b2b2a00d92769fa
+size 4672282880

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,528 @@
+{
+  "metadata": {
+    "total_size": 24619634944
+  },
+  "weight_map": {
+    "all_final_layer.2-1.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "all_final_layer.2-1.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "all_final_layer.2-1.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "all_final_layer.2-1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "all_x_embedder.2-1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "all_x_embedder.2-1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "cap_embedder.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "cap_embedder.1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "cap_embedder.1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "cap_pad_token": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "context_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.10.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.10.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.11.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.12.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.13.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.14.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.15.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.16.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.17.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.18.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.19.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.2.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.2.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.20.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.20.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.21.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.22.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.23.adaLN_modulation.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.23.adaLN_modulation.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.23.attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.23.attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.23.attention.to_k.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.23.attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.23.attention.to_q.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.23.attention.to_v.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.23.attention_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.23.attention_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.23.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.23.feed_forward.w2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.23.feed_forward.w3.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.23.ffn_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.23.ffn_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.adaLN_modulation.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.adaLN_modulation.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.attention.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.attention.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.attention.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.attention.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.attention.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.attention.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.attention_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.attention_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.feed_forward.w1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.feed_forward.w2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.feed_forward.w3.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.ffn_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.24.ffn_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.adaLN_modulation.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.adaLN_modulation.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.attention.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.attention.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.attention.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.attention.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.attention.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.attention.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.attention_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.attention_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.feed_forward.w1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.feed_forward.w2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.feed_forward.w3.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.ffn_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.25.ffn_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.adaLN_modulation.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.adaLN_modulation.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.attention.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.attention.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.attention.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.attention.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.attention.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.attention.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.attention_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.attention_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.feed_forward.w1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.feed_forward.w2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.feed_forward.w3.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.ffn_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.26.ffn_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.adaLN_modulation.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.adaLN_modulation.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.attention.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.attention.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.attention.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.attention.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.attention.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.attention.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.attention_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.attention_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.feed_forward.w1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.feed_forward.w2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.feed_forward.w3.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.ffn_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.27.ffn_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.adaLN_modulation.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.adaLN_modulation.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.attention.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.attention.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.attention.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.attention.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.attention.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.attention.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.attention_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.attention_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.feed_forward.w1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.feed_forward.w2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.feed_forward.w3.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.ffn_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.28.ffn_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.adaLN_modulation.0.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.adaLN_modulation.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.attention.norm_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.attention.norm_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.attention.to_k.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.attention.to_out.0.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.attention.to_q.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.attention.to_v.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.attention_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.attention_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.feed_forward.w1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.feed_forward.w2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.feed_forward.w3.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.ffn_norm1.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.29.ffn_norm2.weight": "diffusion_pytorch_model-00003-of-00003.safetensors",
+    "layers.3.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.3.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.4.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.5.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.6.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.7.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.8.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.9.adaLN_modulation.0.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.9.adaLN_modulation.0.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.9.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.9.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.9.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.9.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.9.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.9.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.9.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.9.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.9.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.9.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "layers.9.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.9.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "layers.9.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
+    "noise_refiner.0.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.adaLN_modulation.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.adaLN_modulation.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.attention.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.attention.to_q.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.attention.to_v.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "noise_refiner.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "t_embedder.mlp.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "t_embedder.mlp.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "t_embedder.mlp.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "t_embedder.mlp.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "x_pad_token": "diffusion_pytorch_model-00001-of-00003.safetensors"
+  }
+}

vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.36.0.dev0",
+  "_name_or_path": "flux-dev",
+  "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": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.3611,
+  "shift_factor": 0.1159,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": false,
+  "use_quant_conv": false
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b59a26851551b67ae1fe58d32e76486e1e812def4696a4bea97f16604d40a3
+size 167666902